Skip to content

About

INDUS-DEDUCT — Calibrated, anti-hallucination computational epigraphy benchmark across 5,679 Indus Valley inscriptions (5-way Sumerian/Linear B/non-linguistic calibration, 700-yr BH-FDR drift, 690 LOCO restorations)

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

INDUS-DEDUCT (v1.0.1)

A Calibrated, Anti-Hallucination Computational Benchmark for the Indus Valley (Harappan) Script

DOI Live Portal Tests Cross-OS License

Live Interactive Explorer (EN / TR): https://indus.emare.dev/?lang=en · Zenodo DOI: 10.5281/zenodo.24383348 · PDF Preprint: INDUS_DEDUCT_PREPRINT.pdf · Claim Ledger: CLAIM_LEDGER.md

INDUS-DEDUCT is an end-to-end, reproducible 13-layer computational epigraphy benchmark across 5,679 Indus inscriptions (5,805 parsed lines; 713 raw signs). Every pipeline stage obeys a strict anti-hallucination contract:

  • Zero speculative upstream leakage: Upstream sanskrit, translation, and notes columns are stripped prior to modeling and guarded by test_01_zero_speculative_contamination.
  • Calibrated against real scripts & negative controls: Benchmarked at matched size and length (N = 2,047) against Ur III Sumerian (CDLI), Linear B, Linear A, and a structured non-linguistic stamp negative control.
  • Zero fabricated phonetic readings: We explicitly separate verified structural/stratigraphic proofs (Tier A) from comparative/typological leads (Tier B) and retired/falsified claims (Tier C). See CLAIM_LEDGER.md.

Key Deliverables

Deliverable Path Description
Full Academic Preprint (PDF) paper/INDUS_DEDUCT_PREPRINT.pdf 11-page peer-review-ready preprint with 3 embedded high-res figures (Layers 0–12)
Executive Claim Ledger CLAIM_LEDGER.md 1-page Tier A (Proven) / Tier B (Supported) / Tier C (Retired/Null) referee map
Interactive Web Portal portal/index.html 6-tab live FaunaTech Doğal Atlas v2.0 browser (294 live TTF glyphs, 690 restorations, calibration & stratigraphy)
Open Damaged Restoration Catalog reports/damaged_inscriptions_restoration_catalog.csv Calibrated Top-5 restorations for all 690 single-gap damaged inscriptions across 25 sites
Automated Verification Suite tests/test_claim_ledger.py 11/11 machine-verified invariants + SHA-256 integrity (DATA_MANIFEST.json)

Headline Verified Findings (Tier A)

  1. Five-Way Calibration (Layer 8): Retires within-sequence conditional entropy z_H1 (Non-Linguistic Stamps = -245.34σ vs. Indus = -108.85σ) and establishes three validated discriminators separating Indus and attested natural scripts from structured non-linguistic stamps:
    • Unseen-trigram generalization over position baseline: Indus +6.38 pp (+0.432 bits), Ur III Sumerian +10.71 pp, Linear B +0.81 pp vs. Non-Linguistic -2.95 pp (-0.960 bits).
    • Kober bridge–ending MI z: Indus +53.67σ, Ur III Sumerian +20.40σ, Linear B +18.47σ vs. Non-Linguistic +0.07σ.
    • Blind 2-affix stacking (Suffix:Prefix): Indus 207:1 (4.96× right-edge bottleneck) vs. Ur III Sumerian 4:39, Linear B 22:11, Non-Linguistic 0:0.
  2. Logo-Syllabic Core & Sub-Graphemic Grammar (Layers 1B, 5B, 7): N_core = 240–271 graphemes (95.7% tokens); : X : four-dash frame converts medial stems (2.9%) to terminals (62.2%, 8/8 pairs, p = 4.38e-45) and transfers zero-shot across unseen base glyphs (LOBO Δlog-loss = -31.3%).
  3. 700-Year Paleographic Drift & Cross-City Sync (Layer 12): De-confounding Mohenjo-daro excavation datums (n = 1,253 within-area; DKG(S) n = 595) and replicating against Harappa Period 2–5 (n = 637, Spearman rho = +0.289, p = 0.0376) uncovers two BH-FDR paleographic drift chains: #156 → #154 (q = 0.0083) and the 3-stage sprouting chain #838 → #803 → #806 (q = 0.0339, #806 #1 late sign in Harappa q = 0.0106), while core SEAL:S grammar remains frozen across 700 years (p > 0.09).
  4. Document Registries & Maritime vs. Riverine Logistics (Layers 9–12):
    • Mohenjo-daro Copper Tablets (TAB:C, 99.6% MD-exclusive): Text ↔ Icon MI z = +19.66σ (96.2% purity) + 23 single-sign reverse equations (#341 quadruped ↔ 503 615 740), yet 4 tests refute bare animal nouns (H1) in favor of compound institutional/ritual formulas (H2).
    • Harappa Double-Sided Tokens (TAB:I/B, 772 objects): Fixed Entity ↔ Quantity lock (+9.55σ) and : X : + 400 clitic stacking (95.2%, p = 1.16e-8).
    • Riverine Tablets vs. Maritime Cargo: 98.9% of tablets occur inland (enriched in freshwater Gavi gharial 62/66 and Fish 47/47), whereas 65.3% of cargo sealings (TAG*) and ~66% of circular Gulf seals (SEAL:C) are coastal/maritime — anchored by Twin-Humans #091 (0% final, 11.89× trade/cargo lift p = 1.48e-6, 42.35× in foreign corridor q = 2.86e-4).
  5. Exact Phonetic Decipherment Boundary (Layers 4B, 5B, 8, 11A): Known-answer 23-seal Max-CSP locks 23/23 (100%) of closed Linear B (+22.75σ) and Ur III Sumerian (+7.00σ) at k = 0, fails at k = 0 under realistic 74% open Sumerian (z = -0.11σ), and recovers 21/23 (+4.97σ, 68.2% shared signs) at k = 2 bilingual anchors. Expanding foreign Indus seals 24 → 42 → 55 strictly increases DOF (29 → 43 → 45), proving k ≥ 2 bilingual anchors are required.
  6. Leak-Free Visual-Neural LOCO Damaged Restoration (Layer 11B): Across 285 real damaged inscriptions held out over 12 cities (STRICT_LOCO), our visual-glyph + neural MLP hybrid improves edge_all Top-1 from 53.5% → 57.5% (Top-5 82.9%, baseline 10.2%) and interior_all Top-1 from 30.0% → 40.0% (Top-3 60.0%).

