openapi.json

{
  "openapi": "3.1.0",
  "info": {
    "title": "Lenz \u2014 AI Fact-Checking API",
    "version": "1.0.0",
    "description": "# Four API calls and one to run them\n\nA research-depth ladder: find claims, judge fast, prove deep, citecheck; `/review` runs them all.\n\n- `POST /extract` \u2014 enumerate every major verifiable claim in a document (up to 100, most check-worthy first, inputs to 50k chars), or in a public web page given its URL; an optional `focus` narrows the list to the claims you care about, and `locate: true` keeps only the claims traced back to the text, with where each is made. Costs no credits; fair-use cap 1,000/account/day.\n- `POST /assess` \u2014 a fast panel verdict, with the pages the reviewers looked at, typically 10-25s. Sync, 1 credit per claim. Send one text in `claim`, or a list of up to 20 in `claims` \u2014 one row per claim, same order, all checked in parallel. A text that makes more claims than one call checks gets the most check-worthy checked and the rest back as `more_claims`, free, to send on.\n- `POST /verify` \u2014 a full investigation, with verified citations, in ~90s. Async, 10 credits \u2014 or 5 with `depth: \"low\"`, a shallower check that comes back sooner.\n- `POST /citecheck` \u2014 does each cited source say what the text attributes to it: send pairs of a statement and its URL or DOI, or a whole text. Async; 1 credit per checked citation, refunded when a citation could not be checked ([guide](https://lenz.io/docs/citations)).\n- `POST /review` \u2014 the extract \u2192 assess \u2192 verify ladder on a whole draft, returning the issues with suggested rewrites in 2-4 min. Async, 1 credit per claim assessed + 10 (5 at `depth: \"low\"`) per claim verified. With `escalate.max_citations` (0-20, default 0) it also checks whether each source the draft cites says what the draft attributes to it, at 1 credit per checked citation (one that could not be checked is refunded) ([guide](https://lenz.io/docs/citations)). `more_claims` and `more_citations` list what the review found and did not check, at no cost; send them to `/assess` and `/citecheck` to check the rest.\n- Also `POST /ask/{id}` \u2014 ask follow-up questions grounded on a verification.\n\n## Built for teams whose AI output is async or document-shaped\n\nLegal-memo generators, AI deep-research, due-diligence platforms, vertical agents producing structured deliverables, \"report-as-a-service\" companies. `/assess` opens the door to sync UX too \u2014 fast enough to gate a chat completion or a UI submit.\n\n## API versions\n\nLenz versions the shape of its responses by date: send `X-Lenz-API-Version: 2026-10-11` to choose this shape. This reference describes `2026-10-11`. A field `2026-05-13` still sends under an older name is listed `deprecated` beside the current one, and where its shape differs, the operation names the `...Legacy` component it receives (`x-lenz-versions` on the response). Every response carries `X-Lenz-API-Version`, naming the version it is in. Which version a request gets without the header, and what changed: [https://lenz.io/docs/api-versions](https://lenz.io/docs/api-versions).\n\n## Install the SDK\n\n```bash\npip install lenz-io      # Python\nnpm install lenz-io      # Node / TypeScript\n```\n\nSource on GitHub: [lenz-io-python](https://github.com/lenzhq/lenz-io-python) \u00b7 [lenz-io-node](https://github.com/lenzhq/lenz-io-node).\n\n## The canonical integration: one /review call\n\n```python\nfrom lenz_io import Lenz\nclient = Lenz(api_key=\"lenz_...\")\n\n# Extract, assess, and verify the doubtful claims in one call (async, 2-4 min)\ndraft = \"The EU AI Act took effect in March 2024. It sorts AI systems into four risk tiers.\"\nreview = client.review_and_wait(text=draft)\nfor i in review.issues:\n    print(i.verdict, i.claim, i.suggested_rewrite)\n```\n\nThe default policy: a quick verdict on every claim (up to 20), and the deep check on the rows whose quick verdict is `False`, `Mostly False`, `Mixed` or `No Public Record`, or whose confidence is `low`, up to five. Change it in `escalate`. To deep-check the rows the cap left out (`escalation.disposition == \"cap\"`), send them to `/verify/batch`. A resend with the same `Idempotency-Key` within 24 hours returns the same review; a new key is a new review.\n\n## The primitives, call by call: extract \u2192 assess \u2192 conditional verify\n\n```python\nfrom lenz_io import Lenz\nclient = Lenz(api_key=\"lenz_...\")\n\n# 1. Enumerate the factual claims in your model output (free)\n# extracted.claims lists every claim found, most check-worthy first:\n# always a list (one entry for one claim, [] for none).\n# Pass focus=\"market size and competitors\" to narrow the list;\n# status is \"no_match\" when the document has claims but none match.\nextracted = client.extract(text=llm_output)\nclaims = [c.claim for c in extracted.claims]\n\n# 2. Fast verdict in ONE call (typically 10-25s, 3-model panel): a list of up\n# to 20, one row per claim, in the order you sent them. extract finds up to\n# 100, most check-worthy first, so this checks the first 20.\nquick = client.assess(claims=claims[:20]).claims if claims else []\n\n# 3. Escalate the low-confidence ones to /verify in one batch (~90s, multi-model pipeline)\n# Failed rows are free. A retryable one (a provider, or the time budget)\n# is worth resending; the rest (no_checkable_claim, internal) are not.\nretry = [c.claim for c in quick if c.failure and c.failure.retryable]\nquick += client.assess(claims=retry).claims if retry else []\ndoubtful = [{\"claim\": c.claim} for c in quick if c.status == \"completed\" and c.confidence == \"low\"]\nfor r in client.verify_batch_and_wait(claims=doubtful) if doubtful else []:\n    if r.verification:\n        print(r.verification.verdict, r.verification.lenz_score, r.verification.key_finding)\n```\n\n## How /verify works under the hood\n\nFrame \u2192 Collect Evidence \u2192 Debate (2 models, 2 rounds) \u2192 Adjudicate (three reviewers on models from different vendors, two more when they disagree) \u2192 Conclude. ~90 seconds wall-clock per claim.\n\n### While /verify is running\n\n`GET /verify/status/{task_id}` answers one of five shapes, keyed on `status`: `processing`, `needs_input`, `completed`, `failed`, and, after you cancel the run (see Stopping a run), `cancelled`. Every one echoes `task_id`, and only the fields belonging to that shape are present \u2014 read the ones for the branch you are in, and treat an absent key as absent rather than empty.\n\nA `processing` body carries `progress`:\n\n```json\n{\"status\": \"processing\", \"task_id\": \"\u2026\",\n \"progress\": {\"step\": \"research\", \"index\": 2, \"total\": 5,\n              \"elapsed_seconds\": 42, \"poll_after_seconds\": 5}}\n```\n\n`step` is a closed set \u2014 `starting`, `framing`, `research`, `debate`, `adjudication`, `conclusion` \u2014 so it is safe to switch on. `index` is the 1-based stage position (0 while `starting`) out of `total`; read `total` off the response rather than hard-coding it. `poll_after_seconds` is how long to wait before looking again, and `elapsed_seconds` is how long the run has been going \u2014 a measurement, not an estimate of what is left.\n\nNote that `index` is stage **position**, not elapsed work: the stages are uneven, so a progress bar driven by it will sit on `research` for roughly half the run.\n\n`progress` is **advisory**. It says the work is pending and which stage it is on; it is not a place to read results from. The verdict arrives once, under `result`, when `status` is `completed`.\n\n### When /verify asks for input\n\n`/verify` is not only submit-and-poll. `GET /verify/status/{task_id}` can terminate at `needs_input` \u2014 the submitted text held several claims, or was too vague to check as written \u2014 and the task waits rather than guessing which claim you meant. Several claims in one sentence count the same as several sentences.\n\nResolve it with `POST /verify/{task_id}/select`, passing the exact wording of the claim(s) you want from the ones the status offered. Selection is **by text, not index**; anything that was not offered is rejected with a 422. Each selected claim fans out into its own pipeline, so the response carries one `task_id` per claim \u2014 poll each the way you would a fresh `/verify`.\n\nClaims returned by `/extract` skip this entirely: submitted verbatim, they are never bounced back for rephrasing.\n\n### Covered verification\n\nEvery verification a paid Pro or Scale account runs is put in front of a gate. The ones that qualify carry a contractual warranty, and every result tells you whether it qualified \u2014 a `coverage` block on the completed `/verify/status/{task_id}` body, on `GET /verifications/{id}` and on the `verification.completed` webhook.\n\nIt is on by default, with no request field to set; an account on Pro or Scale can turn certificates off on the API credentials page, for checks submitted from then on (reason `account`; a verification that already carries a certificate keeps it).\n\n`status` is `covered`, `pending_timestamp` or `uncovered`; `reasons` says why not, in a closed seven-value vocabulary. **If you publish automatically, key on the `certificate.timestamped` webhook, not `verification.completed`** \u2014 cover requires the qualified timestamp to precede what you publish, and `completed` fires while the qualified timestamp is still pending.\n\nFull wire format, the reason vocabulary and the offline verifier: [lenz.io/docs/coverage](https://lenz.io/docs/coverage). What is covered and what is not: [lenz.io/warranty](https://lenz.io/warranty).\n\n### When /verify fails\n\nA `failed` status (and the `verification.failed` webhook) carries a `failure` block. `code` says what a caller can do about it, a closed set: `no_checkable_claim` (send a checkable statement), `upstream_unavailable` (a provider or our own executor failed; retry), `internal` (retrying the same input will not help) and `cancelled`. `detail` is one sentence on the cause (which step stopped, or that the search was unavailable). `failure_class` says **why**, and `retryable` is derived from it:\n\n| `failure_class` | Meaning | `retryable` |\n|---|---|---|\n| `upstream_unavailable` | Model or search providers were rate-limited or down, the search for sources did not finish, or the task was never run \u2014 resubmit after a short wait | `true` |\n| `invalid_input` | Not a checkable claim | `false` |\n| `cancelled` | You stopped it with `POST /verify/{task_id}/cancel`; not charged | `false` |\n| `internal` | Anything else \u2014 retrying the same input will not help | `false` |\n| `insufficient_evidence` | Version `2026-05-13` only: too few sources to judge the claim (`research_empty` / `research_insufficient`); the current version answers such a run with \"No Public Record\" (below) | `false` |\n\nBranch on `retryable`. `failure_class` and `code` are **closed sets**. A failed body also carries `docs_url`, pointing at the explanation of its class. A failed `/verify` is not charged.\n\nVersion `2026-05-13` sends the same facts flat: `failure_reason` (the webhook's `error`) is the same code (`not_a_claim` for `no_checkable_claim`), except `research_empty` / `research_insufficient` with `failure_class: \"insufficient_evidence\"`, which is how that version reads a \"No Public Record\" answer. It used to name the pipeline step (`framing_failed`, `conclusion_failed`, `task_stuck`, \u2026); those now read as the code above.\n\n### When an /assess row, a review or a citation check fails\n\nThe same `failure` block, and one vocabulary for `code`: `no_checkable_claim`, `page_unreadable` (a link /review or /extract was sent could not be read), `upstream_unavailable` (a provider or the time budget; retry), `internal`, `cancelled`, `no_citations` and `insufficient_credits`. `detail` names the cause (out of time, no row could be assessed, ...). Branch on `retryable`, never on a list of codes. Version `2026-05-13` keeps the earlier causes as codes (`timeout`, `framing_failed`, `assessment_failed`, `citation_check_failed`, `invalid_input`), and `/extract` answers an unreadable link with its 502 `extraction_failed` where the current version answers 422 `page_unreadable`.\n\n### No Public Record\n\nA claim whose central assertion no public record in the evidence settles (a private fact, an entity nothing records, a record that would carry it and was not found) completes with `verdict: \"No Public Record\"`, `lenz_score: null` and a `confidence`. It is an answer, charged like a verdict, never warranted and always private (`visibility` is ignored for it). It does not make the claim false. On a review it is an issue (in `issues[]`, with no suggested edit; the review reads `outcome: \"issues_found\"`). Version `2026-05-13` never receives it: it reads such a run as the failure it was before (`research_empty` when no source was found, else `research_insufficient`; `GET /verifications/{id}` answers 409 `verification_failed`; `GET /verifications` leaves it out); a run submitted in that version is not charged for it.\n\nIn the next API version a cancelled run is not a failure: `GET /verify/status/{task_id}` answers `{\"status\": \"cancelled\", \"task_id\": \"\u2026\"}`, and a `webhook_url` receives `verification.cancelled`. A request made in 2026-05-13 keeps `status: \"failed\"` with `failure_class: \"cancelled\"` and receives `verification.failed`.\n\n### Stopping a run\n\n`POST /verify/{task_id}/cancel` stops a verification that has not finished. A cancelled run is not charged and saves no verification; model work already under way is not billed to you, and the run stops at its next step. The call is safe to repeat and answers 200 in every state: `cancelled: true` with `status: \"cancelled\"`, or `cancelled: false` with `status: \"completed\"` (it finished first and was charged as usual) or `\"failed\"`. It needs no `Idempotency-Key`. An unknown task, another account's task and a task not submitted through the API answer 404 `not_found`; a task that is a `/review`'s deep check answers 409 `use_review_cancel`. Each item of a `/verify/batch` has its own `task_id`, so cancel per task; there is no call for a whole batch. `POST /reviews/{review_id}/cancel` and `POST /citechecks/{citecheck_id}/cancel` stop everything in a review or a citation check. They refund the quick checks not yet served and the citations not yet checked, and keep what was delivered charged.\n\nOne of those codes comes from framing rather than from a pipeline step and carries `failure_class: invalid_input`: `no_checkable_claim` (`not_a_claim` in 2026-05-13; the input is not a checkable statement, or is too vague to have a checkable reading). A vague input that has a likely reading is verified on it, and the result's `claim` is that reading. On the webhook the same value rides in `error`, as an ordinary `verification.failed` delivery; before 2026-09-03 it fired nothing at all, so a task submitted with a `webhook_url` could terminate in silence.\n\n### What may change without notice\n\nNew keys may be added to status and webhook bodies at any time \u2014 ignore keys you do not recognise. Fields documented as **advisory** \u2014 `progress` and everything inside it \u2014 may also change or disappear without a version bump. The verdict fields under `result` may not: those change only with a versioned, announced release.\n\n## Common patterns\n\n- **Runtime sync UX**: `POST /assess` on the user-facing path; escalate `confidence == \"low\"` claims to `/verify` in the background.\n- **Runtime webhook**: `POST /verify` with `webhook_url`. Lenz POSTs the typed payload when done. Best for document pipelines.\n- **Whole drafts**: `POST /review` with `webhook_url`; handle `review.completed` (a `ReviewWebhookPayload`, deduped on `event_id`) and read `review.issues[]` and `review.citation_issues[]`.\n- **CI / pre-release**: `/extract` + batch `/verify` your golden set on every deploy. The free `/extract` tier covers most of this. Claims returned by `/extract` verify cleanly \u2014 submitted verbatim to `/verify`, they are never bounced back for rephrasing.\n- **Incident triage**: paste the offending output into `/extract`, then `/verify` the wrong-looking claims. Get a citation trail to send back to the customer.\n\n## What's in the response\n\nUnified vocabulary across every claim-shaped response:\n\n- **`claim`** \u2014 the framed claim text.\n- **`verdict`** \u2014 `\"True\" | \"Mostly True\" | \"Mixed\" | \"Mostly False\" | \"False\"`; a verification or an /assess row can also be `\"No Public Record\"` (see above; an /assess row in version `2026-05-13` never is, and can be `\"Error\"`).\n- **`confidence`** \u2014 `\"high\" | \"medium\" | \"low\"`.\n- **`lenz_score`** \u2014 1\u201310 integer score (deep payloads); `null` for `\"No Public Record\"`.\n- **`key_finding`** \u2014 one declarative sentence stating the most important fact the analysis established. For a false claim it states the CORRECTED fact rather than restating the claim, so render it next to the verdict label, never as a standalone headline. `\"\"` on older verifications predating the field.\n- **`suggested_rewrite`** \u2014 a suggested rewrite of `claim` that the verification's findings support. It has not been verified itself: before using it, review it or run it through `/verify`. `null` for a true claim, when no correction is established, and on older verifications. On every verification, single or listed (`GET /verifications/{id}`, `/verify/status`, the `verification.completed` webhook, `GET /verifications`, `GET /library`). On `/assess` rows too when the request sets `suggest_rewrite`: written from the quick check's reasoning for a claim it found False or Mostly False with high confidence, at no extra credit; `null` otherwise, and on every row when not requested.\n- **`sources`** \u2014 evidence with title, URL and snippet: the sentence(s) quoted from the page, verbatim and in the page's own language (`/verify` only).\n- **`audit`** \u2014 adjudication reasoning, debate transcript, panel agreement (`/verify` only).\n\n## How the API is organized\n\n- **Extract** \u2014 pull verifiable claims out of text.\n- **Assess** \u2014 a fast verdict, with the pages the reviewers looked at.\n- **Verify** \u2014 the full investigation: submit one claim or a batch, poll status, and resolve a `needs_input` interrupt by selecting claims.\n- **Verifications** \u2014 list, fetch, delete, and toggle visibility on stored verifications.\n- **Library** \u2014 browse the public catalog. No API key needed.\n- **Ask** \u2014 follow-up questions, 1 credit each.\n- **Account** \u2014 your credit balance and the price list.\n\n## Credits\n\nOne pool per account funds every billable call, at a fixed weight:\n\n| Endpoint | Credits |\n|---|---|\n| `POST /verify` (and `/verify/batch`, `/select`) | 10 per claim |\n| `POST /verify` with `depth: \"low\"` | 5 per claim |\n| `POST /assess` | 1 per claim \u2014 per row that carries a verdict; error rows and rows answered from the cache are free |\n| `POST /ask` | 1 |\n| `POST /extract` | 0 \u2014 free, fair-use capped |\n\n`depth: \"low\"` caps research breadth \u2014 fewer discovery queries, a hard extraction ceiling, no recovery tiers on the happy path \u2014 while every reasoning step runs unchanged. It is not a model downgrade. You are charged for the depth you REQUESTED. A `/verify/batch` may mix depths per item and is billed per item.\n\nAn answer served from the last hour's cache is free: a `/verify`, `/assess` or `/review` claim that gets back a verdict checked in the last hour costs nothing, so a tool that resends a request is not charged twice. The exception is a `/verify` that issues you a new warranty certificate, charged at the depth you requested.\n\n`GET /me/usage` reports the balance under `credits` and the weights under `costs`, with parameter-dependent prices such as `depth` nested under `cost_options`. In version `2026-05-13` the per-capability blocks beside them (`verify`, `assess`, `ask`) are **projections** of that one balance into each capability's own unit \u2014 how many of those calls the remaining credits would buy \u2014 not separate allowances. Spending on any one of them moves all of them.\n\n## Authentication\n\n1. [Create a Lenz account](https://lenz.io/auth).\n2. Generate an API key on the [API credentials](https://lenz.io/api-credentials) page.\n3. Send it on every request:\n   ```\n   Authorization: Bearer lenz_...\n   ```\n\nOr skip steps 1\u20132: **[lenz.io/setup](https://lenz.io/setup)** issues a test key and generates setup instructions for your environment \u2014 MCP client, SDK or plain HTTP \u2014 that you paste into your coding agent to do the wiring.\n\n### One balance, whichever door you come through\n\nLenz also runs a remote MCP server at `https://lenz.io/mcp`, so an agent can fact-check inside a conversation. It is **not** part of this surface \u2014 there are no MCP endpoints below, and its tools are documented at [lenz.io/integrations/mcp-server](https://lenz.io/integrations/mcp-server).\n\nIt matters here for one reason: that server is a client of this API. It takes the same `lenz_...` key and forwards it to the endpoints below, so MCP traffic spends the same credits, counts against the same rate limits, and shows up in `GET /me/usage` \u2014 there is no separate MCP quota to check, and a 402 can just as easily be an agent as your own code.\n\n## Idempotency\n\nSend an `Idempotency-Key` header on `POST /extract`, `POST /assess`, `POST /verify`, `POST /verify/batch`, `POST /verify/{task_id}/select`, `POST /review`, `POST /citecheck` and `POST /ask/{verification_id}` so retries after a network drop do not spawn duplicate tasks or double-debit quota. The server caches the response body and returns it on replay; a re-used key with a different body returns 422. The SDKs generate a key for `extract`, `assess`, `select`, `verify`, `verify_and_wait`, `verify_batch`, `verify_batch_and_wait`, `ask.send`, `review` and `citecheck` and reuse it across their own retries (lenz-io 3.0; 2.x sent a key on `verify_batch` and `ask.send` only when you passed `idempotency_key` yourself). An error from a keyed call carries the key (`idempotency_key` in Python, `idempotencyKey` in Node): resend with that same key, never as a plain new call, which sends a new key and can run the work twice.\n\nOn `/ask` a key also keeps the retry out of the conversation: without one, a repeated question is a second turn, a second credit and a second answer that the next turn reads as context. A retry that lands while the first call is still running gets 409 rather than the reply \u2014 nothing is finalized yet to replay \u2014 so treat it as work already in progress and retry the same key once the first call has had time to finish. `GET /ask/{verification_id}` returns the message history, but carries no request id, so it can only tell you which answer was yours when one question is in flight at a time. lenz-io 3.0 sends a fresh key on every `ask.send` call and reuses it across the retries inside that call, so a retried question is not asked twice. Asking the same question again is a new call with a new key, and is asked again, because a repeated question is usually deliberate; pin the key to make a retry from another process mean \"the same question, once\": `ask.send(..., idempotency_key=...)` in Python, `ask.send(id, { message, idempotencyKey })` in Node. The n8n node's Ask operation sends a key scoped to the workflow execution, so a retry replays rather than re-asks. The Zapier app sends none on ask.\n\n## Errors\n\nThe status code says what to do next; the body says what happened. Every response carries an `X-Request-ID` header \u2014 quote it on a support ticket. lenz-io 3.0 reads the last column for you: `retryable` is set on every SDK error (true for a 429, a 5xx, a dropped connection, a request timeout and a 409 that means \"not yet\"; false for any other 4xx), so branch on it instead of the status.\n\n| Status | Condition | Retry? |\n|---|---|---|\n| 401 | Missing, malformed or unknown key | After fixing credentials |\n| 402 | Out of credits, or the plan is the limit | No \u2014 billing action |\n| 403 | Authenticated but not allowed (private verification, IP block) | No |\n| 409 | A request with the same `Idempotency-Key` is still running, or the work the call names is not in the state it needs (`no_selection_pending`, `verification_not_ready`, `verification_failed`, `use_review_cancel`) | Same-key conflict: yes, with the same key. `verification_not_ready`: poll, or choose the claims when it needs input. `no_selection_pending`: poll the status first. `use_review_cancel`: cancel the review instead |\n| 422 | Malformed input | No |\n| 429 | Rate limit: the per-account `/extract` daily cap, or too many reviews or citation checks running (`review_in_flight`, `citecheck_in_flight`) | Yes, after `Retry-After` |\n| 502 | A sync step (`/assess`, `/extract`, `/ask`) failed deterministically \u2014 a schema or parse failure (`/ask`: `ask_failed`) | No \u2014 same input, same outcome |\n| 503 | Our model providers were rate-limited or down for the step and every fallback was exhausted (`code: upstream_unavailable`) or the pipeline has no capacity (`code: capacity`) | Yes, after `Retry-After` (body `retry_after` too) |\n\n**402** carries `detail`, `code` (always `no_credits`), `upgrade_url`, `doc_url`, `wall_id`, `cost` (what the rejected call would have taken), and \u2014 when resolvable \u2014 `remaining`, `credits_remaining` and `resets_at`. `remaining` and `requested` are in the *capability's* unit (verifications, assesses); `credits_remaining` and `cost` are in credits, so a client can tell \"not enough for a 10-credit verify\" from \"empty\". The resolvable fields are omitted rather than sent as `null`, so an absent key means \"unknown\", not \"zero\".\n\n`wall_id` identifies this specific rejection and is already appended to `upgrade_url`, so sending a user to that URL is all that is needed \u2014 it exists as its own field only for clients that build their own upgrade link. Treat `upgrade_url` as opaque and follow it whole rather than matching it against a fixed string.\n\nThe `code` values are deliberately plan-agnostic: they name the condition, never the plan that would fix it. Send users to `upgrade_url` rather than mapping codes to plan names \u2014 the set of plans changes, the conditions do not.\n\nAn empty balance is deliberately **not** a 429: a 429 tells every client to retry, and an empty balance never succeeds on retry. **429** carries `code`, `limit`, `reset_in_seconds`, `upgrade_url` and the `Retry-After` header. The in-flight 429 of `/review` and `/citecheck` (`review_in_flight`, `citecheck_in_flight`) carries `retry_after_seconds` and `Retry-After` instead. The daily cap is the same on every plan; only a key Lenz has marked unlimited for `/extract` bypasses it.\n\n**Migrating (August 2026).** These rejections were 403, which the SDKs map to their auth error; they are now 402, which maps to the quota error \u2014 not a subclass. If you catch the auth error to handle an empty balance, that branch stops firing. This reaches you on every SDK version, including ones released before the change. `detail` strings are unchanged. Full reference: [lenz.io/docs/errors](https://lenz.io/docs/errors#quota).\n\n## Webhooks\n\nOn `POST /verify` and `POST /review` you may supply a `webhook_url`. We POST an HMAC-SHA256-signed JSON payload to it when the pipeline terminates. Signature header is `X-Lenz-Signature: sha256=<hex>`. Verify with your webhook secret (generate + rotate on [API credentials](https://lenz.io/api-credentials)). Retries: 10s, 60s, 600s (3 retries after the initial delivery, 4 attempts total). The SDKs ship a `LenzWebhooks` helper that verifies signatures and parses the payload into typed events. Events: `verification.completed`, `verification.failed`, `verification.cancelled`, `certificate.timestamped`, and for a review `review.completed` / `review.failed` / `review.cancelled` and for a citation check `citecheck.completed` / `citecheck.failed` / `citecheck.cancelled` (switch on `event`; a review's own deep checks fire no `verification.*` events). The `*.cancelled` events fire once, when you cancel, in the next API version; a submission made in 2026-05-13 receives the matching `*.failed` event with `failure_class: \"cancelled\"` instead.\n\nFor commercial use, volume pricing, or onboarding support, [get in touch](https://lenz.io/contact).",
    "termsOfService": "https://lenz.io/terms"
  },
  "paths": {
    "/api/v1/": {
      "get": {
        "operationId": "apiRoot",
        "summary": "Api Root",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ApiRootOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Service discovery root \u2014 links to docs, OpenAPI spec, and endpoints.\n\nReturned at ``GET /api/v1/`` so curious humans and probing clients\nget a useful JSON payload instead of a 404.\n\n**Versions.** default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Discovery"
        ]
      }
    },
    "/api/v1/library": {
      "get": {
        "operationId": "listLibrary",
        "summary": "List Library",
        "parameters": [
          {
            "in": "query",
            "name": "domain",
            "schema": {
              "default": "",
              "title": "Domain",
              "type": "string"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "entity",
            "schema": {
              "default": "",
              "title": "Entity",
              "type": "string"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "search",
            "schema": {
              "default": "",
              "title": "Search",
              "type": "string"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "sort",
            "schema": {
              "default": "recent",
              "title": "Sort",
              "type": "string"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "page",
            "schema": {
              "default": 1,
              "title": "Page",
              "type": "integer"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "curated",
            "schema": {
              "default": "",
              "title": "Curated",
              "type": "string"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "verdict",
            "schema": {
              "default": "",
              "title": "Verdict",
              "type": "string"
            },
            "required": false
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerificationListOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/VerificationListOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/VerificationListOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Search and browse the public catalog of verified claims.\n\nReturns paginated results from the Lenz Library. Only publicly\npublished verifications are included.\n\n**Sort options:** `recent`, `most_true`, `most_untrue`,\n`relevance` (only when `search` is provided), and `random`.\n\n**`curated`** restricts results to one or more named curated collections,\ncomma-separated. Currently supported: `trivia` (the LLM-curated,\ntrivia-worthy pool behind the open-source quiz demo).\n\n**`verdict`** filters to one or more verdict labels, comma-separated\n(e.g. `True,False`). Labels: `True`, `Mostly True`, `Mixed`,\n`Mostly False`, `False`.\n\n**Versions.** 200: `2026-10-11` receives `VerificationListOut`, `2026-05-13` receives `VerificationListOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Library"
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz()  # no api_key needed for the public library\npage = client.library.list(page=1, sort=\"recent\")\nfor v in page.items:\n    print(v.claim, \"\u2192\", v.verdict)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz();  // no api_key needed\nconst page = await client.library.list({ page: 1, sort: \"recent\" });\npage.items.forEach(v => console.log(v.claim, \"\u2192\", v.verdict));\n"
          }
        ]
      }
    },
    "/api/v1/verify": {
      "post": {
        "operationId": "submit",
        "summary": "Verify",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "202": {
            "description": "Accepted",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerifyAcceptedOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/VerifyAcceptedOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/VerifyAcceptedOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "200": {
            "description": "Sent only to callers on `2026-05-13`: the same receipt for a repeat of a `/verify` answered from the first submission. Every other version answers 202.",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerifyAcceptedOutLegacy"
                }
              }
            },
            "x-lenz-versions": {
              "2026-05-13": {
                "$ref": "#/components/schemas/VerifyAcceptedOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Submit a claim for verification.\n\nThe claim goes in ``claim``. (``text`` is accepted as an alias \u2014 a\ndocument is ``text``, a claim is ``claim``; ``POST /extract`` is the\nendpoint that takes a document.)\n\nReturns a ``task_id`` immediately. Poll ``GET /verify/status/{task_id}``\nor supply ``webhook_url`` in the body for an asynchronous callback when\nthe pipeline terminates.\n\n**Duplicate submissions are collapsed.** With no ``Idempotency-Key``\nheader, the request body itself is the key: resubmitting an identical\nbody within 10 minutes returns the original ``task_id`` instead of\nstarting a second run. To run the same text twice on purpose, send your\nown ``Idempotency-Key`` \u2014 a supplied key always wins.\n\n**``depth``** selects how much work the check does. ``standard``\n(default) is the full pipeline. ``low`` searches fewer sources, skips\nthe recovery fetch tiers and stops the debate after the opening\narguments (no rebuttal round), so it comes back sooner \u2014 with less\nevidence behind the verdict. Framing, the adjudication panel and the\nconclusion run unchanged, and every step runs the same models either\nway; ``low`` is a volume lever, not a model downgrade.\n\n``low`` costs **half the credits**, and you are charged for the depth you\nREQUESTED. A claim answered from a check made in the last hour is free\n(unless it issues you a new warranty certificate, which is charged at the\ndepth you requested). The completed result echoes the depth the verdict\nwas actually produced with, which is why that field can read ``standard``\non a ``low`` request: the echo describes the evidence.\n\n**Versions.** 202: `2026-10-11` receives `VerifyAcceptedOut`, `2026-05-13` receives `VerifyAcceptedOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verify"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/VerifyIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nv = client.verify_and_wait(claim=\"Sharks don't get cancer\")\n# Add language=\"es\" for Spanish output (12 languages supported).\n# Add depth=\"low\" for a shallower check that returns sooner.\nprint(v.verdict, v.lenz_score)\n# False 2\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst v = await client.verifyAndWait({ claim: \"Sharks don't get cancer\" });\n// Add depth: \"low\" for a shallower check that returns sooner.\nconsole.log(v.verdict, v.lenz_score);\n// False 2\n"
          }
        ]
      }
    },
    "/api/v1/verify/batch": {
      "post": {
        "operationId": "batch",
        "summary": "Verify Batch",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "202": {
            "description": "Accepted",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/BatchAcceptedOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/BatchAcceptedOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/BatchAcceptedOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Fan-out wrapper around /verify for multi-claim LLM responses.\n\nBody: ``{claims: [{text, source_url?, webhook_url?, visibility?, depth?},\n...]}`` capped at 20 items. Server pre-checks total credits, then fans out N\nindependent pipelines \u2014 each with its own ``task_id`` and lifecycle.\nEach claim's webhook (per-item override, or batch ``webhook_url``, or\nper-key default) fires when its pipeline terminates. ``batch_id`` is\npurely for client-side correlation; the server doesn't gate anything\non it.\n\nOn a mid-fan-out enqueue error, the response includes the partial\n``items`` list and a ``partial: true`` flag. Per-claim credit spend\nhappens at each claim's normal persist time \u2014 claims that never\nenqueue are never charged.\n\n``depth`` works like ``visibility``: a batch-wide default that any item\ncan override. See ``POST /verify`` for what the values mean.\n\nEach item carries its claim in ``claim`` (``text`` is accepted as an\nalias), plus the same optional fields as ``POST /verify``.\n\n**Versions.** 202: `2026-10-11` receives `BatchAcceptedOut`, `2026-05-13` receives `BatchAcceptedOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verify"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/VerifyBatchIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nbatch = client.verify_batch(claims=[\n    {\"claim\": \"The Eiffel Tower is in Berlin.\"},\n    {\"claim\": \"Water boils at 100\u00b0C at sea level.\"},\n])\nfor item in batch.items:\n    print(item.task_id, item.claim)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst batch = await client.verifyBatch({\n  claims: [\n    { claim: \"The Eiffel Tower is in Berlin.\" },\n    { claim: \"Water boils at 100\u00b0C at sea level.\" },\n  ],\n});\nbatch.items.forEach(i => console.log(i.task_id, i.claim));\n"
          }
        ]
      }
    },
    "/api/v1/assess": {
      "post": {
        "operationId": "assess",
        "summary": "Assess",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/AssessOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/AssessOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/AssessOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Fast verdict via a 3-model panel (sync, ~10-25s).\n\nEscalation contract: a ``claims[].claim`` text POSTed back verbatim to\n``/verify`` within 24 hours is verified as-is \u2014 in normal operation it\ndoes not return ``needs_input`` and its wording is not rewritten.\n\nTwo input forms, one response shape::\n\n    claim / text  \u2500\u25ba ONE text. Lenz reads the claims in it, and each becomes a\n                     row, up to 20 a call; the rest go back, unchecked and\n                     free, in ``more_claims``.\n    claims[]      \u2500\u25ba a LIST of up to 20 items, each one claim. One row per item, same order.\n                     A compound item is assessed on its primary reading and\n                     the rest is listed in that row's ``more_claims``.\n\nThe list form is the batch rung of the extract \u2192 assess \u2192 verify ladder:\none ``/assess`` call answers up to 20 of ``/extract``'s claims (it finds up\nto 100) in about the time a single call takes, because every item is\nassessed in parallel.\n\nA verdict can be served from memory: a completed ``/verify`` of the exact\nsame claim text, or a prior ``/assess`` of it, within the last hour,\nwhichever account ran it \u2014 the verdict is a function of the input.\n``verification_url`` is set only when the caller could read that\nverification by id.\n\nBilling: 1 credit per row that carries a verdict; error rows are free; a\nduplicate item is a second row and a second credit (the panel runs once).\n\n**Versions.** 200: `2026-10-11` receives `AssessOut`, `2026-05-13` receives `AssessOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Assess"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/AssessIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nout = client.assess(claim=\"Coffee causes cancer and the earth is flat.\")\n# Add language=\"es\" for Spanish verdict text; verdict labels stay English.\nfor c in out.claims:\n    print(c.claim, \"\u2192\", c.verdict, c.confidence)\n    if c.rationale:\n        print(\"  \", c.rationale)\n\n# Several claims at once: one row per item, same order (up to 20).\nrows = client.assess(claims=[\"Coffee causes cancer.\", \"The earth is flat.\"]).claims\nfor c in rows:\n    if c.failure:  # status == \"failed\": no verdict, nothing charged\n        print(\"No verdict:\", c.failure.code, c.failure.hint)\n    else:\n        print(c.verdict, c.confidence)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst out = await client.assess({\n  claim: \"Coffee causes cancer and the earth is flat.\",\n});\nout.claims.forEach(c => {\n  console.log(c.claim, \"\u2192\", c.verdict, c.confidence);\n  if (c.rationale) console.log(\"  \", c.rationale);\n});\n\n// Several claims at once: one row per item, same order (up to 20).\nconst rows = (await client.assess({\n  claims: [\"Coffee causes cancer.\", \"The earth is flat.\"],\n})).claims;\nrows.forEach(c => {\n  // status \"failed\": no verdict, nothing charged\n  if (c.status === \"failed\") console.log(\"No verdict:\", c.failure?.code, c.failure?.hint);\n  else console.log(c.verdict, c.confidence);\n});\n"
          }
        ]
      }
    },
    "/api/v1/extract": {
      "post": {
        "operationId": "extract",
        "summary": "Extract",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ExtractOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ExtractOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ExtractOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Extract verifiable claims from arbitrary text.\n\nRuns the extraction step on its own \u2014 no research, no debate, no credit\ncharge. Enumerates every distinct major factual\nclaim in the input (up to 100), ordered most-check-worthy-first, in\n`claims` (one item for a single claim, `[]` for none). Claims returned\nhere verify cleanly when submitted verbatim to `POST /verify`.\n\nPass `focus` to narrow the result to the claims you care about \u2014 a short\ndescription such as `\"market size, growth and competitors\"`, at most 300\ncharacters. A focus selects from the claims the extractor found and\nnothing else: it cannot add a claim, reword one, reorder them, change the\nlanguage, or change what counts as a claim. Ordering stays\nmost-check-worthy-first.\n\n`status` is one of:\n\n- `ready` \u2014 claims were found (and, with a `focus`, at least one matched).\n- `no_checkable_claim` \u2014 no claim in the input could be checked against\n  public evidence.\n- `no_match` \u2014 claims were found but none fall within your `focus`. The\n  unfocused list is never substituted; widen the focus and call again.\n\n`text` can also be a single public web page URL (http or https, nothing\nelse in the field). Lenz reads the page, or a YouTube video's transcript,\nand extracts the claims from its first 50,000 characters. Pages behind a\nlogin (Facebook, Instagram, Threads, LinkedIn) can't be read. A URL call\ntypically takes 5-40 seconds, so give it a 90-second client timeout (SDK\n2.13 and later do). A page that cannot be read answers 502\n`extraction_failed`; when the services that read pages are down, 503\n`upstream_unavailable` with `Retry-After`. Neither uses a unit of the\ndaily cap.\n\nPass `locate: true` to keep only the claims that can be traced directly\nback to your text, and get each claim's `positions`: the passages that\nmake it, with `start` / `end` offsets into `text` as you\nsent it, in Unicode code points. A claim the text does not make, or makes\nwith a different figure, is left out, so the list says what the author\nwrote and nothing else. Offsets count code points, not UTF-16 units: in\nJavaScript slice with `Array.from(text).slice(start, end).join('')`.\nFor a URL the offsets are `null` and each position carries its passage.\nLocating adds a few seconds, never more than 20. If it cannot run,\nevery `positions` is `null` and the claims are returned unfiltered. `locate`\ndefaults to `false`.\n\nAccepts up to 50,000 characters (longer input is truncated). Free for\nAPI-key holders, capped at 1000 calls per ACCOUNT per day (resets at\n00:00 UTC) regardless of input length \u2014 a focused call costs the same one\nunit as an unfocused one. The cap is shared across all of the account's\nkeys.\n\n**Versions.** 200: `2026-10-11` receives `ExtractOut`, `2026-05-13` receives `ExtractOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Extract"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/ExtractIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nout = client.extract(text=\"Coffee causes cancer and the earth is flat.\")\n# Add language=\"es\" to return extracted claims in Spanish.\nfor c in out.claims:\n    print(c.claim)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst out = await client.extract({\n  text: \"Coffee causes cancer and the earth is flat.\",\n});\n(out.claims ?? []).forEach(c => console.log(c.claim));\n"
          }
        ]
      }
    },
    "/api/v1/verify/{task_id}/select": {
      "post": {
        "operationId": "select",
        "summary": "Select Claim",
        "parameters": [
          {
            "in": "path",
            "name": "task_id",
            "schema": {
              "title": "Task Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "202": {
            "description": "Accepted",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/BatchAcceptedOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/BatchAcceptedOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/BatchAcceptedOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Resolve a multi-claim interrupt by selecting one or more of the offered\nclaims.\n\nEach selected claim fans out into its own independent pipeline (like\n``/verify/batch``), so the response is batch-shaped:\n``{batch_id, items: [{task_id, claim}], partial?}``. Poll each\n``task_id`` via ``GET /verify/status/{task_id}``.\n\nSend the chosen claims in ``claims`` (``texts`` is accepted as an alias).\nEvery selected claim must match one that was offered in the prior\n``needs_input`` response (server-validated against the recorded offer set);\narbitrary client-asserted text is rejected.\n\n**Versions.** 202: `2026-10-11` receives `BatchAcceptedOut`, `2026-05-13` receives `BatchAcceptedOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verify"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/SelectIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      }
    },
    "/api/v1/verify/status/{task_id}": {
      "get": {
        "operationId": "getStatus",
        "summary": "Get Status",
        "parameters": [
          {
            "in": "path",
            "name": "task_id",
            "schema": {
              "title": "Task Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/StatusOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/StatusOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/StatusOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Poll processing status for a submitted verification.\n\nFive shapes keyed on ``status`` \u2014 ``processing``, ``needs_input``,\n``completed``, ``failed``, ``cancelled`` (``2026-05-13`` reads a cancelled\nrun as ``failed``) \u2014 and only the fields belonging to the current one are\npresent (see the response schema). A field that does not belong\nto the current shape is omitted rather than sent as null, so a client may\ntest for presence.\n\n**Versions.** 200: `2026-10-11` receives `StatusOut`, `2026-05-13` receives `StatusOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verify"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\n# typed progress needs lenz-io >= 2.11.0\nclient = Lenz(api_key=\"lenz_...\")\nstatus = client.get_status(\"tsk_abc123\")\n\n# \"processing\" | \"needs_input\" | \"completed\" | \"failed\" | \"cancelled\"\nif status.status == \"processing\" and status.progress:\n    p = status.progress\n    print(f\"{p.step} \u2014 step {p.index} of {p.total}\")\nelif status.status == \"completed\" and status.result:\n    print(status.result.verdict, status.result.key_finding)\nelif status.failure:  # failed or cancelled\n    print(status.status, status.failure.code, status.failure.retryable)\n"
          },
          {
            "lang": "TypeScript",
            "source": "// typed progress needs lenz-io >= 2.11.0\nimport { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst s = await client.getStatus(\"tsk_abc123\");\n\nif (s.status === \"processing\" && s.progress) {\n  const { step, index, total } = s.progress;\n  console.log(`${step} \u2014 step ${index} of ${total}`);\n} else if (s.status === \"completed\") {\n  console.log(s.result!.verdict, s.result!.key_finding);\n} else if (s.failure) {\n  // \"failed\" or \"cancelled\"\n  console.log(s.status, s.failure.code, s.failure.retryable);\n}\n"
          }
        ]
      }
    },
    "/api/v1/verify/{task_id}/cancel": {
      "post": {
        "operationId": "cancel",
        "summary": "Cancel Verification",
        "parameters": [
          {
            "in": "path",
            "name": "task_id",
            "schema": {
              "title": "Task Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CancelOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CancelOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CancelOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Stop a verification that has not finished.\n\nA cancelled run is not charged and produces no verification: nothing is\nsaved. Work already under way when you cancel (a model call in flight) is\nnot billed to you, and the run itself stops at its next step. A run waiting\non `POST /verify/{task_id}/select` is cancelled too.\n\nThe call is safe to repeat and answers 200 whatever the state, so a client\nthat gives up never has to handle an error for losing a race:\n\n- `cancelled: true`, `status: \"cancelled\"`: the run is cancelled, by this\n  call or an earlier one.\n- `cancelled: false`, `status: \"completed\"`: it finished first. The\n  verification exists and was charged as usual.\n- `cancelled: false`, `status: \"failed\"`: it had already failed.\n\n`GET /verify/status/{task_id}` answers `cancelled` from then on, and a\n`webhook_url` receives `verification.cancelled` (a `2026-05-13` submission\nreceives `verification.failed` with `failure_class: \"cancelled\"`).\n\nAnother account's task, an unknown one, and a web task answer 404. A task\nthat is a `/review`'s deep check answers 409 `use_review_cancel`: cancel\nthe review (`POST /reviews/{review_id}/cancel`), which cancels everything in\nit.\n\n**Versions.** 200: `2026-10-11` receives `CancelOut`, `2026-05-13` receives `CancelOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verify"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nresult = client.cancel(\"tsk_abc123\")  # lenz-io >= 3.0.0\n# cancelled=True: stopped (by this call or an earlier one), not charged.\n# cancelled=False: it had ended; status is \"completed\" or \"failed\",\n# or \"needs_input\" when select already resolved it: cancel each task id\n# select returned (those keep running).\nprint(result.cancelled, result.status)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst result = await client.cancel(\"tsk_abc123\"); // lenz-io >= 3.0.0\n// cancelled: true = stopped (by this call or an earlier one), not charged.\n// cancelled: false = it had ended; status is \"completed\" or \"failed\",\n// or \"needs_input\" when select already resolved it: cancel each task id\n// select returned (those keep running).\nconsole.log(result.cancelled, result.status);\n"
          }
        ]
      }
    },
    "/api/v1/me/usage": {
      "get": {
        "operationId": "getUsage",
        "summary": "Me Usage",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/MeUsageOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/MeUsageOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/MeUsageOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Return the calling account's credit balance and what it can still buy.\n\n**``credits`` is the balance.** One pool funds every billable capability,\nat the weights in ``costs`` \u2014 today ``verify`` 10, ``assess`` 1, ``ask`` 1.\nIt has two buckets: the monthly allowance for the current ``plan``, which\nresets at ``resets_at``, and non-expiring ``extra`` credits from grants and\ntop-ups, spent only once the allowance is gone. ``remaining`` is the sum,\nand is what a call is actually checked against.\n\nThe current shape is ``credits``, ``costs``, ``cost_options``, ``extract``,\n``plan``, ``plan_label`` and ``has_webhook_secret``. Callers on API version\n``2026-05-13`` also get the deprecated fields below, which are kept for\nthem: ``credits.bonus``, ``quota_resets_at`` (the same\nas ``credits.resets_at``) and the ``verify`` / ``ask`` / ``assess`` blocks.\n\n``credits.bonus`` (``2026-05-13`` only) is the deprecated old name of\n``credits.extra``, the same number. Read ``extra``.\n\n``plan`` is the stable slug to branch on; ``plan_label`` is the same tier\nas display copy (\"Pro\"). Two fields rather than one humanised\nstring, so a reworded label cannot break a client comparing tiers.\nThe Pro plan's ``plan`` is ``pro``; it read ``developer`` before\n2026-09-15, while ``plan_label`` already read \"Pro\".\n\n**The per-capability blocks are deprecated** (``2026-05-13`` only). ``verify`` / ``ask`` /\n``assess`` are **projections** of that one pool into each capability's own\nunit \u2014 \"how many of these could I still make\" \u2014 not separate allowances.\nSpending on one moves all of them, and they are floor divisions, so a\nverify block ticks once per 10 credits spent anywhere.\n\nRead ``credits`` and ``costs`` instead; the blocks and the per-block\n``credits`` alias stay for ``2026-05-13`` callers. Derive them::\n\n    remaining = credits.remaining // costs[capability]\n    total     = credits.total     // costs[capability]\n    used      = total - remaining\n\nTwo capabilities at the same price emit identical blocks \u2014 ``ask`` and\n``assess`` are both 1 credit \u2014 which is the clearest sign the shape\ndescribes an allowance that no longer exists.\n\n``bonus`` in each block is ``credits.extra`` in that capability's unit. The\nolder key ``credits`` is its deprecated alias, kept for the same callers.\n\n``costs`` is one entry per capability at its DEFAULT price. Prices that\ndepend on a request parameter live in ``cost_options``, nested capability\n\u2192 parameter \u2192 value \u2014 ``{\"verify\": {\"depth\": {\"standard\": 10, \"low\": 5}}}``.\nTwo maps rather than a flat one with a ``verify_low`` key, so a future\ntuning parameter nests instead of adding an entry that reads like a fifth\ncapability. Every capability in ``cost_options`` also appears in ``costs``\nat its default, so reading only ``costs`` is always correct.\n\n``extract`` is free at the pool (``costs.extract`` is 0) and is bounded by\na per-account daily fair-use cap instead, reported separately here and\nrejected with 429 rather than 402.\n\n**Versions.** 200: `2026-10-11` receives `MeUsageOut`, `2026-05-13` receives `MeUsageOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Account"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nu = client.usage()\n# One credit pool funds every call; `costs` is the price list.\nprint(u.credits.remaining, \"credits left\", u.costs)\n# The same balance in one capability's unit: credits.remaining // costs[capability].\nprint(u.credits.remaining // u.costs[\"verify\"], \"verify calls left\")\nprint(u.credits.remaining // u.costs[\"assess\"], \"assess calls left\")\nprint(u.credits.extra, \"of them extra credits (grants and top-ups, never expiring)\")\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst u = await client.usage();\nconsole.log(`${u.credits.remaining} credits left`, u.costs);\n// The same balance in one capability's unit: credits.remaining / costs[capability].\nconsole.log(`${Math.floor(u.credits.remaining / u.costs[\"verify\"])} verify calls left`);\nconsole.log(`${Math.floor(u.credits.remaining / u.costs[\"assess\"])} assess calls left`);\n"
          }
        ]
      }
    },
    "/api/v1/verifications": {
      "get": {
        "operationId": "listVerifications",
        "summary": "List Verifications",
        "parameters": [
          {
            "in": "query",
            "name": "page",
            "schema": {
              "default": 1,
              "title": "Page",
              "type": "integer"
            },
            "required": false
          },
          {
            "in": "query",
            "name": "page_size",
            "schema": {
              "default": 20,
              "title": "Page Size",
              "type": "integer"
            },
            "required": false
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerificationListOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/VerificationListOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/VerificationListOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "List the authenticated key's verifications (all visibilities).\n\n**Versions.** 200: `2026-10-11` receives `VerificationListOut`, `2026-05-13` receives `VerificationListOutLegacy`; 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verifications"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\npage = client.verifications.list(page=1)\nfor v in page.items:\n    print(v.verification_id, v.verdict)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst page = await client.verifications.list({ page: 1 });\npage.items.forEach(v => console.log(v.verification_id, v.verdict));\n"
          }
        ]
      }
    },
    "/api/v1/verifications/{verification_id}": {
      "get": {
        "operationId": "getVerification",
        "summary": "Get Verification",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ClaimDetailOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ClaimDetailOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ClaimDetailOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "404": {
            "description": "Not Found",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerificationNotFoundOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "409": {
            "description": "Conflict",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerificationNotReadyOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/VerificationNotReadyOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/VerificationNotReadyOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "410": {
            "description": "Gone",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/VerificationPurgedOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Retrieve the full verification report for a single claim.\n\nReturns the verdict, citations, and (under ``audit``) the panel\nreasoning, debate transcript, and assessments. Same shape as the\n/verify webhook payload and the deprecated /library/{id} endpoint\nthis merger replaces.\n\nAuthorization model (optional Bearer):\n- Anon callers see any listed public claim (``visibility='public'`` AND\n  ``status`` in {pending, published}) PLUS any API ``unlisted`` claim\n  (``visibility='public'``, ``status='hidden'``, ``source_channel='api'``):\n  unlisted is readable by verification_id, just never surfaced in listings.\n- Authed callers additionally see their own claims regardless of\n  visibility or status.\n- Private claims, and non-API hidden public claims (retracted / pre-screen),\n  owned by someone else return 404.\n\nAlso accepts the **task_id** ``/verify`` returned, in place of a\nverification_id. A completed run reads exactly as its verification_id\nwould. A run that has not completed answers **409** with ``status``\n(``processing``, ``needs_input`` or ``failed``) and a ``hint``, plus the\nfailure fields when it failed; poll ``GET /verify/status/{task_id}`` for\nprogress. A task_id that is unknown, or not yours, answers 404 with a\n``hint`` at that endpoint.\n\n**Versions.** 200: `2026-10-11` receives `ClaimDetailOut`, `2026-05-13` receives `ClaimDetailOutLegacy`; 409: `2026-10-11` receives `VerificationNotReadyOut`, `2026-05-13` receives `VerificationNotReadyOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verifications"
        ]
      },
      "delete": {
        "operationId": "deleteVerification",
        "summary": "Delete Verification",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/OkOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Delete an owned verification.\n\nRemoves the verification, its analysis, evidence and follow-up chat, and\nthe text of each request that submitted it from your credit history and\nfrom our API-call log (on a batch, that item only). Not reached by a\ndeletion: copies in our caches, which expire within 24 hours, and our\nbackups, which age out within 60 days.\n\nDeleting a warranted verification keeps its certificate and warranty; the\ncertificate stays at its `certificate_url`.\n\n**Versions.** default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verifications"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      }
    },
    "/api/v1/verifications/{verification_id}/certificate": {
      "get": {
        "operationId": "getCertificate",
        "summary": "Get Certificate",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CertificateOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Download the warranty certificate for a covered verification.\n\nResolved by (verification, ACCOUNT), not by verification alone: one cached\nanalysis can have several holders, each with their own certificate, their\nown cap and their own link. Returning \"the certificate for this\nverification\" would hand one customer another customer's document.\n\nByte-identical to ``/certificate/<certificate_id>.json``. A withdrawn\ncertificate is still served \u2014 it is the record of what was warranted, and\nthe withdrawal date is on it.\n\nServed whether or not new certificates are currently being issued: an\nissued certificate stands.\n\n**Versions.** default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verifications"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      }
    },
    "/api/v1/verifications/{verification_id}/related": {
      "get": {
        "operationId": "listRelated",
        "summary": "List Related",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "in": "query",
            "name": "limit",
            "schema": {
              "default": 5,
              "title": "Limit",
              "type": "integer"
            },
            "required": false
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/RelatedVerificationsOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "List public verifications semantically related to this one.\n\nReturns the closest public-library claims by semantic similarity\n(cosine distance, 0 = identical). Excludes the verification itself,\nnear-duplicates (distance < 0.2), and editorially-hidden claims. Empty\nlist when the verification has not been indexed yet (that happens\nshortly after it completes) or when no claim is close enough.\n\nAuthorization model (optional Bearer) \u2014 identical to\n``GET /verifications/{verification_id}``: anon callers reach listed public claims plus\nAPI-origin unlisted ones; a valid key additionally unlocks the\ncaller's own claims. Results are always drawn from the public\nlibrary only, so keyless access exposes nothing new.\n``limit`` is clamped to [1, 10].\n\n**Versions.** 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Verifications"
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\nrelated = client.verifications.related(\"vid_abc123\", limit=5)\nfor r in related.items:\n    print(r.verification_id, r.claim, r.verdict)\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst related = await client.verifications.related(\"vid_abc123\", { limit: 5 });\nrelated.items.forEach(r => console.log(r.verification_id, r.claim, r.verdict));\n"
          }
        ]
      }
    },
    "/api/v1/ask/{verification_id}": {
      "get": {
        "operationId": "getAskHistory",
        "summary": "Get Ask History",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/AskHistoryOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Get ask history and remaining quota for a verification.\n\n**Versions.** default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Ask"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      },
      "delete": {
        "operationId": "resetAsk",
        "summary": "Reset Ask",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/OkOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Delete all ask messages for this user on a verification.\n\n**Versions.** default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Ask"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      },
      "post": {
        "operationId": "sendAsk",
        "summary": "Send Ask",
        "parameters": [
          {
            "in": "path",
            "name": "verification_id",
            "schema": {
              "title": "Verification Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/AskMessageOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "A field to fix",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ValidationErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ValidationErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ValidationErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Send a question and get an expert response.\n\nThe reply (``content`` field on the response) is plain text with a\nsmall markdown subset baked in by the chat model:\n\n- ``**bold**`` and ``*italic*``\n- ``- `` or ``* `` bullet lists\n- Blank-line paragraph breaks; single newlines inside a paragraph\n  mean line break\n- ``[label](url)`` links, only ever to one of the verification's\n  sources: any other link is reduced to its label before the reply\n  is returned\n\nThe model only produces these \u2014 no headings, no tables, no code\nblocks. Pass the reply through any markdown library or display it\nverbatim.\n\nDocumented at https://lenz.io/docs/quickstart#ask-reply-format.\n\n**Versions.** 422: `2026-10-11` receives `ValidationErrorOut`, `2026-05-13` receives `ValidationErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Ask"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/AskIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      }
    },
    "/api/v1/review": {
      "post": {
        "operationId": "review",
        "summary": "Review a draft",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "202": {
            "description": "Accepted",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewAcceptedOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "402": {
            "description": "Payment Required",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "409": {
            "description": "Conflict",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "The body names a field or a value the endpoint does not take.",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewValidationErrorOut"
                },
                "example": {
                  "detail": "payload.escalate.verdicts: Unknown verdict label 'Misleading'; use one of: False, Mostly False, Mixed, Mostly True, True.",
                  "code": "invalid_verdict_label",
                  "errors": [
                    {
                      "loc": [
                        "body",
                        "payload",
                        "escalate",
                        "verdicts"
                      ],
                      "msg": "Unknown verdict label 'Misleading'; use one of: False, Mostly False, Mixed, Mostly True, True."
                    }
                  ]
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "429": {
            "description": "Too Many Requests",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "503": {
            "description": "Service Unavailable",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Read a draft, quick-check every claim, deep-check the ones that look\nwrong or uncertain, and hand back the issues with the fixes.\n\nReturns 202 with a `review_id`; read the review at the `Location`\n(`GET /reviews/{review_id}`), or receive `review.completed` /\n`review.failed` at your webhook. A review takes two to four minutes.\n\nIt spends the credits the primitives spend: 1 per claim assessed, and 10\n(5 at `depth: low`) per deep check it runs. At most\n`min(claims, max_assessments) \u00d7 1 + max_verifications \u00d7 depth cost`;\nthe review reports what it charged.\n\nSend `escalate.max_citations: N` to also check the draft's first N\ncitations (markdown links, bare URLs, DOIs, `[n]` markers with a reference\nlist): for each, whether the source says what the draft attributes to it.\nOff by default; 1 credit per checked citation, and a source that could not\nbe checked is not charged. `POST /citecheck` is the same check alone.\nThe rows are in `citations[]`, the ones that do not hold up in\n`citation_issues[]`, and `outcome` reads `issues_found` for them.\n`escalate.max_assessments: 0` runs no quick check (a review of the\ncitations alone).\n\nOnly claims traced directly back to the draft are checked: a claim found\nnowhere in it is left out (as `/extract` does with `locate: true`). Each\nclaim row's `positions` says where the draft makes it, and\n`more_claim_locations` gives `{claim, positions}` for each of\n`more_claims`. Claim and citation positions share one shape, `{start, end,\ntext}`: `start` / `end` in Unicode code points of `text` as you sent it,\nhalf-open, and `text` the passage (`null` on a citation, whose row carries\nthe statement). For a URL draft `start` / `end` are `null` and `text`\ncarries the passage.\n\nA `text` that is one URL is read like `/extract` reads it and counts as\none `/extract` call: past the daily `/extract` limit it answers 429\n`extract_daily_limit`. The other 429 is `review_in_flight` (three reviews\nrunning on the account).\n\n**Versions.** 402: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 409: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 429: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 503: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Review"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/ReviewIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Shell",
            "label": "cURL",
            "source": "curl -X POST https://lenz.io/api/v1/review \\\n  -H \"Authorization: Bearer lenz_...\" \\\n  -H \"X-Lenz-API-Version: 2026-10-11\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Idempotency-Key: draft-42\" \\\n  -d '{\"text\": \"The EU AI Act took effect in March 2024. ...\",\n       \"escalate\": {\"max_verifications\": 5}}'\n# 202 {\"review_id\": \"a1b2c3d4\", \"status\": \"queued\"}\n# Location: /api/v1/reviews/a1b2c3d4\n"
          }
        ]
      }
    },
    "/api/v1/reviews/{review_id}": {
      "get": {
        "operationId": "getReview",
        "summary": "Get a review",
        "parameters": [
          {
            "in": "path",
            "name": "review_id",
            "schema": {
              "title": "Review Id",
              "type": "string"
            },
            "required": true
          },
          {
            "in": "query",
            "name": "view",
            "schema": {
              "default": "full",
              "title": "View",
              "type": "string"
            },
            "required": false
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "anyOf": [
                    {
                      "$ref": "#/components/schemas/ReviewFullOut"
                    },
                    {
                      "$ref": "#/components/schemas/ReviewIssuesOut"
                    }
                  ],
                  "title": "Response"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "anyOf": [
                  {
                    "$ref": "#/components/schemas/ReviewFullOut"
                  },
                  {
                    "$ref": "#/components/schemas/ReviewIssuesOut"
                  }
                ],
                "title": "Response"
              },
              "2026-05-13": {
                "anyOf": [
                  {
                    "$ref": "#/components/schemas/ReviewFullOutLegacy"
                  },
                  {
                    "$ref": "#/components/schemas/ReviewIssuesOutLegacy"
                  }
                ],
                "title": "Response"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "403": {
            "description": "Forbidden",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "404": {
            "description": "Not Found",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "410": {
            "description": "Gone",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "Unprocessable Entity",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewValidationErrorOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "The review as it stands: quick verdicts at ~25-40 s, deep checks as each\nlands. `?view=issues` returns the same object without `claims[]`. Poll no\nfaster than `poll_after_seconds`; read `issues[]` at `completed`.\n\n**Versions.** 200: `2026-10-11` receives `ReviewFullOut | ReviewIssuesOut`, `2026-05-13` receives `ReviewFullOutLegacy | ReviewIssuesOutLegacy`; 403: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 404: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 410: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Review"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Shell",
            "label": "cURL",
            "source": "curl \"https://lenz.io/api/v1/reviews/a1b2c3d4?view=issues\" \\\n  -H \"X-Lenz-API-Version: 2026-10-11\" \\\n  -H \"Authorization: Bearer lenz_...\"\n# Poll every poll_after_seconds until status is completed or failed,\n# then read outcome and issues[] (verdict, key_finding, suggested_rewrite).\n"
          }
        ]
      }
    },
    "/api/v1/reviews/{review_id}/cancel": {
      "post": {
        "operationId": "cancelReview",
        "summary": "Cancel a review",
        "parameters": [
          {
            "in": "path",
            "name": "review_id",
            "schema": {
              "title": "Review Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewFullOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewFullOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewFullOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "403": {
            "description": "Forbidden",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "404": {
            "description": "Not Found",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "410": {
            "description": "Gone",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ReviewErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ReviewErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Stop a review: its quick checks, its deep checks and its citation\nchecks. Returns the review as it stands afterwards, `status: cancelled`.\n\nYou are charged only for what it delivered before the cancel: quick\nchecks it served, deep checks that finished, citations it checked. The\nrest is refunded or never charged. A review that had already finished is\nreturned unchanged (`completed` or `failed`), so the body always says\nwhat happened; cancelling again is safe. A review's deep check cannot be\ncancelled on its own (`POST /verify/{task_id}/cancel` answers 409\n`use_review_cancel`): cancel the review.\n\n**Versions.** 200: `2026-10-11` receives `ReviewFullOut`, `2026-05-13` receives `ReviewFullOutLegacy`; 403: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 404: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; 410: `2026-10-11` receives `ReviewErrorOut`, `2026-05-13` receives `ReviewErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Review"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\n# Stops the review, its deep checks and its citation checks (lenz-io >= 3.0.0).\nreview = client.cancel_review(\"a1b2c3d4\")  # the full review, as get_review reads it\nprint(review.status, review.credits.charged)  # \"cancelled\", what it delivered cost\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\n// Stops the review, its deep checks and its citation checks (lenz-io >= 3.0.0).\nconst review = await client.cancelReview(\"a1b2c3d4\"); // as getReview reads it\nconsole.log(review.status, review.credits.charged);\n"
          }
        ]
      }
    },
    "/api/v1/citecheck": {
      "post": {
        "operationId": "citecheck",
        "summary": "Check the citations of a draft",
        "parameters": [
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "202": {
            "description": "Accepted",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckAcceptedOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "402": {
            "description": "Payment Required",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "409": {
            "description": "Conflict",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "422": {
            "description": "Unprocessable Entity",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ReviewValidationErrorOut"
                }
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "429": {
            "description": "Too Many Requests",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "503": {
            "description": "Service Unavailable",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Check whether each cited source says what the draft attributes to it.\n\nSend `text` (a draft with its links: markdown links, bare URLs, `doi:` and\n`doi.org` forms, `[n]` markers with a reference list) or `pairs` (up to 20\nstatements, each with the `url` or `doi` it cites). Returns 202 with a\n`citecheck_id`; read the check at the `Location`\n(`GET /citechecks/{citecheck_id}`), or receive `citecheck.completed` /\n`citecheck.failed` at your webhook.\n\nIt costs 1 credit per checked citation: at most 1 credit per citation you\nsend (or `max_citations` for a text), and a citation that could not be\nchecked is refunded. `credits.charged` on the check says what it cost.\n\n**Versions.** 402: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 409: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 429: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 503: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Citecheck"
        ],
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/CitecheckIn"
              }
            }
          },
          "required": true
        },
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      }
    },
    "/api/v1/citechecks/{citecheck_id}": {
      "get": {
        "operationId": "getCitecheck",
        "summary": "Get a citation check",
        "parameters": [
          {
            "in": "path",
            "name": "citecheck_id",
            "schema": {
              "title": "Citecheck Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "403": {
            "description": "Forbidden",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "404": {
            "description": "Not Found",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "410": {
            "description": "Gone",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "The check as it stands. Poll no faster than `poll_after_seconds`; read\n`citation_issues[]` at `completed`.\n\n**Versions.** 200: `2026-10-11` receives `CitecheckOut`, `2026-05-13` receives `CitecheckOutLegacy`; 403: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 404: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 410: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Citecheck"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ]
      }
    },
    "/api/v1/citechecks/{citecheck_id}/cancel": {
      "post": {
        "operationId": "cancelCitecheck",
        "summary": "Cancel a citation check",
        "parameters": [
          {
            "in": "path",
            "name": "citecheck_id",
            "schema": {
              "title": "Citecheck Id",
              "type": "string"
            },
            "required": true
          },
          {
            "$ref": "#/components/parameters/XLenzApiVersion"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "403": {
            "description": "Forbidden",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "404": {
            "description": "Not Found",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "410": {
            "description": "Gone",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/CitecheckErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/CitecheckErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/CitecheckErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          },
          "default": {
            "description": "An error",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/ErrorOut"
                }
              }
            },
            "x-lenz-versions": {
              "2026-10-11": {
                "$ref": "#/components/schemas/ErrorOut"
              },
              "2026-05-13": {
                "$ref": "#/components/schemas/ErrorOutLegacy"
              }
            },
            "headers": {
              "X-Lenz-API-Version": {
                "$ref": "#/components/headers/XLenzApiVersion"
              }
            }
          }
        },
        "description": "Stop a citation check. Returns the check as it stands afterwards,\n`status: cancelled`.\n\nYou are charged only for the citations it checked before the cancel; the\nrest are refunded. A check that had already finished is returned\nunchanged (`completed` or `failed`); cancelling again is safe.\n\n**Versions.** 200: `2026-10-11` receives `CitecheckOut`, `2026-05-13` receives `CitecheckOutLegacy`; 403: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 404: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; 410: `2026-10-11` receives `CitecheckErrorOut`, `2026-05-13` receives `CitecheckErrorOutLegacy`; default: `2026-10-11` receives `ErrorOut`, `2026-05-13` receives `ErrorOutLegacy`.",
        "tags": [
          "Citecheck"
        ],
        "security": [
          {
            "APIKeyBearerAuth": []
          }
        ],
        "x-codeSamples": [
          {
            "lang": "Python",
            "source": "from lenz_io import Lenz\n\nclient = Lenz(api_key=\"lenz_...\")\ncheck = client.cancel_citecheck(\"12bbbf65\")  # lenz-io >= 3.0.0; as get_citecheck reads it\nprint(check.status, check.credits.charged)  # citations not checked are refunded\n"
          },
          {
            "lang": "TypeScript",
            "source": "import { Lenz } from \"lenz-io\";\n\nconst client = new Lenz({ apiKey: \"lenz_...\" });\nconst check = await client.cancelCitecheck(\"12bbbf65\"); // lenz-io >= 3.0.0\nconsole.log(check.status, check.credits.charged);\n"
          }
        ]
      }
    }
  },
  "components": {
    "schemas": {
      "EntityRef": {
        "description": "An entity (person, place, organization, concept) referenced in the\nsubmitted claim.\n\n``qid`` is the Wikidata Q identifier (e.g. ``Q42`` for Douglas Adams)\nwhen Lenz resolved the entity against its own entity catalog; ``null``\notherwise. Customers can join on ``qid`` to their own Wikidata-indexed\ncorpus, or hit the Wikidata API directly for richer metadata.",
        "properties": {
          "name": {
            "title": "Name",
            "type": "string"
          },
          "qid": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Qid"
          }
        },
        "required": [
          "name"
        ],
        "title": "EntityRef",
        "type": "object"
      },
      "VerificationListItemOut": {
        "description": "Single item in a list of verifications: ``GET /verifications``\n(authed-owner listing) and ``GET /library`` (public catalog), one shape.\n\nSlim shape: no ``url`` (customers reference claims by\n``verification_id``), no ``visibility``.",
        "properties": {
          "verification_id": {
            "title": "Verification Id",
            "type": "string"
          },
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "domain": {
            "title": "Domain",
            "type": "string"
          },
          "entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/EntityRef"
            },
            "title": "Entities",
            "type": "array"
          },
          "verdict": {
            "default": "",
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "default": "low",
            "title": "Confidence",
            "type": "string"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Lenz Score"
          },
          "key_finding": {
            "default": "",
            "title": "Key Finding",
            "type": "string"
          },
          "executive_summary": {
            "default": "",
            "title": "Executive Summary",
            "type": "string"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "A suggested rewrite of `claim` that this verification's findings support, to use in place of the original sentence. It has not been verified itself: before using it, review it or run it through `/verify`. `null` for a true claim, when no correction is established, and on verifications that predate the field. On every verification, single or listed; not on `/assess` rows.",
            "title": "Suggested Rewrite"
          },
          "created_at": {
            "default": "",
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "default": "",
            "description": "When the verification finished (ISO 8601). Always set on a completed verification; a rerun moves it. API version `2026-05-13` sends `modified_at` instead: this time, but only when it falls on a later UTC calendar day than `created_at`, else null.",
            "title": "Completed At",
            "type": "string"
          },
          "language": {
            "title": "Language",
            "type": "string"
          }
        },
        "required": [
          "verification_id",
          "claim",
          "domain",
          "language"
        ],
        "title": "VerificationListItemOut",
        "type": "object"
      },
      "VerificationListOut": {
        "description": "Paginated verifications response. Shared by /library + /verifications.",
        "properties": {
          "items": {
            "items": {
              "$ref": "#/components/schemas/VerificationListItemOut"
            },
            "title": "Items",
            "type": "array"
          },
          "total": {
            "title": "Total",
            "type": "integer"
          },
          "page": {
            "title": "Page",
            "type": "integer"
          },
          "page_size": {
            "title": "Page Size",
            "type": "integer"
          }
        },
        "required": [
          "items",
          "total",
          "page",
          "page_size"
        ],
        "title": "VerificationListOut",
        "type": "object"
      },
      "VerifyIn": {
        "properties": {
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The claim to check. A statement in natural language; several claims in one string are split and handled separately.",
            "title": "Claim"
          },
          "text": {
            "default": "",
            "description": "Accepted alias for `claim`. Send one or the other; `text` is used when it has content.",
            "title": "Text",
            "type": "string"
          },
          "source_url": {
            "default": "",
            "title": "Source Url",
            "type": "string"
          },
          "webhook_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where to POST this request's webhook. Omitted or `null`: your credential's default webhook URL, if it has one. `\"\"`: no webhook for this request. API version `2026-05-13` reads `\"\"` as omitted.",
            "title": "Webhook Url"
          },
          "language": {
            "default": "",
            "description": "ISO 639-1 code for the language of the verification and its source summaries. Omitted: English. `auto`: detected from the submitted text (the same rule as lenz.io: a supported language, or English when the text is short, English or in a language we do not answer in). A code always wins. Responses carry the code that was used, never `auto`.",
            "title": "Language",
            "type": "string"
          },
          "visibility": {
            "default": "private",
            "enum": [
              "private",
              "unlisted"
            ],
            "title": "Visibility",
            "type": "string"
          },
          "depth": {
            "default": "standard",
            "enum": [
              "standard",
              "low"
            ],
            "title": "Depth",
            "type": "string"
          }
        },
        "title": "VerifyIn",
        "type": "object"
      },
      "VerifyBatchIn": {
        "properties": {
          "claims": {
            "items": {
              "$ref": "#/components/schemas/VerifyBatchItemIn"
            },
            "title": "Claims",
            "type": "array"
          },
          "webhook_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where to POST this request's webhook. Omitted or `null`: your credential's default webhook URL, if it has one. `\"\"`: no webhook for this request. API version `2026-05-13` reads `\"\"` as omitted.",
            "title": "Webhook Url"
          },
          "language": {
            "default": "",
            "title": "Language",
            "type": "string"
          },
          "visibility": {
            "default": "private",
            "enum": [
              "private",
              "unlisted"
            ],
            "title": "Visibility",
            "type": "string"
          },
          "depth": {
            "default": "standard",
            "enum": [
              "standard",
              "low"
            ],
            "title": "Depth",
            "type": "string"
          }
        },
        "required": [
          "claims"
        ],
        "title": "VerifyBatchIn",
        "type": "object"
      },
      "VerifyBatchItemIn": {
        "properties": {
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The claim to check. A statement in natural language; several claims in one string are split and handled separately.",
            "title": "Claim"
          },
          "text": {
            "default": "",
            "description": "Accepted alias for `claim`. Send one or the other; `text` is used when it has content.",
            "title": "Text",
            "type": "string"
          },
          "source_url": {
            "default": "",
            "title": "Source Url",
            "type": "string"
          },
          "webhook_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "This item's webhook. Omitted or `null`: the batch's `webhook_url`. `\"\"`: no webhook for this item. API version `2026-05-13` reads `\"\"` as omitted.",
            "title": "Webhook Url"
          },
          "language": {
            "default": "",
            "title": "Language",
            "type": "string"
          },
          "visibility": {
            "anyOf": [
              {
                "enum": [
                  "private",
                  "unlisted"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Visibility"
          },
          "depth": {
            "anyOf": [
              {
                "enum": [
                  "standard",
                  "low"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Depth"
          }
        },
        "title": "VerifyBatchItemIn",
        "type": "object"
      },
      "AssessClaimOut": {
        "description": "Per-claim entry inside an ``AssessOut.claims`` list.\n\n``status`` is ``completed`` when the row carries a verdict and ``failed``\nwhen it does not; a failed row has ``verdict`` and ``confidence``\n``null`` and says why in ``failure`` (``code``, ``detail``, ``hint``,\n``failure_class``, ``retryable``, ``docs_url``). ``failure.code`` is an\nOPEN set: ``no_checkable_claim`` (no claim in the item could be checked\nagainst public evidence), ``framing_failed`` (the item could not be read;\nsend it rephrased), ``upstream_unavailable`` and ``timeout`` (worth\nsending again in a new call). On a failed row ``claim`` echoes the item\nas submitted. Failed rows are free.\n\nA verdict row is the entire answer for that claim. ``verification_url``\nis set when a full verification of the same claim exists and the caller\ncan read it; follow it for sources, reasoning and the deep score.\n\n``verdict`` may be ``No Public Record``: the reviewers found no public\nrecord that would show the claim (its ``confidence`` is medium or low,\nnever high; a deep check, /verify, looks further). A failed row whose\n``failure.detail`` says the reviewers did not reach an answer is free and\nworth sending again.\n\n``rationale`` is the reasoning of a reviewer who agrees with the panel's\nverdict. It is a reviewer's note, not a checked source; for sourced\nevidence, call /verify.\n\nSame field vocabulary as ``ClaimDetailOut`` (``claim``, ``verdict``,\n``confidence``); /assess omits ``lenz_score``, which only a full\nverification computes. ``language`` echoes the output language so a\nbatch caller can route per-claim text when items differ in language.\n\n``suggested_rewrite`` is on every row: the claim with its wrong part\ncorrected when the request set ``suggest_rewrite`` and the check found the\nclaim False or Mostly False with high confidence; ``null`` when it was not\nrequested, the row is outside that, or there was no correction to write. It\nis not itself verified: review it, or run it through /verify.\n\n``more_claims`` lists the OTHER claims found in a list item that were NOT\nassessed (the list form assesses one claim per item, the primary): send\nthem as their own items to check them. A vague item is assessed on its\nmost likely reading, which ``claim`` carries.",
        "properties": {
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "language": {
            "title": "Language",
            "type": "string"
          },
          "status": {
            "enum": [
              "completed",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "verdict": {
            "anyOf": [
              {
                "enum": [
                  "True",
                  "Mostly True",
                  "Mixed",
                  "Mostly False",
                  "False",
                  "No Public Record"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verdict"
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Rationale"
          },
          "dissent": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Deprecated: always null.",
            "title": "Dissent"
          },
          "searched_pages": {
            "default": [],
            "description": "Pages looked at while assessing this claim, as title and link.",
            "items": {
              "$ref": "#/components/schemas/SearchedPageOut"
            },
            "title": "Searched Pages",
            "type": "array"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Suggested Rewrite"
          },
          "more_claims": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "More Claims",
            "type": "array"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "identified_claims": {
            "items": {
              "type": "string"
            },
            "type": "array",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `more_claims`."
          }
        },
        "required": [
          "claim",
          "language",
          "status"
        ],
        "title": "AssessClaimOut",
        "type": "object"
      },
      "AssessOut": {
        "description": "Response body for ``POST /assess``.\n\n``status`` is ``ok`` when at least one row carries a verdict (other rows\nmay have failed), ``no_checkable_claim`` when no claim in the input could\nbe checked against public evidence (every row, or the single text),\nand ``error`` when no row carries a verdict for another reason. A single\ntext with no checkable claim answers ``claims: []`` with the reason in\n``failure`` (the same block a failed row carries); ``failure`` is\n``null`` otherwise.",
        "properties": {
          "status": {
            "enum": [
              "ok",
              "no_checkable_claim",
              "error"
            ],
            "title": "Status",
            "type": "string"
          },
          "claims": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/AssessClaimOut"
            },
            "title": "Claims",
            "type": "array"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "more_claims": {
            "description": "Claims found in a single `text` past the ones checked: one call checks at most 20, ranked most check-worthy first. Not checked and not charged; send them as `claims` (up to 20 a call) to check them. Always `[]` for the `claims` list form.",
            "items": {
              "type": "string"
            },
            "title": "More Claims",
            "type": "array"
          }
        },
        "required": [
          "status"
        ],
        "title": "AssessOut",
        "type": "object"
      },
      "FailureOut": {
        "description": "Why an item failed, and what to do next. The same block everywhere an\nitem fails: a verification, an /assess row, a review, a review's claim\nrows and citation checks.\n\n``code`` is what failed, ``detail`` one sentence on it (the same sentence\nfor the same code on every endpoint), ``hint`` what to send next (null\nwhen there is nothing to change), ``failure_class`` why, ``retryable``\nwhether sending the same request again can succeed, ``docs_url`` where\nthat class is explained.\n\nAPI version ``2026-05-13`` sends each endpoint's earlier fields instead\n(flat ``error`` / ``failure_reason`` on a verification, ``error_code`` /\n``hint`` on an /assess row, ``failure.failure_reason`` on a review).",
        "properties": {
          "code": {
            "description": "What failed, one vocabulary everywhere: `no_checkable_claim`, `page_unreadable`, `upstream_unavailable`, `internal`, `cancelled`, `no_citations`, `insufficient_credits` (a verification only ever says the first, the third, the fourth and `cancelled`). Branch on `retryable` for whether to resend, and on the input codes for what to say; fall through on a value you do not know. `no_checkable_claim`: no claim in the input could be checked against public evidence (an opinion, a forecast, a claim about a private person, a statement whose only source is unidentified; on a review, also claims found that could not be traced back to the text); `hint` says which. `page_unreadable`: the link /review was sent could not be read. Version `2026-05-13` spells `no_checkable_claim` as `no_claim` (/assess, /review) or `not_a_claim` (/extract, a verification), and keeps the earlier causes as codes (`timeout`, `framing_failed`, `assessment_failed`, `citation_check_failed`, `invalid_input`).",
            "title": "Code",
            "type": "string"
          },
          "detail": {
            "description": "The cause, in one sentence (out of time, no row could be assessed, ...); the same sentence for the same cause everywhere.",
            "title": "Detail",
            "type": "string"
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "What to send next; null when there is nothing to change.",
            "title": "Hint"
          },
          "failure_class": {
            "enum": [
              "upstream_unavailable",
              "invalid_input",
              "cancelled",
              "internal"
            ],
            "title": "Failure Class",
            "type": "string"
          },
          "retryable": {
            "title": "Retryable",
            "type": "boolean"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Docs Url"
          }
        },
        "required": [
          "code",
          "detail",
          "failure_class",
          "retryable",
          "docs_url"
        ],
        "title": "FailureOut",
        "type": "object"
      },
      "SearchedPageOut": {
        "description": "A page looked at while assessing a claim.",
        "properties": {
          "title": {
            "title": "Title",
            "type": "string"
          },
          "url": {
            "title": "Url",
            "type": "string"
          }
        },
        "required": [
          "title",
          "url"
        ],
        "title": "SearchedPageOut",
        "type": "object"
      },
      "AssessIn": {
        "description": "Request body for ``POST /assess``.\n\nTwo forms. ``claim`` (or its alias ``text``) is ONE text: read once and\nexpanded, so every claim found in it becomes a row (up to 20, one credit\neach; a text that makes more lists the rest in ``more_claims``). ``claims`` is a list\nof up to 20 items: exactly one row per item, in order \u2014 the batch rung of\nthe extract \u2192 assess \u2192 verify ladder. Sending both is a 422.",
        "properties": {
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The claim to check. A statement in natural language; several claims in one string are split and handled separately.",
            "title": "Claim"
          },
          "text": {
            "default": "",
            "description": "Accepted alias for `claim`. Send one or the other; `text` is used when it has content.",
            "title": "Text",
            "type": "string"
          },
          "claims": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "A list of up to 20 \u2014 one verdict row each, in order. Use this for the claims `/extract` returned; each item is one claim (\u22642000 chars), not a document. Mutually exclusive with `claim`.",
            "title": "Claims"
          },
          "language": {
            "default": "",
            "description": "ISO 639-1 code for the language of the verdict rows. Omitted: English. `auto`: detected from the submitted text (the same rule as lenz.io: a supported language, or English when the text is short, English or in a language we do not answer in). A code always wins. Responses carry the code that was used, never `auto`. With `claims`, `auto` picks ONE language for the whole request: the language more than half of the items of at least 20 letters agree on, else English; for a list in mixed languages send a code.",
            "title": "Language",
            "type": "string"
          },
          "suggest_rewrite": {
            "default": false,
            "description": "Also write `suggested_rewrite` on each row: the claim with its wrong part corrected, for a claim the check found False or Mostly False with high confidence. Off by default. It costs no extra credit and works in both forms, per row. The rewrite comes from the quick check's reasoning and is not itself verified: review it, or run it through `/verify`, before using it.",
            "title": "Suggest Rewrite",
            "type": "boolean"
          }
        },
        "title": "AssessIn",
        "type": "object"
      },
      "ExtractOut": {
        "description": "The claims found in the submitted text.\n\n`claims` lists every claim found, most check-worthy first: one item for a\nsingle claim, `[]` when there is none.\n\n`status` is `ready` when claims were found, `no_checkable_claim` when no\nclaim in the text could be checked against public evidence, and\n`no_match` when a `focus` was given and no claim falls within it.\n\nWith `locate: true`, only claims traced back to the text are listed, and\neach claim's `positions` give the passages that make it.",
        "properties": {
          "status": {
            "default": "ready",
            "enum": [
              "ready",
              "no_checkable_claim",
              "no_match"
            ],
            "title": "Status",
            "type": "string"
          },
          "claims": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ExtractedClaimOut"
            },
            "title": "Claims",
            "type": "array"
          },
          "domain": {
            "default": "",
            "title": "Domain",
            "type": "string"
          },
          "key_entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ExtractedEntityOut"
            },
            "title": "Key Entities",
            "type": "array"
          },
          "presumed_intent": {
            "default": "",
            "title": "Presumed Intent",
            "type": "string"
          },
          "original_input": {
            "default": "",
            "title": "Original Input",
            "type": "string"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The language the claims are written in, as an ISO 639-1 code: the one you sent, `en` when you sent none, or the detected one when you asked for detection. Pass it on to `/assess` or `/verify` to keep a chain in one language. Absent on a replay of a response stored before this field existed.",
            "title": "Language"
          }
        },
        "title": "ExtractOut",
        "type": "object"
      },
      "ExtractedClaimOut": {
        "properties": {
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "positions": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/PositionOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Only with `locate: true`: every place the text makes this claim, in text order, at most 10. `null` when `locate` was not set or the claims could not be located.",
            "title": "Positions"
          }
        },
        "required": [
          "claim"
        ],
        "title": "ExtractedClaimOut",
        "type": "object"
      },
      "ExtractedEntityOut": {
        "properties": {
          "name": {
            "default": "",
            "title": "Name",
            "type": "string"
          },
          "type": {
            "default": "",
            "title": "Type",
            "type": "string"
          }
        },
        "title": "ExtractedEntityOut",
        "type": "object"
      },
      "PositionOut": {
        "properties": {
          "start": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the passage starts in `text` as you sent it, in Unicode code points (not UTF-16 units or bytes). Half-open with `end`. `null` when `text` was a URL: the page is not returned, so there is nothing to index, and `text` carries the passage instead.",
            "title": "Start"
          },
          "end": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the passage ends, exclusive; `null` as for `start`.",
            "title": "End"
          },
          "text": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The passage itself, as it appears in the text. `null` on a citation position, whose row already carries the statement.",
            "title": "Text"
          }
        },
        "required": [
          "start",
          "end",
          "text"
        ],
        "title": "PositionOut",
        "type": "object"
      },
      "ExtractIn": {
        "properties": {
          "text": {
            "description": "The document to extract claims from. Up to 50,000 characters; longer input is truncated. Or a single public web page URL (http or https, nothing else in the field): Lenz reads the page, or a YouTube video's transcript, and extracts the claims from its first 50,000 characters.",
            "title": "Text",
            "type": "string"
          },
          "language": {
            "default": "",
            "description": "ISO 639-1 code for the language of the emitted claims. Omitted: English. `auto`: detected from the submitted text (the same rule as lenz.io: a supported language, or English when the text is short, English or in a language we do not answer in). A code always wins. Responses carry the code that was used, never `auto`. For a `text` that is one URL, `auto` reads the page.",
            "title": "Language",
            "type": "string"
          },
          "focus": {
            "default": "",
            "description": "Optional. Narrows the result to the claims this describes, e.g. \"market size, growth and competitors\". At most 300 characters \u2014 a longer focus is rejected, never truncated. A focus can only select from the claims the extractor found: it cannot add a claim, reword one, reorder them, or change what counts as a claim. When nothing matches, `status` is `no_match` and `claims` is empty; the unfocused list is never substituted.",
            "maxLength": 300,
            "title": "Focus",
            "type": "string"
          },
          "locate": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "Optional, default `false`. When `true`, only claims that could be traced directly back to your text are returned, and each claim's `positions` say where in the text it is made. A claim found nowhere in the text, or found with a different figure, is left out; so is a list that ends up empty, which answers `no_checkable_claim`. Adds a few seconds, never more than 20. If the claims cannot be located, every `positions` is `null` and the list is returned unfiltered.",
            "title": "Locate"
          }
        },
        "required": [
          "text"
        ],
        "title": "ExtractIn",
        "type": "object"
      },
      "SelectIn": {
        "properties": {
          "claims": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "The claims to verify, as strings: the `claim` of each entry in the status response's `claims` (`text` in API version `2026-05-13`), copied verbatim.",
            "title": "Claims"
          },
          "texts": {
            "description": "Accepted alias for `claims`. Send one or the other; `texts` is used when it has content.",
            "items": {
              "type": "string"
            },
            "title": "Texts",
            "type": "array"
          }
        },
        "title": "SelectIn",
        "type": "object"
      },
      "AssessmentOut": {
        "description": "An adjudicator's individual assessment. Nested under ``audit``.\n\nCurrent verifications carry three independent reviewers (``Reviewer A``\nto ``Reviewer C``), each assigned a model from a different vendor (after a\nprovider failure a reviewer can run on another vendor's model), and two\nmore (``Reviewer D``, ``Reviewer E``) when those three disagree, all\nrunning the same checks over the evidence; ``warnings`` carries the source\nissues, evidence gaps and precision issues that reviewer found, in one\nlist. ``panelist_name`` is a display value, not a stable key.\nVerifications from before the change carry the specialist panelists\ninstead, one flag category each: logical fallacies (Logic Examiner),\nprecision issues (Precision Analyst), weakest sources (Source Auditor)\nand, before 2026-06, missing context (Context Analyst).",
        "properties": {
          "panelist_name": {
            "default": "",
            "title": "Panelist Name",
            "type": "string"
          },
          "focus_area": {
            "default": "",
            "title": "Focus Area",
            "type": "string"
          },
          "score": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Score"
          },
          "reasoning": {
            "default": "",
            "title": "Reasoning",
            "type": "string"
          },
          "warnings": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Warnings",
            "type": "array"
          }
        },
        "title": "AssessmentOut",
        "type": "object"
      },
      "AuditOut": {
        "description": "Audit / explainability block \u2014 for callers that need to show their work.\n\n``panel_agreement`` is derived from the panel: ``unanimous`` (all agree),\n``majority`` (score spread <= 2), or ``split`` \u2014 over every reviewer that\nvoted, so a panel that called in Reviewers D and E is counted whole.\nFor \"No Public Record\" it counts the no-record votes (``unanimous`` when\nevery voting reviewer voted no-record, ``majority`` when most did), and is\n``''`` when no panel voted (decided by research alone); its debate is\nempty.",
        "properties": {
          "adjudication_summary": {
            "default": "",
            "title": "Adjudication Summary",
            "type": "string"
          },
          "assessments": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/AssessmentOut"
            },
            "title": "Assessments",
            "type": "array"
          },
          "debate_pro": {
            "allOf": [
              {
                "$ref": "#/components/schemas/DebateSideOut"
              }
            ],
            "default": {
              "role": "",
              "argument": "",
              "rebuttal": ""
            }
          },
          "debate_con": {
            "allOf": [
              {
                "$ref": "#/components/schemas/DebateSideOut"
              }
            ],
            "default": {
              "role": "",
              "argument": "",
              "rebuttal": ""
            }
          },
          "panel_agreement": {
            "default": "",
            "title": "Panel Agreement",
            "type": "string"
          }
        },
        "title": "AuditOut",
        "type": "object"
      },
      "ClaimDetailOut": {
        "description": "Full verification report.\n\nSlim top-level (verdict + confidence + lenz_score + sources). Audit\ndetail (panel reasoning, debate, individual panelist assessments)\nlives under ``audit``.\n\nSame field vocabulary as ``VerificationListItemOut`` (list view) and\n``AssessClaimOut`` (fast verdict). A consumer that branches on\n``verdict`` or ``confidence`` reads the same field name regardless\nof which endpoint produced the payload.",
        "properties": {
          "verification_id": {
            "title": "Verification Id",
            "type": "string"
          },
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "visibility": {
            "default": "private",
            "title": "Visibility",
            "type": "string"
          },
          "depth": {
            "default": "standard",
            "title": "Depth",
            "type": "string"
          },
          "domain": {
            "default": "",
            "title": "Domain",
            "type": "string"
          },
          "entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/EntityRef"
            },
            "title": "Entities",
            "type": "array"
          },
          "presumed_intent": {
            "default": "",
            "title": "Presumed Intent",
            "type": "string"
          },
          "verdict": {
            "default": "",
            "description": "`True`, `Mostly True`, `Mixed`, `Mostly False` or `False`, or `No Public Record`: Lenz found no public record that settles the claim, which does not make it false. It has no `lenz_score` (null), a `confidence`, and is never warranted. Version `2026-05-13` never receives it: it reads such a run as a failure (`research_empty` when no source was found, else `research_insufficient`).",
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "default": "low",
            "title": "Confidence",
            "type": "string"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "1-10; null for `No Public Record`.",
            "title": "Lenz Score"
          },
          "key_finding": {
            "default": "",
            "title": "Key Finding",
            "type": "string"
          },
          "executive_summary": {
            "default": "",
            "title": "Executive Summary",
            "type": "string"
          },
          "warnings": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Warnings",
            "type": "array"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "A suggested rewrite of `claim` that this verification's findings support, to use in place of the original sentence. It has not been verified itself: before using it, review it or run it through `/verify`. `null` for a true claim, when no correction is established, and on verifications that predate the field. On every verification, single or listed; not on `/assess` rows.",
            "title": "Suggested Rewrite"
          },
          "created_at": {
            "default": "",
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "default": "",
            "description": "When the verification finished (ISO 8601). Always set on a completed verification; a rerun moves it. API version `2026-05-13` sends `modified_at` instead: this time, but only when it falls on a later UTC calendar day than `created_at`, else null.",
            "title": "Completed At",
            "type": "string"
          },
          "sources": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/SourceOut"
            },
            "title": "Sources",
            "type": "array"
          },
          "audit": {
            "allOf": [
              {
                "$ref": "#/components/schemas/AuditOut"
              }
            ],
            "default": {
              "adjudication_summary": "",
              "assessments": [],
              "debate_pro": {
                "argument": "",
                "rebuttal": "",
                "role": ""
              },
              "debate_con": {
                "argument": "",
                "rebuttal": "",
                "role": ""
              },
              "panel_agreement": ""
            }
          },
          "language": {
            "title": "Language",
            "type": "string"
          },
          "coverage": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/CoverageOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "verification_id",
          "claim",
          "language"
        ],
        "title": "ClaimDetailOut",
        "type": "object"
      },
      "ClaimOptionOut": {
        "description": "One claim a ``needs_input`` (``multi_claim``) poll offers. Send ``claim``,\nverbatim, to ``POST /verify/{task_id}/select``.\n\nAPI version ``2026-05-13`` calls the field ``text`` (``CandidateClaimOut``).",
        "properties": {
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "domain": {
            "default": "",
            "title": "Domain",
            "type": "string"
          },
          "text": {
            "type": "string",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `claim`."
          }
        },
        "required": [
          "claim"
        ],
        "title": "ClaimOptionOut",
        "type": "object"
      },
      "CoverageOut": {
        "description": "Whether this verdict carries a warranty, and if not, why not.\n\nPresent only when covered verification is enabled. It describes the pair\n(this account, this analysis), not the analysis alone: two accounts can\nhold two certificates over one cached verdict, so the block one customer\nsees is never the block another sees.\n\n``reasons`` is empty exactly when ``status`` is not ``uncovered``. The\nvocabulary is closed and deliberately smaller than the set of rules\nbehind the decision: ``plan`` and ``depth`` are actionable, ``account``\nmeans the account turned certificates off (Pro and Scale), ``verdict`` is\na product rule callers design around, ``quality`` covers everything a\ncaller can neither act on nor define, and ``withdrawn`` / ``issue_failed``\nare statements about Lenz rather than about the caller's claim.",
        "properties": {
          "status": {
            "default": "uncovered",
            "enum": [
              "covered",
              "uncovered",
              "pending_timestamp"
            ],
            "title": "Status",
            "type": "string"
          },
          "reasons": {
            "default": [],
            "items": {
              "enum": [
                "plan",
                "account",
                "depth",
                "verdict",
                "quality",
                "withdrawn",
                "issue_failed"
              ],
              "type": "string"
            },
            "title": "Reasons",
            "type": "array"
          },
          "certificate_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Certificate Id"
          },
          "certificate_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Certificate Url"
          },
          "as_of": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "As Of"
          },
          "currency": {
            "default": "",
            "title": "Currency",
            "type": "string"
          },
          "cap": {
            "default": 0,
            "title": "Cap",
            "type": "integer"
          },
          "aggregate": {
            "default": 0,
            "title": "Aggregate",
            "type": "integer"
          },
          "terms_version": {
            "default": "",
            "title": "Terms Version",
            "type": "string"
          }
        },
        "title": "CoverageOut",
        "type": "object"
      },
      "DebateSideOut": {
        "description": "One side of the debate (pro or con). Nested under ``audit``.",
        "properties": {
          "role": {
            "default": "",
            "title": "Role",
            "type": "string"
          },
          "argument": {
            "default": "",
            "title": "Argument",
            "type": "string"
          },
          "rebuttal": {
            "default": "",
            "title": "Rebuttal",
            "type": "string"
          }
        },
        "title": "DebateSideOut",
        "type": "object"
      },
      "ProgressOut": {
        "description": "Where a running verification has got to. Advisory \u2014 never results.\n\n``step`` is a closed set, so it is safe to switch on. ``index`` is the\n1-based stage position (0 while ``starting``) out of ``total``; read\n``total`` off the response rather than hard-coding it, since stages may\nbe added.\n\n``index`` is stage POSITION, not elapsed work: the stages are uneven, so\na client rendering it as a bar will see it sit on ``research`` for roughly\nhalf the run. ``elapsed_seconds`` is a measurement of how long the run has\nbeen going, never an estimate of what is left.",
        "properties": {
          "step": {
            "enum": [
              "starting",
              "framing",
              "research",
              "debate",
              "adjudication",
              "conclusion"
            ],
            "title": "Step",
            "type": "string"
          },
          "index": {
            "title": "Index",
            "type": "integer"
          },
          "total": {
            "title": "Total",
            "type": "integer"
          },
          "elapsed_seconds": {
            "title": "Elapsed Seconds",
            "type": "integer"
          },
          "poll_after_seconds": {
            "title": "Poll After Seconds",
            "type": "integer"
          }
        },
        "required": [
          "step",
          "index",
          "total",
          "elapsed_seconds",
          "poll_after_seconds"
        ],
        "title": "ProgressOut",
        "type": "object"
      },
      "SourceOut": {
        "description": "A research source used to evaluate a claim.\n\n``date`` is the source article's publication date (a source-level\nattribute, not a Lenz API event time \u2014 so it's not renamed to\n``published_at``).",
        "properties": {
          "source_name": {
            "default": "",
            "title": "Source Name",
            "type": "string"
          },
          "title": {
            "default": "",
            "title": "Title",
            "type": "string"
          },
          "url": {
            "default": "",
            "title": "Url",
            "type": "string"
          },
          "snippet": {
            "default": "",
            "description": "The sentence(s) quoted from the source page, verbatim and in the page's own language, with ` \u2026 ` between separate passages. A few sources carry no verified quote \u2014 for those it is the surrounding passage instead, which may run longer and contain line breaks.",
            "title": "Snippet",
            "type": "string"
          },
          "snippet_language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The language of `snippet` (the source page's own language) as an ISO 639-1 code (e.g. `uk`, `pt`), when it is not English; null for English or when unknown. The verdict's own language is `language`.",
            "title": "Snippet Language"
          },
          "date": {
            "default": "",
            "title": "Date",
            "type": "string"
          }
        },
        "title": "SourceOut",
        "type": "object"
      },
      "StatusOut": {
        "description": "Body of ``GET /verify/status/{task_id}``.\n\nFive shapes keyed on ``status``, and only the fields belonging to the\ncurrent one are present \u2014``processing`` carries ``progress``,\n``needs_input`` carries ``reason``, ``claims`` and ``hint``,\n``completed`` carries ``result``, ``failed`` carries ``failure``, and\n``cancelled`` (the run was stopped with\n``POST /verify/{task_id}/cancel``) carries nothing more: it was not\ncharged and has no verification.\nBranch on ``status`` and read the fields for that branch; absent is\nmeaningful, so do not treat a missing key as an empty one.\n\n``task_id`` is echoed on every shape, so a caller polling several\nverifications in one loop can tell the replies apart without threading\nthe id through their own call site.",
        "properties": {
          "status": {
            "enum": [
              "processing",
              "needs_input",
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "progress": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ProgressOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "reason": {
            "anyOf": [
              {
                "const": "multi_claim",
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reason"
          },
          "claims": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ClaimOptionOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claims"
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ClaimDetailOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Hint"
          }
        },
        "required": [
          "status",
          "task_id"
        ],
        "title": "StatusOut",
        "type": "object"
      },
      "CancelOut": {
        "description": "Body of ``POST /verify/{task_id}/cancel``.\n\n``cancelled`` is true when the run is cancelled after this call, whether\nthis call stopped it or an earlier one did (a repeat is safe). A run that\nhad already finished is not touched: ``cancelled`` is false and ``status``\nsays how it ended (``completed``: the verification was saved and charged\nas usual). ``status`` is the same word ``GET /verify/status/{task_id}``\nanswers at that moment (version ``2026-05-13`` reads a cancelled run as\n``failed``, with ``cancelled: true``).\n\nA cancelled run is not charged and has no verification; model work already\nunder way when it stopped is not billed to you. The run itself stops at its\nnext step.",
        "properties": {
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "cancelled": {
            "title": "Cancelled",
            "type": "boolean"
          },
          "status": {
            "enum": [
              "processing",
              "needs_input",
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          }
        },
        "required": [
          "task_id",
          "cancelled",
          "status"
        ],
        "title": "CancelOut",
        "type": "object"
      },
      "MeUsageCreditsOut": {
        "description": "The account's credit balance \u2014 the one pool every capability spends.\n\nTwo buckets: the monthly allowance for the current plan (resets at\n``resets_at``) and non-expiring ``extra`` credits from grants and top-ups,\nwhich are spent only once the allowance is gone. ``remaining`` is the sum\nand is what a call is checked against.\n\n``bonus`` is a DEPRECATED alias of ``extra`` (the balance's name until\n2026-09-15); read ``extra``. It stays for existing callers. It was renamed because the balance holds top-ups you paid for as\nwell as grants.",
        "properties": {
          "total": {
            "default": 0,
            "title": "Total",
            "type": "integer"
          },
          "used": {
            "default": 0,
            "title": "Used",
            "type": "integer"
          },
          "remaining": {
            "default": 0,
            "title": "Remaining",
            "type": "integer"
          },
          "extra": {
            "default": 0,
            "title": "Extra",
            "type": "integer"
          },
          "bonus": {
            "default": 0,
            "deprecated": true,
            "title": "Bonus",
            "type": "integer",
            "description": "Sent only to callers on `2026-05-13`; use `extra`."
          },
          "resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Resets At"
          }
        },
        "title": "MeUsageCreditsOut",
        "type": "object"
      },
      "MeUsageExtractOut": {
        "description": "Daily ``/extract`` usage (rate-limited per day, not credit-based).\n\n``calls_today`` is the ACCOUNT's counter, shared across all of its keys;\n``unlimited`` reports whether the CALLING key bypasses the cap.",
        "properties": {
          "calls_today": {
            "default": 0,
            "title": "Calls Today",
            "type": "integer"
          },
          "daily_limit": {
            "default": 0,
            "title": "Daily Limit",
            "type": "integer"
          },
          "unlimited": {
            "default": false,
            "title": "Unlimited",
            "type": "boolean"
          }
        },
        "title": "MeUsageExtractOut",
        "type": "object"
      },
      "MeUsageOut": {
        "description": "The calling account's credit balance, and what it can still buy.\n\n``credits`` is the balance and ``costs`` is the price list. Those two,\nplus ``cost_options``, are the whole contract for a new integration. The\ncurrent shape is ``credits``, ``costs``, ``cost_options``, ``extract``,\n``plan``, ``plan_label`` and ``has_webhook_secret``.\n\nCallers on API version ``2026-05-13`` also get the DEPRECATED fields, kept\nfor them: the ``verify`` / ``ask`` / ``assess`` blocks\n(projections of that same pool into each capability's unit) with their\n``credits`` alias, ``credits.bonus`` and ``quota_resets_at``.\n\n``extract`` is free at the pool (``costs.extract`` is 0) and carries a\nper-account daily fair-use cap instead; it rejects with 429, not 402.\n\nThe Pro plan's ``plan`` is ``pro`` since 2026-09-15; it was ``developer``\nbefore. ``plan_label`` reads \"Pro\" either way.",
        "properties": {
          "plan": {
            "default": "free",
            "title": "Plan",
            "type": "string"
          },
          "plan_label": {
            "default": "Free",
            "title": "Plan Label",
            "type": "string"
          },
          "quota_resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "title": "Quota Resets At",
            "description": "Sent only to callers on `2026-05-13`; use `credits.resets_at`."
          },
          "credits": {
            "$ref": "#/components/schemas/MeUsageCreditsOut"
          },
          "costs": {
            "additionalProperties": {
              "type": "integer"
            },
            "title": "Costs",
            "type": "object"
          },
          "cost_options": {
            "additionalProperties": {
              "additionalProperties": {
                "additionalProperties": {
                  "type": "integer"
                },
                "type": "object"
              },
              "type": "object"
            },
            "default": {},
            "title": "Cost Options",
            "type": "object"
          },
          "verify": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/MeUsageQuotaOut"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; divide `credits` by `costs`."
          },
          "ask": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/MeUsageQuotaOut"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; divide `credits` by `costs`."
          },
          "assess": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/MeUsageQuotaOut"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; divide `credits` by `costs`."
          },
          "extract": {
            "$ref": "#/components/schemas/MeUsageExtractOut"
          },
          "has_webhook_secret": {
            "default": false,
            "title": "Has Webhook Secret",
            "type": "boolean"
          }
        },
        "required": [
          "credits",
          "costs",
          "extract"
        ],
        "title": "MeUsageOut",
        "type": "object"
      },
      "MeUsageQuotaOut": {
        "description": "DEPRECATED. One capability's share of the pool, projected into its unit.\n\nSent only to API version ``2026-05-13`` callers and kept for them, with\nthe per-block ``credits`` alias below. Read\n``MeUsageOut.credits`` and ``MeUsageOut.costs`` instead and do the\ndivision \u2014 it is one line, and it is the same one this block does::\n\n    remaining = credits.remaining // costs[capability]\n    total     = credits.total     // costs[capability]\n    used      = total - remaining\n\nThese are **projections, not allowances**. Every billable capability draws\non the single balance in ``MeUsageOut.credits``, at the weight in\n``MeUsageOut.costs``; this block answers \"how many ``/verify`` calls could\nI still make if I spent everything on them\". Spending on any capability\nmoves every block, and the division floors \u2014 a ``verify`` block whose\nweight is 10 ticks once per 10 credits spent anywhere.\n\nThey predate the pool, when each really was its own allowance, and that is\nwhy the current shape leaves them out: two capabilities at the same price emit\nbyte-identical objects (``ask`` and ``assess`` are both 1 credit today),\nso the shape suggests a per-capability allowance that no longer exists.\n\n``bonus`` is ``MeUsageOut.credits.extra``, the non-expiring balance, in\nthis capability's unit.\n``quota_used`` is derived as ``quota_total - quota_remaining``, so\n``used + remaining == total`` always holds.\n\n``credits`` is a DEPRECATED alias of ``bonus``, kept for the same callers;\nread ``MeUsageOut.credits`` for the pool. It never meant the pool \u2014 before the pool existed it\nmeant this capability's one-off top-up balance, which is exactly what\n``bonus`` now reports.",
        "properties": {
          "quota_used": {
            "default": 0,
            "title": "Quota Used",
            "type": "integer"
          },
          "quota_total": {
            "default": 0,
            "title": "Quota Total",
            "type": "integer"
          },
          "quota_remaining": {
            "default": 0,
            "title": "Quota Remaining",
            "type": "integer"
          },
          "bonus": {
            "default": 0,
            "title": "Bonus",
            "type": "integer"
          },
          "credits": {
            "default": 0,
            "title": "Credits",
            "type": "integer"
          },
          "remaining": {
            "default": 0,
            "title": "Remaining",
            "type": "integer"
          }
        },
        "title": "MeUsageQuotaOut",
        "type": "object"
      },
      "VerificationNotFoundOut": {
        "description": "404 from ``GET /verifications/{id}``.\n\n``hint`` is present when the id has the shape of a task_id, and points at\n``GET /verify/status/{task_id}``.",
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "default": "not_found",
            "description": "Version `2026-05-13` leaves it out.",
            "title": "Code",
            "type": "string"
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Hint"
          }
        },
        "required": [
          "detail"
        ],
        "title": "VerificationNotFoundOut",
        "type": "object"
      },
      "VerificationNotReadyOut": {
        "description": "409 from ``GET /verifications/{id}`` for a task_id with no result yet.\n\nThe endpoint accepts the task_id ``/verify`` returned, and a completed run\nreads exactly as its verification_id would. A run that has not completed\nhas no verification to return, so it answers 409. ``status`` says why:\nstill ``processing``, waiting on\n``needs_input``, or ``failed``. Poll ``GET /verify/status/{task_id}`` for\nprogress, the options a ``needs_input`` run offers, or the full failure.\n\n``failure`` is present on ``failed`` only.",
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "enum": [
              "verification_not_ready",
              "verification_failed"
            ],
            "title": "Code",
            "type": "string"
          },
          "status": {
            "enum": [
              "processing",
              "needs_input",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "hint": {
            "title": "Hint",
            "type": "string"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "detail",
          "code",
          "status",
          "task_id",
          "hint"
        ],
        "title": "VerificationNotReadyOut",
        "type": "object"
      },
      "VerificationPurgedOut": {
        "description": "410 for a verification its account's retention period has removed.\n\nAnswered by ``GET /verifications/{id}``, ``GET /verify/status/{task_id}``\nfor a completed task, ``/related`` and ``/ask``, and only to a caller who\ncould read the verification: anyone else gets the usual 404. The\ncertificate of a covered verification stays available.",
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "default": "purged",
            "title": "Code",
            "type": "string"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Purged At"
          }
        },
        "required": [
          "detail"
        ],
        "title": "VerificationPurgedOut",
        "type": "object"
      },
      "RelatedVerificationsOut": {
        "description": "Wrapper for ``GET /verifications/{id}/related``.\n\nEmpty ``items`` when the verification has no embedding yet (early\npipeline) or no public-library claim is close enough.",
        "properties": {
          "items": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/SimilarVerificationOut"
            },
            "title": "Items",
            "type": "array"
          }
        },
        "title": "RelatedVerificationsOut",
        "type": "object"
      },
      "SimilarVerificationOut": {
        "description": "An existing public verification that semantically resembles a\ngiven claim text: an item in ``GET /verifications/{id}/related``, for\ncallers surfacing \"see also\" references next to a verdict.",
        "properties": {
          "verification_id": {
            "title": "Verification Id",
            "type": "string"
          },
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "verdict": {
            "default": "",
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "default": "low",
            "title": "Confidence",
            "type": "string"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Lenz Score"
          },
          "url": {
            "default": "",
            "title": "Url",
            "type": "string"
          },
          "distance": {
            "title": "Distance",
            "type": "number"
          }
        },
        "required": [
          "verification_id",
          "claim",
          "distance"
        ],
        "title": "SimilarVerificationOut",
        "type": "object"
      },
      "AskIn": {
        "properties": {
          "message": {
            "description": "The follow-up question. Maximum 500 characters.",
            "title": "Message",
            "type": "string"
          },
          "language": {
            "default": "",
            "description": "ISO 639-1 code for the language of the answer. Omitted, or `auto`: the verification's own language (English for older ones); the question is never language-detected. A code overrides it.",
            "title": "Language",
            "type": "string"
          }
        },
        "required": [
          "message"
        ],
        "title": "AskIn",
        "type": "object"
      },
      "ReviewAcceptedOut": {
        "properties": {
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "const": "queued",
            "description": "The acceptance receipt, not the current state.",
            "title": "Status",
            "type": "string"
          }
        },
        "required": [
          "review_id",
          "status"
        ],
        "title": "ReviewAcceptedOut",
        "type": "object"
      },
      "ReviewErrorOut": {
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "title": "Code",
            "type": "string"
          },
          "upgrade_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Upgrade Url"
          },
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Limit"
          },
          "scope": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Scope"
          },
          "wall_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Wall Id"
          },
          "remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Remaining"
          },
          "credits_remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Credits Remaining"
          },
          "cost": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cost"
          },
          "resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Resets At"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Docs Url"
          },
          "review_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Review Id"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Purged At"
          },
          "retry_after": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Seconds to wait before sending again; the same value as the `Retry-After` header.",
            "title": "Retry After"
          },
          "retry_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Sent only to callers on `2026-05-13`; use `retry_after`.",
            "deprecated": true
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "title": "ReviewErrorOut",
        "type": "object"
      },
      "ReviewErrorItemOut": {
        "properties": {
          "loc": {
            "items": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "integer"
                }
              ]
            },
            "title": "Loc",
            "type": "array"
          },
          "msg": {
            "title": "Msg",
            "type": "string"
          },
          "type": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The kind of problem. Version `2026-05-13` leaves it out.",
            "title": "Type"
          },
          "ctx": {
            "anyOf": [
              {
                "additionalProperties": true,
                "type": "object"
              },
              {
                "type": "null"
              }
            ],
            "description": "Pydantic's context for the error (the limit that was exceeded, ...).",
            "title": "Ctx"
          }
        },
        "required": [
          "loc",
          "msg"
        ],
        "title": "ReviewErrorItemOut",
        "type": "object"
      },
      "ReviewValidationErrorOut": {
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "title": "Code",
            "type": "string"
          },
          "errors": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewErrorItemOut"
            },
            "title": "Errors",
            "type": "array"
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "title": "ReviewValidationErrorOut",
        "type": "object"
      },
      "EscalationPolicyIn": {
        "additionalProperties": false,
        "description": "Which quick-checked claims get a deep check. A claim escalates when its\nquick label is in ``verdicts`` OR its confidence band is in ``confidence``.\nBoth may be empty; ``max_verifications: 0`` makes an assess-only review.",
        "properties": {
          "verdicts": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Quick-check labels that get a deep check. Default [\"False\", \"Mostly False\", \"Mixed\", \"No Public Record\"].",
            "title": "Verdicts"
          },
          "confidence": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Quick-check confidence bands that get a deep check (low, medium, high). Default [\"low\"].",
            "title": "Confidence"
          },
          "max_verifications": {
            "anyOf": [
              {
                "maximum": 20,
                "minimum": 0,
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "The deep-check cap. Default 5.",
            "title": "Max Verifications"
          },
          "max_assessments": {
            "anyOf": [
              {
                "maximum": 20,
                "minimum": 0,
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "How many of the draft's claims, most check-worthy first, get a quick verdict. Default 20. 0: no quick checks (a review that checks only the citations).",
            "title": "Max Assessments"
          },
          "depth": {
            "anyOf": [
              {
                "enum": [
                  "standard",
                  "low"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Depth of every deep check. Default standard.",
            "title": "Depth"
          },
          "max_citations": {
            "anyOf": [
              {
                "maximum": 20,
                "minimum": 0,
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "How many of the draft's citations (links, DOIs, [n] markers with a reference list), in its order, are checked: does each source say what the draft attributes to it? 1 credit per checked citation. Default 0: no citation check. Guide: https://lenz.io/docs/citations",
            "title": "Max Citations"
          },
          "suggest_edits": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "For each claim with a suggested rewrite, from its deep check or, when it has none, from its quick check (found False or Mostly False with high confidence), the smallest edits to the draft that make it say what the rewrite says, written in the draft's language (claims[].suggested_edits). No extra credits. The review completes once they are settled. Default false. Guide: https://lenz.io/docs/citations",
            "title": "Suggest Edits"
          }
        },
        "title": "EscalationPolicyIn",
        "type": "object"
      },
      "ReviewIn": {
        "additionalProperties": false,
        "description": "A draft to review: up to 50,000 characters, or one public http(s) URL.",
        "properties": {
          "text": {
            "description": "The draft, up to 50,000 characters (longer text is cut and reported as input_truncated), or one public http(s) URL, read like /extract reads one.",
            "title": "Text",
            "type": "string"
          },
          "language": {
            "default": "",
            "description": "ISO 639-1 code for the output language of every claim and rewrite. Omitted: English. `auto`: detected once from the draft (the same rule as lenz.io: a supported language, or English when the draft is short, English or in a language we do not answer in; a draft that is one URL is read on its page). A code always wins. The review carries the code that was used; for a one-URL draft it reads `auto` until the page is read.",
            "title": "Language",
            "type": "string"
          },
          "webhook_url": {
            "anyOf": [
              {
                "maxLength": 500,
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Omitted or null: the credential's default webhook URL. \"\": no webhook for this review. A URL: review.completed / review.failed go there.",
            "title": "Webhook Url"
          },
          "visibility": {
            "default": "private",
            "description": "Applied to every deep check.",
            "enum": [
              "private",
              "unlisted"
            ],
            "title": "Visibility",
            "type": "string"
          },
          "escalate": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/EscalationPolicyIn"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "text"
        ],
        "title": "ReviewIn",
        "type": "object"
      },
      "ClaimLocationOut": {
        "properties": {
          "claim": {
            "description": "The claim, exactly as it appears in the claim list it belongs to.",
            "title": "Claim",
            "type": "string"
          },
          "positions": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/PositionOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Every place the text makes the claim, in text order, at most 10. `null` only when this claim could not be placed (on /extract every returned claim was placed).",
            "title": "Positions"
          }
        },
        "required": [
          "claim",
          "positions"
        ],
        "title": "ClaimLocationOut",
        "type": "object"
      },
      "ReviewAssessmentCountsOut": {
        "properties": {
          "completed": {
            "title": "Completed",
            "type": "integer"
          },
          "failed": {
            "title": "Failed",
            "type": "integer"
          }
        },
        "required": [
          "completed",
          "failed"
        ],
        "title": "ReviewAssessmentCountsOut",
        "type": "object"
      },
      "ReviewAssessmentOut": {
        "properties": {
          "status": {
            "enum": [
              "pending",
              "running",
              "completed",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "verdict": {
            "anyOf": [
              {
                "enum": [
                  "True",
                  "Mostly True",
                  "Mixed",
                  "Mostly False",
                  "False",
                  "No Public Record"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verdict"
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Rationale"
          },
          "dissent": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Deprecated: always null.",
            "title": "Dissent"
          },
          "searched_pages": {
            "default": [],
            "description": "Pages looked at while assessing this claim, as title and link.",
            "items": {
              "$ref": "#/components/schemas/SearchedPageOut"
            },
            "title": "Searched Pages",
            "type": "array"
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `escalate.suggest_edits`: the claim with its wrong part corrected, from the quick check's reasoning, when it found the claim False or Mostly False with high confidence. Not itself verified. `null` otherwise.",
            "title": "Suggested Rewrite"
          },
          "more_claims": {
            "default": [],
            "description": "Further claims found inside this one, not checked.",
            "items": {
              "type": "string"
            },
            "title": "More Claims",
            "type": "array"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set when status is failed."
          },
          "identified_claims": {
            "description": "Sent only to callers on `2026-05-13`; use `more_claims`.",
            "items": {
              "type": "string"
            },
            "type": "array",
            "deprecated": true
          }
        },
        "required": [
          "status"
        ],
        "title": "ReviewAssessmentOut",
        "type": "object"
      },
      "ReviewCitationCheckOut": {
        "properties": {
          "status": {
            "enum": [
              "pending",
              "running",
              "completed",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "page_read": {
            "anyOf": [
              {
                "enum": [
                  "full",
                  "partial",
                  "not_found",
                  "none"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "What reading the source gave: full, partial (cut short, a teaser or an abstract alone), not_found, none.",
            "title": "Page Read"
          },
          "page_title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Page Title"
          },
          "page_published_date": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Page Published Date"
          },
          "page_language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The language of the page that was read, as an ISO 639-1 code (e.g. `en`, `uk`); null when unknown.",
            "title": "Page Language"
          },
          "source_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the text was actually read from.",
            "title": "Source Url"
          },
          "source_version": {
            "anyOf": [
              {
                "enum": [
                  "published",
                  "accepted",
                  "submitted"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Source Version"
          },
          "support": {
            "anyOf": [
              {
                "enum": [
                  "supported",
                  "partly_supported",
                  "contradicted",
                  "not_in_source",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Support"
          },
          "snippet": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The passage from the source the support answer rests on, checked against the page text.",
            "title": "Snippet"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The reviewer's sentence: reasoning, not a checked source.",
            "title": "Rationale"
          },
          "quote": {
            "anyOf": [
              {
                "enum": [
                  "matched",
                  "not_in_source",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Quote"
          },
          "missing_quote": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The first of quotes the source does not contain; null unless quote is not_in_source.",
            "title": "Missing Quote"
          },
          "doi_registered": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi Registered"
          },
          "metadata": {
            "anyOf": [
              {
                "enum": [
                  "consistent",
                  "mismatch",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Metadata"
          },
          "metadata_differences": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewMetadataDifferenceOut"
            },
            "title": "Metadata Differences",
            "type": "array"
          },
          "registered": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewRegisteredOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "unchecked_reason": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Why the finding is unchecked; an extensible string.",
            "title": "Unchecked Reason"
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Hint"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "status"
        ],
        "title": "ReviewCitationCheckOut",
        "type": "object"
      },
      "ReviewCitationCountsOut": {
        "description": "Three disjoint counts; once every check has ended they add up to citations_selected.",
        "properties": {
          "checked": {
            "description": "A finding other than unchecked.",
            "title": "Checked",
            "type": "integer"
          },
          "unchecked": {
            "description": "Could not be checked, for a reason of the page or the draft.",
            "title": "Unchecked",
            "type": "integer"
          },
          "failed": {
            "description": "No finding, for a reason of ours.",
            "title": "Failed",
            "type": "integer"
          }
        },
        "required": [
          "checked",
          "unchecked",
          "failed"
        ],
        "title": "ReviewCitationCountsOut",
        "type": "object"
      },
      "ReviewCitationFailedRowOut": {
        "properties": {
          "citation_index": {
            "title": "Citation Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "citation_index",
          "reference",
          "cited_url",
          "doi",
          "failure"
        ],
        "title": "ReviewCitationFailedRowOut",
        "type": "object"
      },
      "ReviewCitationIssueOut": {
        "properties": {
          "citation_index": {
            "title": "Citation Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "statement": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Statement"
          },
          "quotes": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Quotes",
            "type": "array"
          },
          "position": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/PositionOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "finding": {
            "enum": [
              "doi_not_found",
              "page_not_found",
              "contradicted",
              "quote_not_in_source",
              "not_in_source",
              "partly_supported",
              "metadata_mismatch",
              "supported",
              "unchecked"
            ],
            "title": "Finding",
            "type": "string"
          },
          "source": {
            "anyOf": [
              {
                "enum": [
                  "doi",
                  "page",
                  "support",
                  "quote",
                  "metadata"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Source"
          },
          "snippet": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set only when source is support.",
            "title": "Snippet"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set only when source is support.",
            "title": "Rationale"
          },
          "metadata_differences": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewMetadataDifferenceOut"
            },
            "title": "Metadata Differences",
            "type": "array"
          },
          "missing_quote": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set only when finding is quote_not_in_source.",
            "title": "Missing Quote"
          },
          "page_title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Page Title"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "citation_index",
          "reference",
          "cited_url",
          "doi",
          "statement",
          "position",
          "finding",
          "source",
          "snippet",
          "rationale",
          "page_title",
          "failure"
        ],
        "title": "ReviewCitationIssueOut",
        "type": "object"
      },
      "ReviewCitationOut": {
        "properties": {
          "index": {
            "title": "Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "statement": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Statement"
          },
          "quotes": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Quotes",
            "type": "array"
          },
          "position": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/PositionOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewCitationResultOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "check": {
            "$ref": "#/components/schemas/ReviewCitationCheckOut"
          }
        },
        "required": [
          "index",
          "reference",
          "cited_url",
          "doi",
          "statement",
          "position",
          "result",
          "check"
        ],
        "title": "ReviewCitationOut",
        "type": "object"
      },
      "ReviewCitationResultOut": {
        "properties": {
          "finding": {
            "enum": [
              "doi_not_found",
              "page_not_found",
              "contradicted",
              "quote_not_in_source",
              "not_in_source",
              "partly_supported",
              "metadata_mismatch",
              "supported",
              "unchecked"
            ],
            "title": "Finding",
            "type": "string"
          },
          "source": {
            "anyOf": [
              {
                "enum": [
                  "doi",
                  "page",
                  "support",
                  "quote",
                  "metadata"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Source"
          },
          "is_issue": {
            "description": "True for every finding except partly_supported, supported and unchecked. partly_supported is reported, with its snippet, but is not an issue.",
            "title": "Is Issue",
            "type": "boolean"
          }
        },
        "required": [
          "finding",
          "source",
          "is_issue"
        ],
        "title": "ReviewCitationResultOut",
        "type": "object"
      },
      "ReviewClaimOut": {
        "properties": {
          "index": {
            "title": "Index",
            "type": "integer"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "positions": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/PositionOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the draft makes this claim: every place, in text order, at most 10, in the same shape as a citation's `position`: `start` / `end` in Unicode code points of `text` as you sent it, half-open, and the passage in `text`. For a URL draft `start` / `end` are `null` and `text` carries the passage. Only claims traced back to the draft are listed at all. `null` when the claim could not be placed, or once a zero-retention draft is gone.",
            "title": "Positions"
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewResultOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "assessment": {
            "$ref": "#/components/schemas/ReviewAssessmentOut"
          },
          "escalation": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewEscalationOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "verification": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewVerificationOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "suggested_edits": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewSuggestedEditsOut"
              },
              {
                "type": "null"
              }
            ],
            "description": "Asked with `escalate.suggest_edits`. They follow the row's suggested rewrite: its completed deep check's, else its quick check's (see the issue's `source`). `null` when not asked, when the claim has no suggested rewrite, when the draft's passage is not in a supported language or could not be placed, or once a zero-retention draft is gone. Guide: https://lenz.io/docs/citations#suggested-edits"
          }
        },
        "required": [
          "index",
          "claim",
          "result",
          "assessment",
          "escalation",
          "verification"
        ],
        "title": "ReviewClaimOut",
        "type": "object"
      },
      "ReviewCreditsOut": {
        "properties": {
          "charged": {
            "description": "Net credits this review cost the account, read from the ledger. Authoritative once no deep check is running.",
            "title": "Charged",
            "type": "integer"
          }
        },
        "required": [
          "charged"
        ],
        "title": "ReviewCreditsOut",
        "type": "object"
      },
      "ReviewEntityOut": {
        "properties": {
          "name": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Name"
          },
          "qid": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Qid"
          }
        },
        "title": "ReviewEntityOut",
        "type": "object"
      },
      "ReviewEscalationOut": {
        "properties": {
          "matched_rules": {
            "items": {
              "enum": [
                "verdict",
                "confidence"
              ],
              "type": "string"
            },
            "title": "Matched Rules",
            "type": "array"
          },
          "disposition": {
            "enum": [
              "not_selected",
              "planned",
              "cap",
              "credits",
              "account_cap"
            ],
            "title": "Disposition",
            "type": "string"
          }
        },
        "required": [
          "matched_rules",
          "disposition"
        ],
        "title": "ReviewEscalationOut",
        "type": "object"
      },
      "ReviewFailedRowOut": {
        "properties": {
          "claim_index": {
            "title": "Claim Index",
            "type": "integer"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "stage": {
            "enum": [
              "assessment",
              "verification"
            ],
            "title": "Stage",
            "type": "string"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "claim_index",
          "claim",
          "stage",
          "failure"
        ],
        "title": "ReviewFailedRowOut",
        "type": "object"
      },
      "ReviewFullOut": {
        "properties": {
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "description": "verifying: deep checks or citation checks are running. cancelled: you cancelled it (POST /reviews/{review_id}/cancel); only what it delivered before that is charged.",
            "enum": [
              "queued",
              "assessing",
              "verifying",
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "outcome": {
            "anyOf": [
              {
                "enum": [
                  "clean",
                  "issues_found",
                  "incomplete",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Null until terminal. clean covers the selected claims at the policy's chosen depth. issues_found with an empty issues[] means the rows are in citation_issues[]. A deep check that reads \"No Public Record\" is an issue (not on the public record).",
            "title": "Outcome"
          },
          "created_at": {
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Completed At"
          },
          "language": {
            "description": "The language the review is written in, as an ISO 639-1 code. `auto` only while a review sent with `language: \"auto\"` on a draft that is one URL has not read its page yet; then the detected code, or `en` when the page could not be read.",
            "title": "Language",
            "type": "string"
          },
          "policy": {
            "$ref": "#/components/schemas/ReviewPolicyOut"
          },
          "summary": {
            "$ref": "#/components/schemas/ReviewSummaryOut"
          },
          "credits": {
            "$ref": "#/components/schemas/ReviewCreditsOut"
          },
          "poll_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Poll After Seconds"
          },
          "issues": {
            "items": {
              "$ref": "#/components/schemas/ReviewIssueOut"
            },
            "title": "Issues",
            "type": "array"
          },
          "failures": {
            "items": {
              "$ref": "#/components/schemas/ReviewFailedRowOut"
            },
            "title": "Failures",
            "type": "array"
          },
          "citation_issues": {
            "default": [],
            "description": "Citations whose source does not say what the draft says, the most serious first; partly_supported rows are not issues and are only in citations[]. [] when the check was not asked.",
            "items": {
              "$ref": "#/components/schemas/ReviewCitationIssueOut"
            },
            "title": "Citation Issues",
            "type": "array"
          },
          "citation_failures": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationFailedRowOut"
            },
            "title": "Citation Failures",
            "type": "array"
          },
          "more_claims": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims found past max_assessments, in the draft's order: found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Claims"
          },
          "more_claim_locations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ClaimLocationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the draft makes each of `more_claims`, in the same order: `{claim, positions}`, the shape `/extract` returns with `locate: true` (see a claim row's `positions`). Null until the draft is read.",
            "title": "More Claim Locations"
          },
          "more_citations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ReviewMoreCitationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations found past the ones selected (up to 100): found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Citations"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "view": {
            "const": "full",
            "title": "View",
            "type": "string"
          },
          "claims": {
            "items": {
              "$ref": "#/components/schemas/ReviewClaimOut"
            },
            "title": "Claims",
            "type": "array"
          },
          "citations": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationOut"
            },
            "title": "Citations",
            "type": "array"
          }
        },
        "required": [
          "review_id",
          "status",
          "outcome",
          "created_at",
          "completed_at",
          "language",
          "policy",
          "summary",
          "credits",
          "poll_after_seconds",
          "issues",
          "failures",
          "failure",
          "view",
          "claims"
        ],
        "title": "ReviewFullOut",
        "type": "object"
      },
      "ReviewIssueOut": {
        "properties": {
          "claim_index": {
            "title": "Claim Index",
            "type": "integer"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "verified_claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verified Claim"
          },
          "verdict": {
            "enum": [
              "True",
              "Mostly True",
              "Mixed",
              "Mostly False",
              "False",
              "No Public Record"
            ],
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "source": {
            "enum": [
              "assessment",
              "verification"
            ],
            "title": "Source",
            "type": "string"
          },
          "verification_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Id"
          },
          "verification_status": {
            "anyOf": [
              {
                "enum": [
                  "processing",
                  "completed",
                  "failed",
                  "cancelled"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Status"
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Url"
          },
          "escalation": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewEscalationOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "key_finding": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Key Finding"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Rationale"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The rewrite the row's edits come from: its completed deep check's, else (with `escalate.suggest_edits`) its quick check's; `source` says which. A suggestion, not itself verified.",
            "title": "Suggested Rewrite"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "suggested_edits": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewSuggestedEditsOut"
              },
              {
                "type": "null"
              }
            ],
            "description": "A copy of its claim row's `suggested_edits`. Asked with `escalate.suggest_edits`. They follow the row's suggested rewrite: its completed deep check's, else its quick check's (see the issue's `source`). `null` when not asked, when the claim has no suggested rewrite, when the draft's passage is not in a supported language or could not be placed, or once a zero-retention draft is gone. Guide: https://lenz.io/docs/citations#suggested-edits"
          }
        },
        "required": [
          "claim_index",
          "claim",
          "verified_claim",
          "verdict",
          "confidence",
          "source",
          "verification_id",
          "verification_status",
          "verification_url",
          "url",
          "escalation",
          "key_finding",
          "rationale",
          "suggested_rewrite",
          "failure"
        ],
        "title": "ReviewIssueOut",
        "type": "object"
      },
      "ReviewIssuesOut": {
        "properties": {
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "description": "verifying: deep checks or citation checks are running. cancelled: you cancelled it (POST /reviews/{review_id}/cancel); only what it delivered before that is charged.",
            "enum": [
              "queued",
              "assessing",
              "verifying",
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "outcome": {
            "anyOf": [
              {
                "enum": [
                  "clean",
                  "issues_found",
                  "incomplete",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Null until terminal. clean covers the selected claims at the policy's chosen depth. issues_found with an empty issues[] means the rows are in citation_issues[]. A deep check that reads \"No Public Record\" is an issue (not on the public record).",
            "title": "Outcome"
          },
          "created_at": {
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Completed At"
          },
          "language": {
            "description": "The language the review is written in, as an ISO 639-1 code. `auto` only while a review sent with `language: \"auto\"` on a draft that is one URL has not read its page yet; then the detected code, or `en` when the page could not be read.",
            "title": "Language",
            "type": "string"
          },
          "policy": {
            "$ref": "#/components/schemas/ReviewPolicyOut"
          },
          "summary": {
            "$ref": "#/components/schemas/ReviewSummaryOut"
          },
          "credits": {
            "$ref": "#/components/schemas/ReviewCreditsOut"
          },
          "poll_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Poll After Seconds"
          },
          "issues": {
            "items": {
              "$ref": "#/components/schemas/ReviewIssueOut"
            },
            "title": "Issues",
            "type": "array"
          },
          "failures": {
            "items": {
              "$ref": "#/components/schemas/ReviewFailedRowOut"
            },
            "title": "Failures",
            "type": "array"
          },
          "citation_issues": {
            "default": [],
            "description": "Citations whose source does not say what the draft says, the most serious first; partly_supported rows are not issues and are only in citations[]. [] when the check was not asked.",
            "items": {
              "$ref": "#/components/schemas/ReviewCitationIssueOut"
            },
            "title": "Citation Issues",
            "type": "array"
          },
          "citation_failures": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationFailedRowOut"
            },
            "title": "Citation Failures",
            "type": "array"
          },
          "more_claims": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims found past max_assessments, in the draft's order: found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Claims"
          },
          "more_claim_locations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ClaimLocationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the draft makes each of `more_claims`, in the same order: `{claim, positions}`, the shape `/extract` returns with `locate: true` (see a claim row's `positions`). Null until the draft is read.",
            "title": "More Claim Locations"
          },
          "more_citations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ReviewMoreCitationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations found past the ones selected (up to 100): found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Citations"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "view": {
            "const": "issues",
            "title": "View",
            "type": "string"
          }
        },
        "required": [
          "review_id",
          "status",
          "outcome",
          "created_at",
          "completed_at",
          "language",
          "policy",
          "summary",
          "credits",
          "poll_after_seconds",
          "issues",
          "failures",
          "failure",
          "view"
        ],
        "title": "ReviewIssuesOut",
        "type": "object"
      },
      "ReviewMetadataDifferenceOut": {
        "properties": {
          "field": {
            "enum": [
              "title",
              "authors",
              "year",
              "journal"
            ],
            "title": "Field",
            "type": "string"
          },
          "cited": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited"
          },
          "registered": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Registered"
          }
        },
        "required": [
          "field"
        ],
        "title": "ReviewMetadataDifferenceOut",
        "type": "object"
      },
      "ReviewMoreCitationOut": {
        "description": "A citation found in the draft and not checked by this request.",
        "properties": {
          "index": {
            "title": "Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "sentence": {
            "description": "The draft sentence around the citation, at most 1,000 characters.",
            "title": "Sentence",
            "type": "string"
          },
          "position": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/PositionOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "index",
          "sentence"
        ],
        "title": "ReviewMoreCitationOut",
        "type": "object"
      },
      "ReviewPolicyOut": {
        "properties": {
          "verdicts": {
            "items": {
              "enum": [
                "True",
                "Mostly True",
                "Mixed",
                "Mostly False",
                "False",
                "No Public Record"
              ],
              "type": "string"
            },
            "title": "Verdicts",
            "type": "array"
          },
          "confidence": {
            "items": {
              "enum": [
                "low",
                "medium",
                "high"
              ],
              "type": "string"
            },
            "title": "Confidence",
            "type": "array"
          },
          "max_verifications": {
            "title": "Max Verifications",
            "type": "integer"
          },
          "max_assessments": {
            "title": "Max Assessments",
            "type": "integer"
          },
          "depth": {
            "enum": [
              "standard",
              "low"
            ],
            "title": "Depth",
            "type": "string"
          },
          "max_citations": {
            "default": 0,
            "title": "Max Citations",
            "type": "integer"
          },
          "suggest_edits": {
            "default": false,
            "title": "Suggest Edits",
            "type": "boolean"
          }
        },
        "required": [
          "verdicts",
          "confidence",
          "max_verifications",
          "max_assessments",
          "depth"
        ],
        "title": "ReviewPolicyOut",
        "type": "object"
      },
      "ReviewRegisteredOut": {
        "properties": {
          "title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Title"
          },
          "authors": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Authors",
            "type": "array"
          },
          "year": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Year"
          },
          "journal": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Journal"
          }
        },
        "title": "ReviewRegisteredOut",
        "type": "object"
      },
      "ReviewResultOut": {
        "properties": {
          "verdict": {
            "enum": [
              "True",
              "Mostly True",
              "Mixed",
              "Mostly False",
              "False",
              "No Public Record"
            ],
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "source": {
            "enum": [
              "assessment",
              "verification"
            ],
            "title": "Source",
            "type": "string"
          },
          "is_issue": {
            "title": "Is Issue",
            "type": "boolean"
          }
        },
        "required": [
          "verdict",
          "confidence",
          "source",
          "is_issue"
        ],
        "title": "ReviewResultOut",
        "type": "object"
      },
      "ReviewSuggestedEditsOut": {
        "description": "The smallest edits to the draft that make it say what the claim's deep\ncheck rewrite says, in the draft's language. Review content, never part of\nthe verification: a verification is shared, your draft is not.",
        "properties": {
          "status": {
            "description": "`pending` while they are computed (poll the review); `completed` once SETTLED, which includes settling on no edit (`edits: []`).",
            "enum": [
              "pending",
              "completed"
            ],
            "title": "Status",
            "type": "string"
          },
          "edits": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/SuggestedEditOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "`null` while pending; `[]` when settled with no edit (the passage could not be edited safely, no edit passed the checks, or computing it failed on our side). Not itself verified: review it before you use it.",
            "title": "Edits"
          }
        },
        "required": [
          "status",
          "edits"
        ],
        "title": "ReviewSuggestedEditsOut",
        "type": "object"
      },
      "ReviewSummaryOut": {
        "properties": {
          "claims_found": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims found in the draft and traced back to it; null until the draft is read.",
            "title": "Claims Found"
          },
          "claims_selected": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims this review works on; null until the draft is read.",
            "title": "Claims Selected"
          },
          "claim_limit": {
            "description": "The resolved max_assessments.",
            "title": "Claim Limit",
            "type": "integer"
          },
          "claim_limit_exceeded": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "True when claims_found is more than claim_limit: the rest are in more_claims, found and not checked. False when every claim found was selected. Null until the draft is read.",
            "title": "Claim Limit Exceeded"
          },
          "input_truncated": {
            "title": "Input Truncated",
            "type": "boolean"
          },
          "assessments": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewAssessmentCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "verifications": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewVerificationCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "issues": {
            "title": "Issues",
            "type": "integer"
          },
          "citations_found": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations with a URL or DOI in the text the review read (after the 50,000 character cut); null until the draft is read, or when the check was not asked.",
            "title": "Citations Found"
          },
          "citations_selected": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "The ones this review works on: the first in the draft's order.",
            "title": "Citations Selected"
          },
          "citation_limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "The resolved cap.",
            "title": "Citation Limit"
          },
          "citation_limit_exceeded": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "True when citations_found is more than citation_limit: the rest are in more_citations, found and not checked. False when every citation found was selected, exactly citation_limit included. Null until the text is read.",
            "title": "Citation Limit Exceeded"
          },
          "citation_checks": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewCitationCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "citation_issues": {
            "default": 0,
            "description": "Rows in citation_issues[]; 0 when the check was not asked.",
            "title": "Citation Issues",
            "type": "integer"
          },
          "citations_skipped": {
            "anyOf": [
              {
                "enum": [
                  "url_input",
                  "switched_off",
                  "insufficient_credits"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Why the check was asked for and did not run.",
            "title": "Citations Skipped"
          },
          "claim_limit_reached": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "Sent only to callers on `2026-05-13`; use `claim_limit_exceeded`. It was true when `claims_found` was at least `claim_limit`, not more than it.",
            "deprecated": true
          },
          "citation_limit_reached": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "Sent only to callers on `2026-05-13`; use `citation_limit_exceeded`.",
            "deprecated": true
          }
        },
        "required": [
          "claims_found",
          "claims_selected",
          "claim_limit",
          "claim_limit_exceeded",
          "input_truncated",
          "assessments",
          "verifications",
          "issues"
        ],
        "title": "ReviewSummaryOut",
        "type": "object"
      },
      "ReviewVerificationCountsOut": {
        "properties": {
          "planned": {
            "title": "Planned",
            "type": "integer"
          },
          "completed": {
            "title": "Completed",
            "type": "integer"
          },
          "failed": {
            "title": "Failed",
            "type": "integer"
          }
        },
        "required": [
          "planned",
          "completed",
          "failed"
        ],
        "title": "ReviewVerificationCountsOut",
        "type": "object"
      },
      "ReviewVerificationOut": {
        "properties": {
          "status": {
            "enum": [
              "processing",
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "content_status": {
            "enum": [
              "available",
              "purged"
            ],
            "title": "Content Status",
            "type": "string"
          },
          "verification_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Id"
          },
          "task_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Task Id"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Language"
          },
          "visibility": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "EFFECTIVE: a same-account cache hit keeps its own.",
            "title": "Visibility"
          },
          "depth": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "EFFECTIVE: a cache hit may serve standard for a low request.",
            "title": "Depth"
          },
          "domain": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Domain"
          },
          "entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewEntityOut"
            },
            "title": "Entities",
            "type": "array"
          },
          "verdict": {
            "anyOf": [
              {
                "enum": [
                  "True",
                  "Mostly True",
                  "Mixed",
                  "Mostly False",
                  "False",
                  "No Public Record"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The deep check's verdict. `\"No Public Record\"` (with `lenz_score: null`): not on the public record. It is an issue (in `issues[]`, with no suggested edit).",
            "title": "Verdict"
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Lenz Score"
          },
          "key_finding": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Key Finding"
          },
          "executive_summary": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Executive Summary"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Suggested Rewrite"
          },
          "warnings": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Warnings",
            "type": "array"
          },
          "created_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Created At"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "When the verification finished; null until it has.",
            "title": "Completed At"
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Url"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "status",
          "content_status"
        ],
        "title": "ReviewVerificationOut",
        "type": "object"
      },
      "SuggestedEditOut": {
        "description": "One replacement in the draft: a `PositionOut` whose span is always\nin `text` as you sent it.",
        "properties": {
          "start": {
            "description": "Where the replaced span starts in `text` as you sent it, in Unicode code points. Half-open with `end`, inside `positions[position]`.",
            "title": "Start",
            "type": "integer"
          },
          "end": {
            "description": "Where the replaced span ends, exclusive.",
            "title": "End",
            "type": "integer"
          },
          "text": {
            "description": "Exactly the slice of `text` at `start`..`end`, as you sent it.",
            "title": "Text",
            "type": "string"
          },
          "position": {
            "description": "Which of the claim row's `positions` the edit sits in (index); a grouping hint.",
            "minimum": 0,
            "title": "Position",
            "type": "integer"
          },
          "replacement": {
            "description": "What replaces it; '' deletes it.",
            "title": "Replacement",
            "type": "string"
          }
        },
        "required": [
          "start",
          "end",
          "text",
          "position",
          "replacement"
        ],
        "title": "SuggestedEditOut",
        "type": "object"
      },
      "CitecheckAcceptedOut": {
        "properties": {
          "citecheck_id": {
            "title": "Citecheck Id",
            "type": "string"
          },
          "status": {
            "const": "queued",
            "description": "The acceptance receipt, not the current state.",
            "title": "Status",
            "type": "string"
          }
        },
        "required": [
          "citecheck_id",
          "status"
        ],
        "title": "CitecheckAcceptedOut",
        "type": "object"
      },
      "CitecheckErrorOut": {
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "title": "Code",
            "type": "string"
          },
          "citecheck_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With idempotency_conflict: the check this key is creating, once it exists.",
            "title": "Citecheck Id"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Purged At"
          },
          "remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `no_credits`: citation checks the balance still covers.",
            "title": "Remaining"
          },
          "upgrade_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Upgrade Url"
          },
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Limit"
          },
          "scope": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Scope"
          },
          "wall_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Wall Id"
          },
          "cost": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cost"
          },
          "resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Resets At"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Docs Url"
          },
          "retry_after": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Seconds to wait before sending again; the same value as the `Retry-After` header.",
            "title": "Retry After"
          },
          "retry_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Sent only to callers on `2026-05-13`; use `retry_after`.",
            "deprecated": true
          },
          "credits_remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Sent only to callers on `2026-05-13`; use `remaining`. On a citation 402 it is the same number: a citation costs one credit.",
            "deprecated": true
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "title": "CitecheckErrorOut",
        "type": "object"
      },
      "CitationPairIn": {
        "additionalProperties": false,
        "description": "One statement and the source it cites: a URL, a DOI or a citation, exactly one.",
        "properties": {
          "statement": {
            "description": "The sentence that cites the source, at most 1,000 characters.",
            "title": "Statement",
            "type": "string"
          },
          "url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The cited page: http or https, at most 2,000 bytes.",
            "title": "Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The cited DOI alone, like 10.1038/nature12373.",
            "title": "Doi"
          },
          "cite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "A source named by its citation, alone: a legal authority such as a US case like `372 U.S. 335` (a caption may precede it), a statute like `42 U.S.C. \u00a7 1983`, a regulation like `17 C.F.R. \u00a7 240.10b-5` or an EU act like `Regulation (EU) 2016/679`, or a DOI. At most 300 characters. Read like a citation found in a text; a DOI is the same as `doi`.",
            "title": "Cite"
          },
          "quotes": {
            "default": [],
            "description": "At most 3 excerpts the statement quotes from the source, each 15 to 500 characters and words of the statement.",
            "items": {
              "type": "string"
            },
            "title": "Quotes",
            "type": "array"
          },
          "cited_title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `doi`: the title the reference gives.",
            "title": "Cited Title"
          },
          "cited_authors": {
            "default": [],
            "description": "With `doi`: the authors, family names, at most 10.",
            "items": {
              "type": "string"
            },
            "title": "Cited Authors",
            "type": "array"
          },
          "cited_year": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `doi`: the year the reference gives, four digits.",
            "title": "Cited Year"
          },
          "cited_journal": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `doi`: the journal the reference gives.",
            "title": "Cited Journal"
          }
        },
        "required": [
          "statement"
        ],
        "title": "CitationPairIn",
        "type": "object"
      },
      "CitecheckIn": {
        "additionalProperties": false,
        "description": "A draft whose citations to check, or the statement-source pairs themselves.",
        "properties": {
          "text": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The draft, up to 50,000 characters, with its links (markdown links, bare URLs, doi: and doi.org forms, [n] markers with a reference list). Send exactly one of text and pairs.",
            "title": "Text"
          },
          "pairs": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/CitationPairIn"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "1 to 20 statement-source pairs to check as they are. Send exactly one of text and pairs.",
            "title": "Pairs"
          },
          "max_citations": {
            "anyOf": [
              {
                "maximum": 20,
                "minimum": 1,
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "With text: how many citations, in the draft's order. Default 20.",
            "title": "Max Citations"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": "",
            "description": "The language Lenz writes the reasoning in. English when omitted. Hints are always in English.",
            "title": "Language"
          },
          "webhook_url": {
            "anyOf": [
              {
                "maxLength": 500,
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Omitted or null: the credential's default webhook URL. \"\": no webhook. A URL: citecheck.completed / citecheck.failed go there.",
            "title": "Webhook Url"
          }
        },
        "title": "CitecheckIn",
        "type": "object"
      },
      "CitecheckOut": {
        "properties": {
          "citecheck_id": {
            "title": "Citecheck Id",
            "type": "string"
          },
          "status": {
            "description": "cancelled: you cancelled it (POST /citechecks/{citecheck_id}/cancel). Only citations it checked before that are charged.",
            "enum": [
              "queued",
              "checking",
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "outcome": {
            "anyOf": [
              {
                "enum": [
                  "clean",
                  "issues_found",
                  "incomplete",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Null until terminal. incomplete: a citation could not be checked for a reason of ours.",
            "title": "Outcome"
          },
          "created_at": {
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Completed At"
          },
          "language": {
            "description": "The language the reasoning is written in, as the review envelope echoes it.",
            "title": "Language",
            "type": "string"
          },
          "poll_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Poll After Seconds"
          },
          "policy": {
            "$ref": "#/components/schemas/CitecheckPolicyOut"
          },
          "summary": {
            "$ref": "#/components/schemas/CitecheckSummaryOut"
          },
          "credits": {
            "$ref": "#/components/schemas/ReviewCreditsOut"
          },
          "citations": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationOut"
            },
            "title": "Citations",
            "type": "array"
          },
          "citation_issues": {
            "default": [],
            "description": "Citations whose source does not say what the draft says, the most serious first; partly_supported rows are not issues and are only in citations[].",
            "items": {
              "$ref": "#/components/schemas/ReviewCitationIssueOut"
            },
            "title": "Citation Issues",
            "type": "array"
          },
          "citation_failures": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationFailedRowOut"
            },
            "title": "Citation Failures",
            "type": "array"
          },
          "more_citations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ReviewMoreCitationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations found in the text past the ones selected (up to 100): found but not checked; send them in a later request to check them. Null until the text is read; [] for pairs.",
            "title": "More Citations"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOut"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "citecheck_id",
          "status",
          "outcome",
          "created_at",
          "completed_at",
          "language",
          "poll_after_seconds",
          "policy",
          "summary",
          "credits",
          "failure"
        ],
        "title": "CitecheckOut",
        "type": "object"
      },
      "CitecheckPolicyOut": {
        "properties": {
          "max_citations": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "How many citations the check selects: for text, the limit (default 20); for pairs, the number of pairs checked.",
            "title": "Max Citations"
          }
        },
        "required": [
          "max_citations"
        ],
        "title": "CitecheckPolicyOut",
        "type": "object"
      },
      "CitecheckSummaryOut": {
        "properties": {
          "citations_found": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations with a URL or DOI in the text, or the pairs sent; null until read.",
            "title": "Citations Found"
          },
          "citations_selected": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Citations Selected"
          },
          "citation_limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Citation Limit"
          },
          "citation_limit_exceeded": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "True when citations_found is more than citation_limit: the rest are in more_citations, found and not checked. False when every citation found was selected, exactly citation_limit included. Null until the text is read.",
            "title": "Citation Limit Exceeded"
          },
          "citation_checks": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewCitationCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "citation_issues": {
            "default": 0,
            "title": "Citation Issues",
            "type": "integer"
          },
          "citation_limit_reached": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "Sent only to callers on `2026-05-13`; use `citation_limit_exceeded`.",
            "deprecated": true
          }
        },
        "title": "CitecheckSummaryOut",
        "type": "object"
      },
      "WebhookPayload": {
        "description": "Body the customer's endpoint receives for a verification event.\n\nOne envelope for every event: ``event``, ``event_id`` (the same on every\nretry: deduplicate on it), ``task_id`` (pollable on\n``GET /verify/status/{task_id}``), ``verification_id`` once the\nverification exists, ``status``, and the body polling returns at that\nmoment under ``verification``. Keys a payload does not carry are absent,\nnot null.\n\nAlways signed with HMAC-SHA256 over the raw body bytes; signature\nrides in the ``X-Lenz-Signature: sha256=<hex>`` header, and the version\nthe body was built in in ``X-Lenz-API-Version``. A webhook follows the\nversion of the request that asked for it; version ``2026-05-13`` sends\nthe earlier flat body (``result`` / ``needs_input`` / ``error`` beside\n``task_id``, no ``event_id``).\n\nThe ``attempt`` field is 1-indexed and includes the initial delivery,\nso values run 1 through 4 (initial + 3 retries).",
        "properties": {
          "event": {
            "title": "Event",
            "type": "string"
          },
          "event_id": {
            "title": "Event Id",
            "type": "string"
          },
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "verification_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Verification Id"
          },
          "batch_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Batch Id"
          },
          "review_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Review Id"
          },
          "status": {
            "title": "Status",
            "type": "string"
          },
          "verification": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/StatusOut"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "coverage": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/CoverageOut"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "attempt": {
            "title": "Attempt",
            "type": "integer"
          },
          "delivered_at": {
            "title": "Delivered At",
            "type": "string"
          }
        },
        "required": [
          "event",
          "event_id",
          "task_id",
          "status",
          "attempt",
          "delivered_at"
        ],
        "title": "WebhookPayload",
        "type": "object"
      },
      "ReviewWebhookPayload": {
        "description": "Body of ``review.completed`` / ``review.failed`` / ``review.cancelled``.\n\n``event_id`` is stable per (review, event): dedupe on it (``attempt``\nchanges on retries). ``delivered_at`` is the attempt time. Version\n``2026-05-13`` also sends ``task_id``, an internal delivery identity that\nis not pollable on ``/verify/status``.",
        "properties": {
          "event": {
            "enum": [
              "review.completed",
              "review.failed",
              "review.cancelled"
            ],
            "title": "Event",
            "type": "string"
          },
          "event_id": {
            "title": "Event Id",
            "type": "string"
          },
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "enum": [
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "review": {
            "$ref": "#/components/schemas/ReviewFullOut"
          },
          "attempt": {
            "title": "Attempt",
            "type": "integer"
          },
          "delivered_at": {
            "title": "Delivered At",
            "type": "string"
          }
        },
        "required": [
          "event",
          "event_id",
          "review_id",
          "status",
          "review",
          "attempt",
          "delivered_at"
        ],
        "title": "ReviewWebhookPayload",
        "type": "object"
      },
      "CitecheckWebhookPayload": {
        "description": "Body of ``citecheck.completed`` / ``citecheck.failed`` / ``citecheck.cancelled``.\n\n``event_id`` is stable per (check, event): dedupe on it. Version\n``2026-05-13`` also sends ``task_id``, an internal delivery identity that\nis not pollable on ``/verify/status``.",
        "properties": {
          "event": {
            "enum": [
              "citecheck.completed",
              "citecheck.failed",
              "citecheck.cancelled"
            ],
            "title": "Event",
            "type": "string"
          },
          "event_id": {
            "title": "Event Id",
            "type": "string"
          },
          "citecheck_id": {
            "title": "Citecheck Id",
            "type": "string"
          },
          "status": {
            "enum": [
              "completed",
              "failed",
              "cancelled"
            ],
            "title": "Status",
            "type": "string"
          },
          "citecheck": {
            "$ref": "#/components/schemas/CitecheckOut"
          },
          "attempt": {
            "title": "Attempt",
            "type": "integer"
          },
          "delivered_at": {
            "title": "Delivered At",
            "type": "string"
          }
        },
        "required": [
          "event",
          "event_id",
          "citecheck_id",
          "status",
          "citecheck",
          "attempt",
          "delivered_at"
        ],
        "title": "CitecheckWebhookPayload",
        "type": "object"
      },
      "ValidationErrorItemOut": {
        "title": "ValidationErrorItemOut",
        "type": "object",
        "description": "One field to fix: where (`loc`, as the request names it), what (`msg`) and the kind (`type`).",
        "properties": {
          "loc": {
            "type": "array",
            "items": {
              "anyOf": [
                {
                  "type": "string"
                },
                {
                  "type": "integer"
                }
              ]
            }
          },
          "msg": {
            "type": "string"
          },
          "type": {
            "type": "string"
          },
          "ctx": {
            "type": "object",
            "description": "Pydantic's context for the error (the limit that was exceeded, ...)."
          }
        },
        "required": [
          "loc",
          "msg",
          "type"
        ],
        "additionalProperties": true
      },
      "ErrorOut": {
        "title": "ErrorOut",
        "type": "object",
        "description": "Every error response: `detail` is one sentence on what happened and `code` names it (every code is listed at https://lenz.io/docs/errors#codes). A field you must fix adds `errors`. Waits are `retry_after` (seconds, the same value as the `Retry-After` header); a docs link is `docs_url`. Some codes add their own fields: a 402 carries `upgrade_url`, `wall_id`, `cost` and the balance, a 429 `limit` and `upgrade_url`.",
        "properties": {
          "detail": {
            "type": "string"
          },
          "code": {
            "type": "string"
          },
          "errors": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ValidationErrorItemOut"
            }
          },
          "hint": {
            "type": "string"
          },
          "docs_url": {
            "type": "string"
          },
          "retry_after": {
            "type": "integer"
          },
          "upgrade_url": {
            "type": "string"
          },
          "wall_id": {
            "type": "string"
          },
          "remaining": {
            "type": "integer"
          },
          "credits_remaining": {
            "type": "integer"
          },
          "cost": {
            "type": "integer"
          },
          "requested": {
            "type": "integer"
          },
          "resets_at": {
            "type": "string"
          },
          "limit": {
            "type": "integer"
          },
          "scope": {
            "type": "string"
          },
          "task_id": {
            "type": "string"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "doc_url": {
            "type": "string",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `docs_url`."
          },
          "reset_in_seconds": {
            "type": "integer",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `retry_after`."
          },
          "retry_after_seconds": {
            "type": "integer",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `retry_after`."
          },
          "error": {
            "type": "string",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `code`."
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "additionalProperties": true
      },
      "ValidationErrorOut": {
        "title": "ValidationErrorOut",
        "type": "object",
        "description": "A 422: `detail` names the first field to fix by its public name (`claims[2].text: ...`), `code` says what kind of problem it is (`validation_error`, `blank_input`, `unsupported_language`, `too_many_items`, ...), and `errors` lists every field. `unrecognized_fields` lists keys the endpoint does not take.",
        "properties": {
          "detail": {
            "type": "string"
          },
          "code": {
            "type": "string"
          },
          "errors": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ValidationErrorItemOut"
            }
          },
          "hint": {
            "type": "string"
          },
          "docs_url": {
            "type": "string"
          },
          "unrecognized_fields": {
            "type": "array",
            "items": {
              "type": "string"
            }
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "additionalProperties": true
      },
      "VerifyAcceptedOut": {
        "title": "VerifyAcceptedOut",
        "type": "object",
        "description": "The receipt of `POST /verify`: poll `GET /verify/status/{task_id}`, or wait for the webhook.",
        "properties": {
          "task_id": {
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "queued"
            ]
          },
          "chain_id": {
            "type": "string",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; an internal id; poll `task_id`."
          }
        },
        "required": [
          "task_id",
          "status"
        ]
      },
      "BatchAcceptedItemOut": {
        "title": "BatchAcceptedItemOut",
        "type": "object",
        "description": "One claim of a batch or a selection, and the task that checks it.",
        "properties": {
          "task_id": {
            "type": "string"
          },
          "claim": {
            "type": "string"
          },
          "claim_text": {
            "type": "string",
            "deprecated": true,
            "description": "Sent only to callers on `2026-05-13`; use `claim`."
          }
        },
        "required": [
          "task_id",
          "claim"
        ],
        "additionalProperties": true
      },
      "BatchAcceptedOut": {
        "title": "BatchAcceptedOut",
        "type": "object",
        "description": "The receipt of `POST /verify/batch` and `POST /verify/{task_id}/select`: one task per claim, in the order sent. Poll each `task_id`.",
        "properties": {
          "batch_id": {
            "type": "string"
          },
          "items": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/BatchAcceptedItemOut"
            }
          },
          "partial": {
            "type": "boolean",
            "description": "True when only some of the claims were accepted (the balance covered the first ones)."
          }
        },
        "required": [
          "batch_id",
          "items"
        ]
      },
      "OkOut": {
        "title": "OkOut",
        "type": "object",
        "description": "The deletion or reset was done.",
        "properties": {
          "ok": {
            "type": "boolean",
            "const": true
          }
        },
        "required": [
          "ok"
        ]
      },
      "AskMessageOut": {
        "title": "AskMessageOut",
        "type": "object",
        "description": "One message of a follow-up conversation; `POST /ask/{verification_id}` answers with the reply.",
        "properties": {
          "role": {
            "type": "string",
            "enum": [
              "user",
              "expert"
            ]
          },
          "content": {
            "type": "string",
            "description": "Markdown."
          },
          "created_at": {
            "type": "string"
          }
        },
        "required": [
          "role",
          "content",
          "created_at"
        ]
      },
      "AskHistoryOut": {
        "title": "AskHistoryOut",
        "type": "object",
        "description": "The follow-up conversation on a verification, oldest message first.",
        "properties": {
          "messages": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/AskMessageOut"
            }
          },
          "exchanges_used": {
            "type": "integer"
          },
          "exchange_limit": {
            "type": "integer"
          },
          "can_send": {
            "type": "boolean"
          }
        },
        "required": [
          "messages",
          "exchanges_used",
          "exchange_limit",
          "can_send"
        ]
      },
      "ApiRootOut": {
        "title": "ApiRootOut",
        "type": "object",
        "description": "The machine-readable index of the API: where the docs, the endpoints, the SDKs and the MCP server are.",
        "properties": {
          "name": {
            "type": "string"
          },
          "version": {
            "type": "string"
          },
          "docs_url": {
            "type": "string"
          },
          "openapi_url": {
            "type": "string"
          },
          "quickstart_url": {
            "type": "string"
          },
          "developer_portal_url": {
            "type": "string"
          },
          "endpoints": {
            "type": "object",
            "additionalProperties": {
              "type": "string"
            }
          },
          "sdks": {
            "type": "object",
            "additionalProperties": {
              "type": "object",
              "additionalProperties": {
                "type": "string"
              }
            }
          },
          "mcp": {
            "type": "object",
            "additionalProperties": {
              "type": "string"
            }
          }
        }
      },
      "CertificateOut": {
        "title": "CertificateOut",
        "type": "object",
        "description": "The signed warranty certificate of a covered verification, as issued. Its format and the offline check are at https://lenz.io/docs/coverage."
      },
      "VerificationListItemOutLegacy": {
        "description": "The ``2026-05-13`` list item: ``modified_at`` (set only when completed\non a later UTC day) where ``VerificationListItemOut`` has\n``completed_at``. It is the shape a caller on that version receives.",
        "properties": {
          "verification_id": {
            "title": "Verification Id",
            "type": "string"
          },
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "domain": {
            "title": "Domain",
            "type": "string"
          },
          "entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/EntityRef"
            },
            "title": "Entities",
            "type": "array"
          },
          "verdict": {
            "default": "",
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "default": "low",
            "title": "Confidence",
            "type": "string"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Lenz Score"
          },
          "key_finding": {
            "default": "",
            "title": "Key Finding",
            "type": "string"
          },
          "executive_summary": {
            "default": "",
            "title": "Executive Summary",
            "type": "string"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "A suggested rewrite of `claim` that this verification's findings support, to use in place of the original sentence. It has not been verified itself: before using it, review it or run it through `/verify`. `null` for a true claim, when no correction is established, and on verifications that predate the field. On every verification, single or listed; not on `/assess` rows.",
            "title": "Suggested Rewrite"
          },
          "created_at": {
            "default": "",
            "title": "Created At",
            "type": "string"
          },
          "modified_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Modified At"
          },
          "language": {
            "title": "Language",
            "type": "string"
          }
        },
        "required": [
          "verification_id",
          "claim",
          "domain",
          "language"
        ],
        "title": "VerificationListItemOutLegacy",
        "type": "object"
      },
      "VerificationListOutLegacy": {
        "description": "The ``2026-05-13`` paginated list (see ``VerificationListItemOutLegacy``).",
        "properties": {
          "items": {
            "items": {
              "$ref": "#/components/schemas/VerificationListItemOutLegacy"
            },
            "title": "Items",
            "type": "array"
          },
          "total": {
            "title": "Total",
            "type": "integer"
          },
          "page": {
            "title": "Page",
            "type": "integer"
          },
          "page_size": {
            "title": "Page Size",
            "type": "integer"
          }
        },
        "required": [
          "items",
          "total",
          "page",
          "page_size"
        ],
        "title": "VerificationListOutLegacy",
        "type": "object"
      },
      "CandidateClaimOut": {
        "description": "A single candidate claim surfaced when the framing detects multiple\ndistinct claims in the submitted text. The caller picks one via\n``POST /verify/{task_id}/select``.",
        "properties": {
          "text": {
            "title": "Text",
            "type": "string"
          },
          "domain": {
            "default": "",
            "title": "Domain",
            "type": "string"
          }
        },
        "required": [
          "text"
        ],
        "title": "CandidateClaimOut",
        "type": "object"
      },
      "ClaimDetailOutLegacy": {
        "description": "The ``2026-05-13`` verification report, as webhooks still carry it:\n``modified_at`` (set only when completed on a later UTC day) where\n``ClaimDetailOut`` has ``completed_at``.",
        "properties": {
          "verification_id": {
            "title": "Verification Id",
            "type": "string"
          },
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "visibility": {
            "default": "private",
            "title": "Visibility",
            "type": "string"
          },
          "depth": {
            "default": "standard",
            "title": "Depth",
            "type": "string"
          },
          "domain": {
            "default": "",
            "title": "Domain",
            "type": "string"
          },
          "entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/EntityRef"
            },
            "title": "Entities",
            "type": "array"
          },
          "presumed_intent": {
            "default": "",
            "title": "Presumed Intent",
            "type": "string"
          },
          "verdict": {
            "default": "",
            "description": "`True`, `Mostly True`, `Mixed`, `Mostly False` or `False`, or `No Public Record`: Lenz found no public record that settles the claim, which does not make it false. It has no `lenz_score` (null), a `confidence`, and is never warranted. Version `2026-05-13` never receives it: it reads such a run as a failure (`research_empty` when no source was found, else `research_insufficient`).",
            "title": "Verdict",
            "type": "string"
          },
          "confidence": {
            "default": "low",
            "title": "Confidence",
            "type": "string"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "1-10; null for `No Public Record`.",
            "title": "Lenz Score"
          },
          "key_finding": {
            "default": "",
            "title": "Key Finding",
            "type": "string"
          },
          "executive_summary": {
            "default": "",
            "title": "Executive Summary",
            "type": "string"
          },
          "warnings": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Warnings",
            "type": "array"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "description": "A suggested rewrite of `claim` that this verification's findings support, to use in place of the original sentence. It has not been verified itself: before using it, review it or run it through `/verify`. `null` for a true claim, when no correction is established, and on verifications that predate the field. On every verification, single or listed; not on `/assess` rows.",
            "title": "Suggested Rewrite"
          },
          "created_at": {
            "default": "",
            "title": "Created At",
            "type": "string"
          },
          "modified_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Modified At"
          },
          "sources": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/SourceOut"
            },
            "title": "Sources",
            "type": "array"
          },
          "audit": {
            "$ref": "#/components/schemas/AuditOut",
            "default": {
              "adjudication_summary": "",
              "assessments": [],
              "debate_pro": {
                "argument": "",
                "rebuttal": "",
                "role": ""
              },
              "debate_con": {
                "argument": "",
                "rebuttal": "",
                "role": ""
              },
              "panel_agreement": ""
            }
          },
          "language": {
            "title": "Language",
            "type": "string"
          },
          "coverage": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/CoverageOut"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          }
        },
        "required": [
          "verification_id",
          "claim",
          "language"
        ],
        "title": "ClaimDetailOutLegacy",
        "type": "object"
      },
      "NeedsInputOut": {
        "description": "Inline body for webhook ``event=verification.needs_input``.\n\nThe pipeline pauses for caller input when framing splits the text into\nmultiple distinct claims (``multi_claim``). A vague input does not pause:\nit is checked on its most likely reading, or fails as ``not_a_claim``\nwhen there is none.\n\n``multi_claim`` is resolved by calling ``POST /verify/{task_id}/select``\nwith one of the offered claim texts.",
        "properties": {
          "reason": {
            "title": "Reason",
            "type": "string"
          },
          "claims": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/CandidateClaimOut"
            },
            "title": "Claims",
            "type": "array"
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": "",
            "title": "Hint"
          }
        },
        "required": [
          "reason"
        ],
        "title": "NeedsInputOut",
        "type": "object"
      },
      "WebhookPayloadLegacy": {
        "description": "The ``2026-05-13`` body of a verification event, sent for a submission\nmade in that version: flat, no ``event_id``, the failure code in\n``error``. The canonical ``WebhookPayload`` carries the same facts in\nits own shape.",
        "properties": {
          "event": {
            "title": "Event",
            "type": "string"
          },
          "verification_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Verification Id"
          },
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "batch_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Batch Id"
          },
          "status": {
            "title": "Status",
            "type": "string"
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ClaimDetailOutLegacy"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "needs_input": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/NeedsInputOut"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "coverage": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/CoverageOut"
              },
              {
                "type": "null"
              }
            ],
            "default": null
          },
          "error": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Error"
          },
          "failure_class": {
            "anyOf": [
              {
                "enum": [
                  "upstream_unavailable",
                  "insufficient_evidence",
                  "invalid_input",
                  "cancelled",
                  "internal"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Failure Class"
          },
          "retryable": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Retryable"
          },
          "review_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "default": null,
            "title": "Review Id"
          },
          "attempt": {
            "title": "Attempt",
            "type": "integer"
          },
          "delivered_at": {
            "title": "Delivered At",
            "type": "string"
          }
        },
        "required": [
          "event",
          "task_id",
          "status",
          "attempt",
          "delivered_at"
        ],
        "title": "WebhookPayloadLegacy",
        "type": "object"
      },
      "ValidationErrorOutLegacy": {
        "title": "ValidationErrorOutLegacy",
        "type": "object",
        "properties": {
          "detail": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "object",
                  "additionalProperties": true
                }
              }
            ]
          },
          "code": {
            "type": "string"
          },
          "errors": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "loc": {
                  "type": "array",
                  "items": {
                    "anyOf": [
                      {
                        "type": "string"
                      },
                      {
                        "type": "integer"
                      }
                    ]
                  }
                },
                "msg": {
                  "type": "string"
                }
              }
            }
          },
          "hint": {
            "type": "string"
          },
          "doc_url": {
            "type": "string"
          },
          "unrecognized_fields": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "error": {
            "type": "string"
          }
        },
        "required": [
          "detail"
        ],
        "description": "A 422 as `2026-05-13` sends it. `detail` is a sentence, or (for a field of the wrong type or a missing one) the list of validation errors, each `{type, loc, msg}`, with `hint`, `doc_url` and `unrecognized_fields` beside it. `code` is on some (an /assess `claims` list, /review, /citecheck); `errors`, each `{loc, msg}`, only on /review and /citecheck."
      },
      "ErrorOutLegacy": {
        "title": "ErrorOutLegacy",
        "type": "object",
        "description": "An error as `2026-05-13` sends it: `detail`, and `code` on most (not on a 401, a 404 or 405 outside /review and /citecheck, a malformed body, or an idempotency conflict); `doc_url`, `reset_in_seconds` (the /extract daily cap), `retry_after_seconds` (a review or citation check already running) and `error` (a repeat of some codes) where the current version has other names.",
        "properties": {
          "detail": {
            "type": "string"
          },
          "code": {
            "type": "string"
          },
          "errors": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/ValidationErrorItemOut"
            }
          },
          "hint": {
            "type": "string"
          },
          "docs_url": {
            "type": "string"
          },
          "retry_after": {
            "type": "integer"
          },
          "upgrade_url": {
            "type": "string"
          },
          "wall_id": {
            "type": "string"
          },
          "remaining": {
            "type": "integer"
          },
          "credits_remaining": {
            "type": "integer"
          },
          "cost": {
            "type": "integer"
          },
          "requested": {
            "type": "integer"
          },
          "resets_at": {
            "type": "string"
          },
          "limit": {
            "type": "integer"
          },
          "scope": {
            "type": "string"
          },
          "task_id": {
            "type": "string"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "doc_url": {
            "type": "string"
          },
          "reset_in_seconds": {
            "type": "integer"
          },
          "retry_after_seconds": {
            "type": "integer"
          },
          "error": {
            "type": "string"
          }
        },
        "required": [
          "detail"
        ],
        "additionalProperties": true
      },
      "ReviewErrorOutLegacy": {
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "title": "Code",
            "type": "string"
          },
          "upgrade_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Upgrade Url"
          },
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Limit"
          },
          "scope": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Scope"
          },
          "wall_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Wall Id"
          },
          "remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Remaining"
          },
          "credits_remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Credits Remaining"
          },
          "cost": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cost"
          },
          "resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Resets At"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Docs Url"
          },
          "review_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Review Id"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Purged At"
          },
          "retry_after": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Seconds to wait before sending again; the same value as the `Retry-After` header.",
            "title": "Retry After"
          },
          "doc_url": {
            "type": "string"
          },
          "retry_after_seconds": {
            "type": "integer"
          },
          "reset_in_seconds": {
            "type": "integer"
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "title": "ReviewErrorOutLegacy",
        "type": "object",
        "description": "A /review error as `2026-05-13` sends it: `doc_url` for `docs_url`, `retry_after_seconds` on `review_in_flight`."
      },
      "CitecheckErrorOutLegacy": {
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "title": "Code",
            "type": "string"
          },
          "citecheck_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With idempotency_conflict: the check this key is creating, once it exists.",
            "title": "Citecheck Id"
          },
          "purged_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Purged At"
          },
          "remaining": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `no_credits`: citation checks the balance still covers.",
            "title": "Remaining"
          },
          "upgrade_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Upgrade Url"
          },
          "limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Limit"
          },
          "scope": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Scope"
          },
          "wall_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Wall Id"
          },
          "cost": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cost"
          },
          "resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Resets At"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Docs Url"
          },
          "retry_after": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Seconds to wait before sending again; the same value as the `Retry-After` header.",
            "title": "Retry After"
          },
          "doc_url": {
            "type": "string"
          },
          "retry_after_seconds": {
            "type": "integer"
          },
          "credits_remaining": {
            "type": "integer"
          }
        },
        "required": [
          "detail",
          "code"
        ],
        "title": "CitecheckErrorOutLegacy",
        "type": "object",
        "description": "A /citecheck error as `2026-05-13` sends it: `doc_url` for `docs_url`, `retry_after_seconds` on `citecheck_in_flight`, and `credits_remaining` beside `remaining` on a 402."
      },
      "VerifyAcceptedOutLegacy": {
        "title": "VerifyAcceptedOutLegacy",
        "type": "object",
        "description": "The /verify receipt as `2026-05-13` sends it: `chain_id` too (not on a repeat answered from the first submission, which is a 200).",
        "properties": {
          "task_id": {
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "queued"
            ]
          },
          "chain_id": {
            "type": "string"
          }
        },
        "required": [
          "task_id",
          "status"
        ]
      },
      "BatchAcceptedItemOutLegacy": {
        "title": "BatchAcceptedItemOutLegacy",
        "type": "object",
        "description": "One receipt item as `2026-05-13` sends it: `claim_text` for `claim`.",
        "properties": {
          "task_id": {
            "type": "string"
          },
          "claim_text": {
            "type": "string"
          }
        },
        "required": [
          "task_id",
          "claim_text"
        ],
        "additionalProperties": true
      },
      "FailureOutLegacy": {
        "title": "FailureOutLegacy",
        "type": "object",
        "properties": {
          "failure_reason": {
            "type": "string",
            "description": "Where it stopped. `not_a_claim` where the current version says `no_checkable_claim`."
          },
          "failure_class": {
            "type": "string",
            "enum": [
              "upstream_unavailable",
              "insufficient_evidence",
              "invalid_input",
              "cancelled",
              "internal"
            ]
          },
          "retryable": {
            "type": "boolean"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "failure_reason",
          "failure_class",
          "retryable",
          "docs_url"
        ],
        "description": "A failure block as `2026-05-13` sends it inside a review, a citation check and a child verification: `failure_reason` where the current version has `code`, and no `detail`. `no_claim` (`not_a_claim` on a child verification) where the current version says `no_checkable_claim`."
      },
      "AssessClaimOutLegacy": {
        "description": "An /assess row as `2026-05-13` sends it: no `status` or `failure`; a row with no verdict has `verdict: \"Error\"`, `confidence: \"low\"` and says why in `error_code` (`no_claim` where the current version says `no_checkable_claim`) and `hint`.",
        "properties": {
          "claim": {
            "title": "Claim",
            "type": "string"
          },
          "language": {
            "title": "Language",
            "type": "string"
          },
          "verdict": {
            "type": "string",
            "enum": [
              "True",
              "Mostly True",
              "Mixed",
              "Mostly False",
              "False",
              "Error"
            ],
            "description": "`Error` when the row carries no verdict (`error_code` says why)."
          },
          "confidence": {
            "type": "string",
            "enum": [
              "low",
              "medium",
              "high"
            ]
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Rationale"
          },
          "dissent": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Deprecated: always null.",
            "title": "Dissent"
          },
          "searched_pages": {
            "default": [],
            "description": "Pages looked at while assessing this claim, as title and link.",
            "items": {
              "$ref": "#/components/schemas/SearchedPageOut"
            },
            "title": "Searched Pages",
            "type": "array"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Suggested Rewrite"
          },
          "identified_claims": {
            "default": [],
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "error_code": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "candidate_claims": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "maxItems": 0,
            "description": "Always `[]`."
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "claim",
          "language",
          "verdict",
          "confidence"
        ],
        "title": "AssessClaimOutLegacy",
        "type": "object"
      },
      "AssessOutLegacy": {
        "description": "The /assess body as `2026-05-13` sends it: `status` says `not_a_claim` for an input with nothing checkable; no `failure`; `error` is null, or a sentence when the single text held no claim, beside `error_code: no_claim` and `candidate_claims: []`.",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "ok",
              "not_a_claim",
              "error"
            ]
          },
          "claims": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/AssessClaimOutLegacy"
            },
            "title": "Claims",
            "type": "array"
          },
          "more_claims": {
            "description": "Claims found in a single `text` past the ones checked: one call checks at most 20, ranked most check-worthy first. Not checked and not charged; send them as `claims` (up to 20 a call) to check them. Always `[]` for the `claims` list form.",
            "items": {
              "type": "string"
            },
            "title": "More Claims",
            "type": "array"
          },
          "error": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "error_code": {
            "type": "string"
          },
          "candidate_claims": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "maxItems": 0,
            "description": "Always `[]`."
          }
        },
        "required": [
          "claims"
        ],
        "title": "AssessOutLegacy",
        "type": "object"
      },
      "ExtractOutLegacy": {
        "description": "The /extract body as `2026-05-13` sends it: the top claim in `claim`, the whole list in `identified_claims` (`[]` for one claim), `locations` with `locate: true`, and `not_a_claim` where the current version says `no_checkable_claim`.",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "ready",
              "not_a_claim",
              "no_match"
            ]
          },
          "domain": {
            "default": "",
            "title": "Domain",
            "type": "string"
          },
          "key_entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ExtractedEntityOut"
            },
            "title": "Key Entities",
            "type": "array"
          },
          "presumed_intent": {
            "default": "",
            "title": "Presumed Intent",
            "type": "string"
          },
          "original_input": {
            "default": "",
            "title": "Original Input",
            "type": "string"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The language the claims are written in, as an ISO 639-1 code: the one you sent, `en` when you sent none, or the detected one when you asked for detection. Pass it on to `/assess` or `/verify` to keep a chain in one language. Absent on a replay of a response stored before this field existed.",
            "title": "Language"
          },
          "claim": {
            "type": "string"
          },
          "identified_claims": {
            "type": "array",
            "items": {
              "type": "string"
            }
          },
          "candidate_claims": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "maxItems": 0,
            "description": "Always `[]`."
          },
          "locations": {
            "anyOf": [
              {
                "type": "array",
                "items": {
                  "$ref": "#/components/schemas/ClaimLocationOut"
                }
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "title": "ExtractOutLegacy",
        "type": "object"
      },
      "StatusOutLegacy": {
        "description": "The poll as `2026-05-13` sends it: a failed run carries `error`, `failure_reason` (`not_a_claim` where the current version says `no_checkable_claim`), `failure_class`, `retryable`, `docs_url` and `hint` at the top level instead of `failure`; `needs_input` options carry `text`; a result carries `modified_at`; a cancelled run is `failed` with `failure_class: \"cancelled\"`.",
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "processing",
              "needs_input",
              "completed",
              "failed"
            ]
          },
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "progress": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ProgressOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "reason": {
            "anyOf": [
              {
                "const": "multi_claim",
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reason"
          },
          "claims": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/CandidateClaimOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claims"
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ClaimDetailOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Hint"
          },
          "error": {
            "type": "string"
          },
          "failure_reason": {
            "type": "string",
            "description": "Where it stopped. `not_a_claim` where the current version says `no_checkable_claim`."
          },
          "failure_class": {
            "type": "string",
            "enum": [
              "upstream_unavailable",
              "insufficient_evidence",
              "invalid_input",
              "cancelled",
              "internal"
            ]
          },
          "retryable": {
            "type": "boolean"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "status",
          "task_id"
        ],
        "title": "StatusOutLegacy",
        "type": "object"
      },
      "CancelOutLegacy": {
        "description": "The cancel response as `2026-05-13` sends it: a cancelled run is `status: \"failed\"` (with `cancelled: true`), the word its poll says.",
        "properties": {
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "cancelled": {
            "title": "Cancelled",
            "type": "boolean"
          },
          "status": {
            "type": "string",
            "enum": [
              "processing",
              "needs_input",
              "completed",
              "failed"
            ]
          }
        },
        "required": [
          "task_id",
          "cancelled",
          "status"
        ],
        "title": "CancelOutLegacy",
        "type": "object"
      },
      "VerificationNotReadyOutLegacy": {
        "description": "The 409 as `2026-05-13` sends it: `failure_reason`, `failure_class`, `retryable` and `docs_url` at the top level instead of `failure`.",
        "properties": {
          "detail": {
            "title": "Detail",
            "type": "string"
          },
          "code": {
            "enum": [
              "verification_not_ready",
              "verification_failed"
            ],
            "title": "Code",
            "type": "string"
          },
          "status": {
            "enum": [
              "processing",
              "needs_input",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "task_id": {
            "title": "Task Id",
            "type": "string"
          },
          "hint": {
            "title": "Hint",
            "type": "string"
          },
          "failure_reason": {
            "type": "string",
            "description": "Where it stopped. `not_a_claim` where the current version says `no_checkable_claim`."
          },
          "failure_class": {
            "type": "string",
            "enum": [
              "upstream_unavailable",
              "insufficient_evidence",
              "invalid_input",
              "cancelled",
              "internal"
            ]
          },
          "retryable": {
            "type": "boolean"
          },
          "docs_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "detail",
          "code",
          "status",
          "task_id",
          "hint"
        ],
        "title": "VerificationNotReadyOutLegacy",
        "type": "object"
      },
      "ReviewAssessmentOutLegacy": {
        "properties": {
          "status": {
            "enum": [
              "pending",
              "running",
              "completed",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "verdict": {
            "anyOf": [
              {
                "enum": [
                  "True",
                  "Mostly True",
                  "Mixed",
                  "Mostly False",
                  "False",
                  "No Public Record"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verdict"
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Rationale"
          },
          "dissent": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "deprecated": true,
            "description": "Deprecated: always null.",
            "title": "Dissent"
          },
          "searched_pages": {
            "default": [],
            "description": "Pages looked at while assessing this claim, as title and link.",
            "items": {
              "$ref": "#/components/schemas/SearchedPageOut"
            },
            "title": "Searched Pages",
            "type": "array"
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "With `escalate.suggest_edits`: the claim with its wrong part corrected, from the quick check's reasoning, when it found the claim False or Mostly False with high confidence. Not itself verified. `null` otherwise.",
            "title": "Suggested Rewrite"
          },
          "identified_claims": {
            "default": [],
            "description": "Further claims found inside this one, not checked.",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set when status is failed."
          },
          "error_code": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "status"
        ],
        "title": "ReviewAssessmentOutLegacy",
        "type": "object",
        "description": "A review claim row's quick check as `2026-05-13` sends it: `identified_claims`, `error_code` and `hint` beside a `failure` in the older block."
      },
      "ReviewSummaryOutLegacy": {
        "properties": {
          "claims_selected": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims this review works on; null until the draft is read.",
            "title": "Claims Selected"
          },
          "claim_limit": {
            "description": "The resolved max_assessments.",
            "title": "Claim Limit",
            "type": "integer"
          },
          "claim_limit_reached": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "True when claims_found is more than claim_limit: the rest are in more_claims, found and not checked. False when every claim found was selected. Null until the draft is read."
          },
          "input_truncated": {
            "title": "Input Truncated",
            "type": "boolean"
          },
          "assessments": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewAssessmentCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "verifications": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewVerificationCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "issues": {
            "title": "Issues",
            "type": "integer"
          },
          "citations_found": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations with a URL or DOI in the text the review read (after the 50,000 character cut); null until the draft is read, or when the check was not asked.",
            "title": "Citations Found"
          },
          "citations_selected": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "The ones this review works on: the first in the draft's order.",
            "title": "Citations Selected"
          },
          "citation_limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "The resolved cap.",
            "title": "Citation Limit"
          },
          "citation_limit_reached": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "True when citations_found is more than citation_limit: the rest are in more_citations, found and not checked. False when every citation found was selected, exactly citation_limit included. Null until the text is read."
          },
          "citation_checks": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewCitationCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "citation_issues": {
            "default": 0,
            "description": "Rows in citation_issues[]; 0 when the check was not asked.",
            "title": "Citation Issues",
            "type": "integer"
          },
          "citations_skipped": {
            "anyOf": [
              {
                "enum": [
                  "url_input",
                  "switched_off",
                  "insufficient_credits"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Why the check was asked for and did not run.",
            "title": "Citations Skipped"
          }
        },
        "required": [
          "claims_selected",
          "claim_limit",
          "claim_limit_reached",
          "input_truncated",
          "assessments",
          "verifications",
          "issues"
        ],
        "title": "ReviewSummaryOutLegacy",
        "type": "object",
        "description": "A review summary as `2026-05-13` sends it: no `claims_found`; `claim_limit_reached` (true when the claims found were at least the limit) and `citation_limit_reached`."
      },
      "CitecheckSummaryOutLegacy": {
        "properties": {
          "citations_found": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations with a URL or DOI in the text, or the pairs sent; null until read.",
            "title": "Citations Found"
          },
          "citations_selected": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Citations Selected"
          },
          "citation_limit": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Citation Limit"
          },
          "citation_limit_reached": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "description": "True when citations_found is more than citation_limit: the rest are in more_citations, found and not checked. False when every citation found was selected, exactly citation_limit included. Null until the text is read."
          },
          "citation_checks": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewCitationCountsOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "citation_issues": {
            "default": 0,
            "title": "Citation Issues",
            "type": "integer"
          }
        },
        "title": "CitecheckSummaryOutLegacy",
        "type": "object",
        "description": "A citation check summary as `2026-05-13` sends it: `citation_limit_reached`."
      },
      "ReviewVerificationOutLegacy": {
        "properties": {
          "status": {
            "type": "string",
            "enum": [
              "processing",
              "completed",
              "failed"
            ]
          },
          "content_status": {
            "enum": [
              "available",
              "purged"
            ],
            "title": "Content Status",
            "type": "string"
          },
          "verification_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Id"
          },
          "task_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Task Id"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Language"
          },
          "visibility": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "EFFECTIVE: a same-account cache hit keeps its own.",
            "title": "Visibility"
          },
          "depth": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "EFFECTIVE: a cache hit may serve standard for a low request.",
            "title": "Depth"
          },
          "domain": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Domain"
          },
          "entities": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewEntityOut"
            },
            "title": "Entities",
            "type": "array"
          },
          "verdict": {
            "anyOf": [
              {
                "type": "string",
                "enum": [
                  "True",
                  "Mostly True",
                  "Mixed",
                  "Mostly False",
                  "False"
                ]
              },
              {
                "type": "null"
              }
            ]
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "lenz_score": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Lenz Score"
          },
          "key_finding": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Key Finding"
          },
          "executive_summary": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Executive Summary"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Suggested Rewrite"
          },
          "warnings": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Warnings",
            "type": "array"
          },
          "created_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Created At"
          },
          "modified_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ]
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Url"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "status",
          "content_status"
        ],
        "title": "ReviewVerificationOutLegacy",
        "type": "object",
        "description": "A review's deep check as `2026-05-13` sends it: `modified_at` (the completion time, set only when it falls on a later UTC day than `created_at`) instead of `completed_at`; a cancelled one is `failed`; a \"No Public Record\" one is `failed` on research (`research_empty` / `research_insufficient`)."
      },
      "ReviewResultOutLegacy": {
        "properties": {
          "verdict": {
            "type": "string",
            "enum": [
              "True",
              "Mostly True",
              "Mixed",
              "Mostly False",
              "False"
            ]
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "source": {
            "enum": [
              "assessment",
              "verification"
            ],
            "title": "Source",
            "type": "string"
          },
          "is_issue": {
            "title": "Is Issue",
            "type": "boolean"
          }
        },
        "required": [
          "verdict",
          "confidence",
          "source",
          "is_issue"
        ],
        "title": "ReviewResultOutLegacy",
        "type": "object",
        "description": "A claim row's result as `2026-05-13` sends it: never \"No Public Record\" (that deep check reads failed, so the result is the quick check's)."
      },
      "ReviewIssueOutLegacy": {
        "properties": {
          "claim_index": {
            "title": "Claim Index",
            "type": "integer"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "verified_claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verified Claim"
          },
          "verdict": {
            "type": "string",
            "enum": [
              "True",
              "Mostly True",
              "Mixed",
              "Mostly False",
              "False"
            ]
          },
          "confidence": {
            "anyOf": [
              {
                "enum": [
                  "low",
                  "medium",
                  "high"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Confidence"
          },
          "source": {
            "enum": [
              "assessment",
              "verification"
            ],
            "title": "Source",
            "type": "string"
          },
          "verification_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Id"
          },
          "verification_status": {
            "anyOf": [
              {
                "type": "string",
                "enum": [
                  "processing",
                  "completed",
                  "failed"
                ]
              },
              {
                "type": "null"
              }
            ]
          },
          "verification_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Verification Url"
          },
          "url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Url"
          },
          "escalation": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewEscalationOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "key_finding": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Key Finding"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Rationale"
          },
          "suggested_rewrite": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The rewrite the row's edits come from: its completed deep check's, else (with `escalate.suggest_edits`) its quick check's; `source` says which. A suggestion, not itself verified.",
            "title": "Suggested Rewrite"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          },
          "suggested_edits": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewSuggestedEditsOut"
              },
              {
                "type": "null"
              }
            ],
            "description": "A copy of its claim row's `suggested_edits`. Asked with `escalate.suggest_edits`. They follow the row's suggested rewrite: its completed deep check's, else its quick check's (see the issue's `source`). `null` when not asked, when the claim has no suggested rewrite, when the draft's passage is not in a supported language or could not be placed, or once a zero-retention draft is gone. Guide: https://lenz.io/docs/citations#suggested-edits"
          }
        },
        "required": [
          "claim_index",
          "claim",
          "verified_claim",
          "verdict",
          "confidence",
          "source",
          "verification_id",
          "verification_status",
          "verification_url",
          "url",
          "escalation",
          "key_finding",
          "rationale",
          "suggested_rewrite",
          "failure"
        ],
        "title": "ReviewIssueOutLegacy",
        "type": "object",
        "description": "An issue as `2026-05-13` sends it: a cancelled deep check reads `failed`; never \"No Public Record\" (that deep check reads failed, so the issue, if any, is the quick check's)."
      },
      "ReviewFullOutLegacy": {
        "properties": {
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "queued",
              "assessing",
              "verifying",
              "completed",
              "failed"
            ]
          },
          "outcome": {
            "anyOf": [
              {
                "enum": [
                  "clean",
                  "issues_found",
                  "incomplete",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Null until terminal. clean covers the selected claims at the policy's chosen depth. issues_found with an empty issues[] means the rows are in citation_issues[]. A deep check that reads \"No Public Record\" is an issue (not on the public record).",
            "title": "Outcome"
          },
          "created_at": {
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Completed At"
          },
          "language": {
            "description": "The language the review is written in, as an ISO 639-1 code. `auto` only while a review sent with `language: \"auto\"` on a draft that is one URL has not read its page yet; then the detected code, or `en` when the page could not be read.",
            "title": "Language",
            "type": "string"
          },
          "policy": {
            "$ref": "#/components/schemas/ReviewPolicyOut"
          },
          "summary": {
            "$ref": "#/components/schemas/ReviewSummaryOutLegacy"
          },
          "credits": {
            "$ref": "#/components/schemas/ReviewCreditsOut"
          },
          "poll_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Poll After Seconds"
          },
          "issues": {
            "items": {
              "$ref": "#/components/schemas/ReviewIssueOutLegacy"
            },
            "title": "Issues",
            "type": "array"
          },
          "failures": {
            "items": {
              "$ref": "#/components/schemas/ReviewFailedRowOutLegacy"
            },
            "title": "Failures",
            "type": "array"
          },
          "citation_issues": {
            "default": [],
            "description": "Citations whose source does not say what the draft says, the most serious first; partly_supported rows are not issues and are only in citations[]. [] when the check was not asked.",
            "items": {
              "$ref": "#/components/schemas/ReviewCitationIssueOutLegacy"
            },
            "title": "Citation Issues",
            "type": "array"
          },
          "citation_failures": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationFailedRowOutLegacy"
            },
            "title": "Citation Failures",
            "type": "array"
          },
          "more_claims": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims found past max_assessments, in the draft's order: found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Claims"
          },
          "more_claim_locations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ClaimLocationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the draft makes each of `more_claims`, in the same order: `{claim, positions}`, the shape `/extract` returns with `locate: true` (see a claim row's `positions`). Null until the draft is read.",
            "title": "More Claim Locations"
          },
          "more_citations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ReviewMoreCitationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations found past the ones selected (up to 100): found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Citations"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          },
          "view": {
            "const": "full",
            "title": "View",
            "type": "string"
          },
          "claims": {
            "items": {
              "$ref": "#/components/schemas/ReviewClaimOutLegacy"
            },
            "title": "Claims",
            "type": "array"
          },
          "citations": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationOutLegacy"
            },
            "title": "Citations",
            "type": "array"
          }
        },
        "required": [
          "review_id",
          "status",
          "outcome",
          "created_at",
          "completed_at",
          "language",
          "policy",
          "summary",
          "credits",
          "poll_after_seconds",
          "issues",
          "failures",
          "failure",
          "view",
          "claims"
        ],
        "title": "ReviewFullOutLegacy",
        "type": "object",
        "description": "A review as `2026-05-13` sends it: a cancelled review is `failed` with a `cancelled` failure."
      },
      "ReviewIssuesOutLegacy": {
        "properties": {
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "queued",
              "assessing",
              "verifying",
              "completed",
              "failed"
            ]
          },
          "outcome": {
            "anyOf": [
              {
                "enum": [
                  "clean",
                  "issues_found",
                  "incomplete",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Null until terminal. clean covers the selected claims at the policy's chosen depth. issues_found with an empty issues[] means the rows are in citation_issues[]. A deep check that reads \"No Public Record\" is an issue (not on the public record).",
            "title": "Outcome"
          },
          "created_at": {
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Completed At"
          },
          "language": {
            "description": "The language the review is written in, as an ISO 639-1 code. `auto` only while a review sent with `language: \"auto\"` on a draft that is one URL has not read its page yet; then the detected code, or `en` when the page could not be read.",
            "title": "Language",
            "type": "string"
          },
          "policy": {
            "$ref": "#/components/schemas/ReviewPolicyOut"
          },
          "summary": {
            "$ref": "#/components/schemas/ReviewSummaryOutLegacy"
          },
          "credits": {
            "$ref": "#/components/schemas/ReviewCreditsOut"
          },
          "poll_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Poll After Seconds"
          },
          "issues": {
            "items": {
              "$ref": "#/components/schemas/ReviewIssueOutLegacy"
            },
            "title": "Issues",
            "type": "array"
          },
          "failures": {
            "items": {
              "$ref": "#/components/schemas/ReviewFailedRowOutLegacy"
            },
            "title": "Failures",
            "type": "array"
          },
          "citation_issues": {
            "default": [],
            "description": "Citations whose source does not say what the draft says, the most serious first; partly_supported rows are not issues and are only in citations[]. [] when the check was not asked.",
            "items": {
              "$ref": "#/components/schemas/ReviewCitationIssueOutLegacy"
            },
            "title": "Citation Issues",
            "type": "array"
          },
          "citation_failures": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationFailedRowOutLegacy"
            },
            "title": "Citation Failures",
            "type": "array"
          },
          "more_claims": {
            "anyOf": [
              {
                "items": {
                  "type": "string"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Claims found past max_assessments, in the draft's order: found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Claims"
          },
          "more_claim_locations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ClaimLocationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the draft makes each of `more_claims`, in the same order: `{claim, positions}`, the shape `/extract` returns with `locate: true` (see a claim row's `positions`). Null until the draft is read.",
            "title": "More Claim Locations"
          },
          "more_citations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ReviewMoreCitationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations found past the ones selected (up to 100): found but not checked; send them in a later request to check them. Null until the draft is read.",
            "title": "More Citations"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          },
          "view": {
            "const": "issues",
            "title": "View",
            "type": "string"
          }
        },
        "required": [
          "review_id",
          "status",
          "outcome",
          "created_at",
          "completed_at",
          "language",
          "policy",
          "summary",
          "credits",
          "poll_after_seconds",
          "issues",
          "failures",
          "failure",
          "view"
        ],
        "title": "ReviewIssuesOutLegacy",
        "type": "object",
        "description": "A review as `2026-05-13` sends it: a cancelled review is `failed` with a `cancelled` failure."
      },
      "CitecheckOutLegacy": {
        "properties": {
          "citecheck_id": {
            "title": "Citecheck Id",
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "queued",
              "checking",
              "completed",
              "failed"
            ]
          },
          "outcome": {
            "anyOf": [
              {
                "enum": [
                  "clean",
                  "issues_found",
                  "incomplete",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Null until terminal. incomplete: a citation could not be checked for a reason of ours.",
            "title": "Outcome"
          },
          "created_at": {
            "title": "Created At",
            "type": "string"
          },
          "completed_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Completed At"
          },
          "language": {
            "description": "The language the reasoning is written in, as the review envelope echoes it.",
            "title": "Language",
            "type": "string"
          },
          "poll_after_seconds": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Poll After Seconds"
          },
          "policy": {
            "$ref": "#/components/schemas/CitecheckPolicyOut"
          },
          "summary": {
            "$ref": "#/components/schemas/CitecheckSummaryOutLegacy"
          },
          "credits": {
            "$ref": "#/components/schemas/ReviewCreditsOut"
          },
          "citations": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationOutLegacy"
            },
            "title": "Citations",
            "type": "array"
          },
          "citation_issues": {
            "default": [],
            "description": "Citations whose source does not say what the draft says, the most serious first; partly_supported rows are not issues and are only in citations[].",
            "items": {
              "$ref": "#/components/schemas/ReviewCitationIssueOutLegacy"
            },
            "title": "Citation Issues",
            "type": "array"
          },
          "citation_failures": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewCitationFailedRowOutLegacy"
            },
            "title": "Citation Failures",
            "type": "array"
          },
          "more_citations": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/ReviewMoreCitationOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Citations found in the text past the ones selected (up to 100): found but not checked; send them in a later request to check them. Null until the text is read; [] for pairs.",
            "title": "More Citations"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "citecheck_id",
          "status",
          "outcome",
          "created_at",
          "completed_at",
          "language",
          "poll_after_seconds",
          "policy",
          "summary",
          "credits",
          "failure"
        ],
        "title": "CitecheckOutLegacy",
        "type": "object",
        "description": "A citation check as `2026-05-13` sends it: a cancelled check is `failed` with a `cancelled` failure."
      },
      "ReviewWebhookPayloadLegacy": {
        "description": "A `review.*` webhook as `2026-05-13` sends it: `task_id` (an internal delivery id, not pollable) beside `review_id`, and the review in its older shape; a cancelled review is `review.failed`.",
        "properties": {
          "event": {
            "type": "string",
            "enum": [
              "review.completed",
              "review.failed"
            ]
          },
          "event_id": {
            "title": "Event Id",
            "type": "string"
          },
          "review_id": {
            "title": "Review Id",
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "completed",
              "failed"
            ]
          },
          "review": {
            "$ref": "#/components/schemas/ReviewFullOutLegacy"
          },
          "attempt": {
            "title": "Attempt",
            "type": "integer"
          },
          "delivered_at": {
            "title": "Delivered At",
            "type": "string"
          },
          "task_id": {
            "type": "string"
          }
        },
        "required": [
          "event",
          "event_id",
          "review_id",
          "status",
          "review",
          "attempt",
          "delivered_at"
        ],
        "title": "ReviewWebhookPayloadLegacy",
        "type": "object"
      },
      "CitecheckWebhookPayloadLegacy": {
        "description": "A `citecheck.*` webhook as `2026-05-13` sends it: `task_id` (an internal delivery id, not pollable) beside `citecheck_id`, and the check in its older shape; a cancelled check is `citecheck.failed`.",
        "properties": {
          "event": {
            "type": "string",
            "enum": [
              "citecheck.completed",
              "citecheck.failed"
            ]
          },
          "event_id": {
            "title": "Event Id",
            "type": "string"
          },
          "citecheck_id": {
            "title": "Citecheck Id",
            "type": "string"
          },
          "status": {
            "type": "string",
            "enum": [
              "completed",
              "failed"
            ]
          },
          "citecheck": {
            "$ref": "#/components/schemas/CitecheckOutLegacy"
          },
          "attempt": {
            "title": "Attempt",
            "type": "integer"
          },
          "delivered_at": {
            "title": "Delivered At",
            "type": "string"
          },
          "task_id": {
            "type": "string"
          }
        },
        "required": [
          "event",
          "event_id",
          "citecheck_id",
          "status",
          "citecheck",
          "attempt",
          "delivered_at"
        ],
        "title": "CitecheckWebhookPayloadLegacy",
        "type": "object"
      },
      "MeUsageOutLegacy": {
        "description": "`/me/usage` as `2026-05-13` sends it: the current body plus `quota_resets_at`, `credits.bonus` and the `verify` / `ask` / `assess` blocks, every one always present.",
        "properties": {
          "plan": {
            "default": "free",
            "title": "Plan",
            "type": "string"
          },
          "plan_label": {
            "default": "Free",
            "title": "Plan Label",
            "type": "string"
          },
          "quota_resets_at": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Quota Resets At"
          },
          "credits": {
            "$ref": "#/components/schemas/MeUsageCreditsOut"
          },
          "costs": {
            "additionalProperties": {
              "type": "integer"
            },
            "title": "Costs",
            "type": "object"
          },
          "cost_options": {
            "additionalProperties": {
              "additionalProperties": {
                "additionalProperties": {
                  "type": "integer"
                },
                "type": "object"
              },
              "type": "object"
            },
            "default": {},
            "title": "Cost Options",
            "type": "object"
          },
          "verify": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/MeUsageQuotaOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "ask": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/MeUsageQuotaOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "assess": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/MeUsageQuotaOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "extract": {
            "$ref": "#/components/schemas/MeUsageExtractOut"
          },
          "has_webhook_secret": {
            "default": false,
            "title": "Has Webhook Secret",
            "type": "boolean"
          }
        },
        "required": [
          "credits",
          "costs",
          "extract"
        ],
        "title": "MeUsageOutLegacy",
        "type": "object"
      },
      "ReviewFailedRowOutLegacy": {
        "properties": {
          "claim_index": {
            "title": "Claim Index",
            "type": "integer"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "stage": {
            "enum": [
              "assessment",
              "verification"
            ],
            "title": "Stage",
            "type": "string"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "claim_index",
          "claim",
          "stage",
          "failure"
        ],
        "title": "ReviewFailedRowOutLegacy",
        "type": "object",
        "description": "`ReviewFailedRowOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains."
      },
      "ReviewCitationIssueOutLegacy": {
        "properties": {
          "citation_index": {
            "title": "Citation Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "statement": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Statement"
          },
          "quotes": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Quotes",
            "type": "array"
          },
          "position": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/PositionOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "finding": {
            "enum": [
              "doi_not_found",
              "page_not_found",
              "contradicted",
              "quote_not_in_source",
              "not_in_source",
              "partly_supported",
              "metadata_mismatch",
              "supported",
              "unchecked"
            ],
            "title": "Finding",
            "type": "string"
          },
          "source": {
            "anyOf": [
              {
                "enum": [
                  "doi",
                  "page",
                  "support",
                  "quote",
                  "metadata"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Source"
          },
          "snippet": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set only when source is support.",
            "title": "Snippet"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set only when source is support.",
            "title": "Rationale"
          },
          "metadata_differences": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewMetadataDifferenceOut"
            },
            "title": "Metadata Differences",
            "type": "array"
          },
          "missing_quote": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Set only when finding is quote_not_in_source.",
            "title": "Missing Quote"
          },
          "page_title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Page Title"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "citation_index",
          "reference",
          "cited_url",
          "doi",
          "statement",
          "position",
          "finding",
          "source",
          "snippet",
          "rationale",
          "page_title",
          "failure"
        ],
        "title": "ReviewCitationIssueOutLegacy",
        "type": "object",
        "description": "`ReviewCitationIssueOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains."
      },
      "ReviewCitationFailedRowOutLegacy": {
        "properties": {
          "citation_index": {
            "title": "Citation Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "citation_index",
          "reference",
          "cited_url",
          "doi",
          "failure"
        ],
        "title": "ReviewCitationFailedRowOutLegacy",
        "type": "object",
        "description": "`ReviewCitationFailedRowOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains."
      },
      "ReviewClaimOutLegacy": {
        "properties": {
          "index": {
            "title": "Index",
            "type": "integer"
          },
          "claim": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Claim"
          },
          "positions": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/components/schemas/PositionOut"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the draft makes this claim: every place, in text order, at most 10, in the same shape as a citation's `position`: `start` / `end` in Unicode code points of `text` as you sent it, half-open, and the passage in `text`. For a URL draft `start` / `end` are `null` and `text` carries the passage. Only claims traced back to the draft are listed at all. `null` when the claim could not be placed, or once a zero-retention draft is gone.",
            "title": "Positions"
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewResultOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          },
          "assessment": {
            "$ref": "#/components/schemas/ReviewAssessmentOutLegacy"
          },
          "escalation": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewEscalationOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "verification": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewVerificationOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          },
          "suggested_edits": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewSuggestedEditsOut"
              },
              {
                "type": "null"
              }
            ],
            "description": "Asked with `escalate.suggest_edits`. They follow the row's suggested rewrite: its completed deep check's, else its quick check's (see the issue's `source`). `null` when not asked, when the claim has no suggested rewrite, when the draft's passage is not in a supported language or could not be placed, or once a zero-retention draft is gone. Guide: https://lenz.io/docs/citations#suggested-edits"
          }
        },
        "required": [
          "index",
          "claim",
          "result",
          "assessment",
          "escalation",
          "verification"
        ],
        "title": "ReviewClaimOutLegacy",
        "type": "object",
        "description": "`ReviewClaimOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains."
      },
      "ReviewCitationOutLegacy": {
        "properties": {
          "index": {
            "title": "Index",
            "type": "integer"
          },
          "reference": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Reference"
          },
          "cited_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Cited Url"
          },
          "doi": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi"
          },
          "statement": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Statement"
          },
          "quotes": {
            "default": [],
            "items": {
              "type": "string"
            },
            "title": "Quotes",
            "type": "array"
          },
          "position": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/PositionOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "result": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewCitationResultOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "check": {
            "$ref": "#/components/schemas/ReviewCitationCheckOutLegacy"
          }
        },
        "required": [
          "index",
          "reference",
          "cited_url",
          "doi",
          "statement",
          "position",
          "result",
          "check"
        ],
        "title": "ReviewCitationOutLegacy",
        "type": "object",
        "description": "`ReviewCitationOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains."
      },
      "ReviewCitationCheckOutLegacy": {
        "properties": {
          "status": {
            "enum": [
              "pending",
              "running",
              "completed",
              "failed"
            ],
            "title": "Status",
            "type": "string"
          },
          "page_read": {
            "anyOf": [
              {
                "enum": [
                  "full",
                  "partial",
                  "not_found",
                  "none"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "What reading the source gave: full, partial (cut short, a teaser or an abstract alone), not_found, none.",
            "title": "Page Read"
          },
          "page_title": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Page Title"
          },
          "page_published_date": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Page Published Date"
          },
          "page_language": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The language of the page that was read, as an ISO 639-1 code (e.g. `en`, `uk`); null when unknown.",
            "title": "Page Language"
          },
          "source_url": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Where the text was actually read from.",
            "title": "Source Url"
          },
          "source_version": {
            "anyOf": [
              {
                "enum": [
                  "published",
                  "accepted",
                  "submitted"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Source Version"
          },
          "support": {
            "anyOf": [
              {
                "enum": [
                  "supported",
                  "partly_supported",
                  "contradicted",
                  "not_in_source",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Support"
          },
          "snippet": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The passage from the source the support answer rests on, checked against the page text.",
            "title": "Snippet"
          },
          "rationale": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The reviewer's sentence: reasoning, not a checked source.",
            "title": "Rationale"
          },
          "quote": {
            "anyOf": [
              {
                "enum": [
                  "matched",
                  "not_in_source",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Quote"
          },
          "missing_quote": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "The first of quotes the source does not contain; null unless quote is not_in_source.",
            "title": "Missing Quote"
          },
          "doi_registered": {
            "anyOf": [
              {
                "type": "boolean"
              },
              {
                "type": "null"
              }
            ],
            "title": "Doi Registered"
          },
          "metadata": {
            "anyOf": [
              {
                "enum": [
                  "consistent",
                  "mismatch",
                  "unchecked"
                ],
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Metadata"
          },
          "metadata_differences": {
            "default": [],
            "items": {
              "$ref": "#/components/schemas/ReviewMetadataDifferenceOut"
            },
            "title": "Metadata Differences",
            "type": "array"
          },
          "registered": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/ReviewRegisteredOut"
              },
              {
                "type": "null"
              }
            ]
          },
          "unchecked_reason": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "description": "Why the finding is unchecked; an extensible string.",
            "title": "Unchecked Reason"
          },
          "hint": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Hint"
          },
          "failure": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/FailureOutLegacy"
              },
              {
                "type": "null"
              }
            ]
          }
        },
        "required": [
          "status"
        ],
        "title": "ReviewCitationCheckOutLegacy",
        "type": "object",
        "description": "`ReviewCitationCheckOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains."
      },
      "BatchAcceptedOutLegacy": {
        "title": "BatchAcceptedOutLegacy",
        "type": "object",
        "description": "`BatchAcceptedOut` as `2026-05-13` sends it: the same fields, with the older shape of what it contains.",
        "properties": {
          "batch_id": {
            "type": "string"
          },
          "items": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/BatchAcceptedItemOutLegacy"
            }
          },
          "partial": {
            "type": "boolean",
            "description": "True when only some of the claims were accepted (the balance covered the first ones)."
          }
        },
        "required": [
          "batch_id",
          "items"
        ]
      }
    },
    "securitySchemes": {
      "APIKeyBearerAuth": {
        "type": "http",
        "scheme": "bearer"
      }
    },
    "parameters": {
      "XLenzApiVersion": {
        "name": "X-Lenz-API-Version",
        "in": "header",
        "required": false,
        "schema": {
          "type": "string",
          "examples": [
            "2026-05-13"
          ]
        },
        "description": "The API version to answer in, as a date. A date before `2026-10-11` (or a value that is not a date) gets `2026-05-13`. See https://lenz.io/docs/api-versions."
      }
    },
    "headers": {
      "XLenzApiVersion": {
        "description": "The API version this response is in.",
        "schema": {
          "type": "string"
        }
      }
    }
  },
  "servers": [
    {
      "url": "https://lenz.io",
      "description": "Production"
    }
  ],
  "tags": [
    {
      "name": "Extract",
      "description": "Pull verifiable claims out of any text. Costs no credits; fair-use cap 1,000/account/day."
    },
    {
      "name": "Assess",
      "description": "Fast panel verdict on a claim, with the pages the reviewers looked at. Sync, typically 10-25s; allow 45s for the response."
    },
    {
      "name": "Verify",
      "description": "The full investigation, with verified citations. Async, ~90s. Submit one claim or a batch, poll status, and resolve a needs_input interrupt with select."
    },
    {
      "name": "Review",
      "description": "The whole recipe in one call: find the claims in a draft, quick-check each, deep-check the ones that look wrong or uncertain, and get the issues back with suggested rewrites. Async, two to four minutes; poll the review or receive review.completed at a webhook."
    },
    {
      "name": "Citecheck",
      "description": "Check whether each cited source says what a draft attributes to it: from a draft with its links, or from statement-source pairs. Async; 1 credit per checked citation, and a source that could not be checked is not charged."
    },
    {
      "name": "Ask",
      "description": "Ask follow-up questions grounded on an existing verification."
    },
    {
      "name": "Verifications",
      "description": "List, fetch, delete, and toggle visibility on stored verifications."
    },
    {
      "name": "Library",
      "description": "Browse the public catalog of verifications. No API key required."
    },
    {
      "name": "Account",
      "description": "Your credit balance, the price list, and rate-limit usage."
    },
    {
      "name": "Discovery",
      "description": "Machine-readable index of the API root."
    }
  ],
  "webhooks": {
    "verification.completed": {
      "post": {
        "summary": "verification.completed",
        "description": "Fires when a verification reaches a terminal state with a verdict.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/WebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/WebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/WebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "verification.failed": {
      "post": {
        "summary": "verification.failed",
        "description": "Fires when the verification pipeline failed and no verdict is available.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/WebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/WebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/WebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "verification.needs_input": {
      "post": {
        "summary": "verification.needs_input",
        "description": "Fires when framing detects multiple claims, ambiguity, or a duplicate.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/WebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/WebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/WebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "verification.cancelled": {
      "post": {
        "summary": "verification.cancelled",
        "description": "Fires when POST /verify/{task_id}/cancel stopped the run: nothing was saved or charged. A 2026-05-13 submission receives verification.failed with failure_class \"cancelled\" instead.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/WebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/WebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/WebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "webhook.test": {
      "post": {
        "summary": "webhook.test",
        "description": "Fires only when you click Send test on the API credentials page (or POST /api-keys/{id}/webhook-test). It carries no result and no real task_id \u2014 its job is to prove a signed POST from us reaches your endpoint before you spend a verification finding out. Switch on `event` and ignore it.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/WebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/WebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/WebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "review.completed": {
      "post": {
        "summary": "review.completed",
        "description": "Fires once when a review ends with every planned deep check done. The body is ReviewWebhookPayload, not WebhookPayload: switch on `event` and dedupe on `event_id`. A review's own deep checks fire no verification.* events.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/ReviewWebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/ReviewWebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/ReviewWebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "review.failed": {
      "post": {
        "summary": "review.failed",
        "description": "Fires once when a review ends without a result (no claim, no credits, an outage).",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/ReviewWebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/ReviewWebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/ReviewWebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "review.cancelled": {
      "post": {
        "summary": "review.cancelled",
        "description": "Fires once when POST /reviews/{review_id}/cancel stopped the review. What was not delivered was not charged. A 2026-05-13 submission receives review.failed instead.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/ReviewWebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/ReviewWebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/ReviewWebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "citecheck.completed": {
      "post": {
        "summary": "citecheck.completed",
        "description": "Fires once when a citation check (POST /citecheck) ends with every citation checked or not checkable. The body is CitecheckWebhookPayload: switch on `event` and dedupe on `event_id`.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/CitecheckWebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/CitecheckWebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/CitecheckWebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "citecheck.failed": {
      "post": {
        "summary": "citecheck.failed",
        "description": "Fires once when a citation check ends without a result (no citation in the text, no credits, an outage).",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/CitecheckWebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/CitecheckWebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/CitecheckWebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "citecheck.cancelled": {
      "post": {
        "summary": "citecheck.cancelled",
        "description": "Fires once when POST /citechecks/{citecheck_id}/cancel stopped the check. Citations not checked were not charged. A 2026-05-13 submission receives citecheck.failed instead.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/CitecheckWebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/CitecheckWebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/CitecheckWebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    },
    "certificate.timestamped": {
      "post": {
        "summary": "certificate.timestamped",
        "description": "Fires when a covered verification's qualified timestamp lands, minutes after verification.completed. If you publish automatically, publish on this event: the warranty covers a publication that FOLLOWS the timestamp, and verification.completed fires while the qualified timestamp is still pending.",
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/WebhookPayload"
              },
              "x-lenz-versions": {
                "2026-10-11": {
                  "$ref": "#/components/schemas/WebhookPayload"
                },
                "2026-05-13": {
                  "$ref": "#/components/schemas/WebhookPayloadLegacy"
                }
              }
            }
          }
        },
        "responses": {
          "2XX": {
            "description": "Your endpoint should return 2xx within 5 seconds. Non-2xx triggers retries at 10s / 60s / 600s (3 retries after the initial delivery, 4 attempts total)."
          }
        }
      }
    }
  }
}