Quickstart & Full Reproduction

1. Zero-Dependency Claim-Ledger Check (Works on Fresh Clone, No pip Required)

git clone https://github.com/emraresoftware/indusemare.git
cd indusemare
python3 -m unittest tests/test_claim_ledger.py -v

This immediately verifies all analytical invariants across Layers 0–12 (reports/*.json) and SHA-256 checksums for bundled data/external/* tables. To respect primary epigraphic concordance rights (ICIT / CISI), raw upstream corpus dumps are not redistributed inside the repository (DATA_MANIFEST.json records their exact SHA-256 hashes for full local verification).

2. Full End-to-End Pipeline Reproduction (with Local Upstream Corpora)

python3 -m venv .venv
.venv/bin/pip install -r requirements.txt

# Place upstream raw corpora under data/raw/ and data/calibration/ (verified via DATA_MANIFEST.json)
.venv/bin/python src/layer0_ingest.py

# Strict 11/11 verification including all 17 DATA_MANIFEST.json SHA-256 hashes + SQLite checks
INDUS_STRICT_CORPUS=1 python3 -m unittest tests/test_claim_ledger.py -v

# Launch the bilingual (EN / TR) interactive FaunaTech Doğal Atlas portal locally
python3 -m http.server 4188 --bind 127.0.0.1 --directory portal

Citation

If you use INDUS-DEDUCT code, benchmark tables, or the 690-inscription damaged restoration catalog, please cite the permanent Zenodo archive:

@software{emre_2026_indus_deduct,
  author       = {Emre and {Emare INDUS-DEDUCT Research Collective}},
  title        = {{INDUS-DEDUCT: A Calibrated, Anti-Hallucination Computational Benchmark for the Indus Valley Script}},
  month        = nov,
  year         = 2026,
  publisher    = {Zenodo},
  version      = {v1.0.1},
  doi          = {10.5281/zenodo.24383348},
  url          = {https://doi.org/10.5281/zenodo.24383348}
}

Upstream Data Attribution

  • Indus Corpus: Derived from the Interactive Corpus of Indus Texts (ICIT; Bryan K. Wells & Andreas Fuls) and Corpus of Indus Seals and Inscriptions (CISI; Asko Parpola et al.), stripped of all speculative columns in Layer 0.
  • Calibration Corpora: Ur III Sumerian gold corpus (CDLI / MTAAC), Linear B transliterated words/tablets, and Linear A open corpus (LinearAWords.json).

About

INDUS-DEDUCT — Calibrated, anti-hallucination computational epigraphy benchmark across 5,679 Indus Valley inscriptions (5-way Sumerian/Linear B/non-linguistic calibration, 700-yr BH-FDR drift, 690 LOCO restorations)

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages