From c0f3df0f7c861bf4a5bec2ab53017ee8be25cbc5 Mon Sep 17 00:00:00 2001 From: dylan Date: Tue, 6 Oct 2026 12:11:35 -0500 Subject: [PATCH] Use concise names for newly public datasets --- src/gasbench/dataset/configs/real_audio.yaml | 8 +++---- src/gasbench/dataset/configs/real_images.yaml | 14 +++++------ src/gasbench/dataset/configs/real_videos.yaml | 24 +++++++++---------- .../dataset/configs/synthetic_audio.yaml | 14 +++++------ .../dataset/configs/synthetic_images.yaml | 24 +++++++++---------- .../dataset/configs/synthetic_videos.yaml | 8 +++---- 6 files changed, 46 insertions(+), 46 deletions(-) diff --git a/src/gasbench/dataset/configs/real_audio.yaml b/src/gasbench/dataset/configs/real_audio.yaml index 515ab60..71517f0 100644 --- a/src/gasbench/dataset/configs/real_audio.yaml +++ b/src/gasbench/dataset/configs/real_audio.yaml @@ -898,7 +898,7 @@ datasets: hf_revision: 0699bb1d85463a1cb5928db83bc61bdd127b4590 # Released v26 holdouts — pinned upstream HF sources. - - name: v26-real-galgame-speech-asr-16khz + - name: galgame-speech-asr-16khz path: litagin/Galgame_Speech_ASR_16kHz hf_revision: 3fb86654222b3f0af0f7c332ae6a0ef9752a9451 media_per_archive: 1000 @@ -908,7 +908,7 @@ datasets: - data/galgame-speech-asr-16kHz-train- modality: audio media_type: real - - name: v26-real-sada2022-arabic-tts + - name: sada2022-arabic-tts path: mohamedalgmaal/sada2022-arabic-tts hf_revision: 10870c1a64d17a24a791ee08e8297f216f96a447 media_per_archive: 1000 @@ -918,7 +918,7 @@ datasets: - batch_ modality: audio media_type: real - - name: v26-real-starrail-voice + - name: starrail-voice path: simon3000/starrail-voice hf_revision: 1e5f1e8658ab2e618c4815cf64ddf905c361067d media_per_archive: 1000 @@ -930,7 +930,7 @@ datasets: - audio modality: audio media_type: real - - name: v26-real-worldspeech + - name: worldspeech path: disco-eth/WorldSpeech hf_revision: b76b85395039f50332fbc421f7c098ee2f2653d7 media_per_archive: 1000 diff --git a/src/gasbench/dataset/configs/real_images.yaml b/src/gasbench/dataset/configs/real_images.yaml index a4acd69..eee90b8 100644 --- a/src/gasbench/dataset/configs/real_images.yaml +++ b/src/gasbench/dataset/configs/real_images.yaml @@ -1290,7 +1290,7 @@ datasets: hf_revision: a3cf2557e18a832c4b2921c8d20948202eab54f5 # Released v26 holdouts — pinned upstream HF sources. - - name: v25-real-beans-test + - name: beans-test path: AI-Lab-Makerere/beans hf_revision: 27aa014ce09b193e1a6f58112d4a66e0eddb69c5 media_per_archive: 1000 @@ -1302,7 +1302,7 @@ datasets: - image modality: image media_type: real - - name: v25-real-beans-train + - name: beans-train path: AI-Lab-Makerere/beans hf_revision: 27aa014ce09b193e1a6f58112d4a66e0eddb69c5 media_per_archive: 1000 @@ -1314,7 +1314,7 @@ datasets: - image modality: image media_type: real - - name: v25-real-beans-validation + - name: beans-validation path: AI-Lab-Makerere/beans hf_revision: 27aa014ce09b193e1a6f58112d4a66e0eddb69c5 media_per_archive: 1000 @@ -1326,7 +1326,7 @@ datasets: - image modality: image media_type: real - - name: v25-real-oxford-iiit-pet-test + - name: oxford-iiit-pet-test path: timm/oxford-iiit-pet hf_revision: 089695c834a7deb60505b7cc506672db1c31a6aa media_per_archive: 1000 @@ -1338,7 +1338,7 @@ datasets: - image modality: image media_type: real - - name: v25-real-oxford-iiit-pet-train + - name: oxford-iiit-pet-train path: timm/oxford-iiit-pet hf_revision: 089695c834a7deb60505b7cc506672db1c31a6aa media_per_archive: 1000 @@ -1350,7 +1350,7 @@ datasets: - image modality: image media_type: real - - name: v26-real-dcvlm-pool-large-dvqa + - name: dcvlm-pool-large-dvqa path: mlfoundations/dcvlm_pool_large hf_revision: 479162ae38203029e06807038cd2e5e545bfd2e0 media_per_archive: 1000 @@ -1360,7 +1360,7 @@ datasets: - dvqa/ modality: image media_type: real - - name: v26-real-puffin-16m + - name: puffin-16m path: ACERobotics/Puffin-16M hf_revision: 2112b3502f9ea0cc1d31d2c5a2b7f2259b52cffd media_per_archive: 1000 diff --git a/src/gasbench/dataset/configs/real_videos.yaml b/src/gasbench/dataset/configs/real_videos.yaml index 7ed80f2..9670962 100644 --- a/src/gasbench/dataset/configs/real_videos.yaml +++ b/src/gasbench/dataset/configs/real_videos.yaml @@ -1341,7 +1341,7 @@ datasets: hf_revision: f0af08aece50ff99a9c399f063d71e455d610bbf # Released v26 holdouts — pinned upstream HF sources. - - name: v25-rendered-physical-interaction-bowling-00000 + - name: physical-interaction-bowling-00000 path: nvidia/PhysicalAI-WorldModel-Synthetic-Physical-Interaction-Scenes hf_revision: bdafca2a9c575629e47509f547e27ab7f3680369 media_per_archive: 250 @@ -1356,7 +1356,7 @@ datasets: - Side.mp4 modality: video media_type: real - - name: v25-rendered-physical-interaction-bowling-00042 + - name: physical-interaction-bowling-00042 path: nvidia/PhysicalAI-WorldModel-Synthetic-Physical-Interaction-Scenes hf_revision: bdafca2a9c575629e47509f547e27ab7f3680369 media_per_archive: 250 @@ -1371,7 +1371,7 @@ datasets: - Side.mp4 modality: video media_type: real - - name: v25-rendered-physical-interaction-bowling-00063 + - name: physical-interaction-bowling-00063 path: nvidia/PhysicalAI-WorldModel-Synthetic-Physical-Interaction-Scenes hf_revision: bdafca2a9c575629e47509f547e27ab7f3680369 media_per_archive: 250 @@ -1386,7 +1386,7 @@ datasets: - Side.mp4 modality: video media_type: real - - name: v25-rendered-physical-interaction-bowling-00084 + - name: physical-interaction-bowling-00084 path: nvidia/PhysicalAI-WorldModel-Synthetic-Physical-Interaction-Scenes hf_revision: bdafca2a9c575629e47509f547e27ab7f3680369 media_per_archive: 250 @@ -1401,7 +1401,7 @@ datasets: - Side.mp4 modality: video media_type: real - - name: v25-rendered-physicalai-worldmodel-synthetic-warehouse-operations-scenes-artifacts-forklift-human-nearmiss-nearmiss-artifacts-00005 + - name: physicalai-warehouse-forklift-nearmiss-00005 path: nvidia/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes hf_revision: d5b88d3abcf659f304a107f4336b71b4e2159133 media_per_archive: 250 @@ -1413,7 +1413,7 @@ datasets: - .rgb.mp4 modality: video media_type: real - - name: v25-rendered-physicalai-worldmodel-synthetic-warehouse-operations-scenes-artifacts-forklift-human-nearmiss-nearmiss-artifacts-00016 + - name: physicalai-warehouse-forklift-nearmiss-00016 path: nvidia/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes hf_revision: d5b88d3abcf659f304a107f4336b71b4e2159133 media_per_archive: 250 @@ -1425,7 +1425,7 @@ datasets: - .rgb.mp4 modality: video media_type: real - - name: v25-rendered-physicalai-worldmodel-synthetic-warehouse-operations-scenes-artifacts-forklift-human-nearmiss-nearmiss-artifacts-00028 + - name: physicalai-warehouse-forklift-nearmiss-00028 path: nvidia/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes hf_revision: d5b88d3abcf659f304a107f4336b71b4e2159133 media_per_archive: 250 @@ -1437,7 +1437,7 @@ datasets: - .rgb.mp4 modality: video media_type: real - - name: v25-rendered-physicalai-worldmodel-synthetic-warehouse-operations-scenes-artifacts-forklift-human-nearmiss-nearmiss-artifacts-00039 + - name: physicalai-warehouse-forklift-nearmiss-00039 path: nvidia/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes hf_revision: d5b88d3abcf659f304a107f4336b71b4e2159133 media_per_archive: 250 @@ -1449,7 +1449,7 @@ datasets: - .rgb.mp4 modality: video media_type: real - - name: v25-rendered-physicalai-worldmodel-synthetic-warehouse-operations-scenes-artifacts-forklift-human-nearmiss-nearmiss-artifacts-00050 + - name: physicalai-warehouse-forklift-nearmiss-00050 path: nvidia/PhysicalAI-WorldModel-Synthetic-Warehouse-Operations-Scenes hf_revision: d5b88d3abcf659f304a107f4336b71b4e2159133 media_per_archive: 250 @@ -1461,7 +1461,7 @@ datasets: - .rgb.mp4 modality: video media_type: real - - name: v26-real-physicalai-robotics-manipulation-objects + - name: physicalai-robotics-manipulation-objects path: nvidia/PhysicalAI-Robotics-Manipulation-Objects hf_revision: 538b6833148b4731e4ea30fe181cc4eecfc13440 media_per_archive: 250 @@ -1471,7 +1471,7 @@ datasets: - .rgb/ modality: video media_type: real - - name: v26-real-pick-tblock-mp-centered-0701-rendered + - name: pick-tblock-mp-centered-0701-rendered path: younghyopark/pick_tblock_mp_centered_0701_rendered hf_revision: b353fb987b6cc55524fb144ea61632168bc2ca5f media_per_archive: 250 @@ -1481,7 +1481,7 @@ datasets: - videos/chunk-000/ modality: video media_type: real - - name: v26-real-vidgen-1m + - name: vidgen-1m path: Fudan-FUXI/VIDGEN-1M hf_revision: 9158f218b6b81694a7809b6ee74e30003d58a70e media_per_archive: 250 diff --git a/src/gasbench/dataset/configs/synthetic_audio.yaml b/src/gasbench/dataset/configs/synthetic_audio.yaml index dd5823c..d76cca2 100644 --- a/src/gasbench/dataset/configs/synthetic_audio.yaml +++ b/src/gasbench/dataset/configs/synthetic_audio.yaml @@ -902,7 +902,7 @@ datasets: hf_revision: 04188209b3135617c0c682c432c2168e01b35011 # Released v26 holdouts — pinned upstream HF sources. - - name: v25-Fake-Synthetic-Turkish-TTS-Data + - name: turkish-tts-data path: Anilosan15/Synthetic_Turkish_TTS_Data hf_revision: f1d0e40efb27b5e78cdd6dbd6f6b601ab2ce9ae0 media_per_archive: 1000 @@ -914,7 +914,7 @@ datasets: - audio modality: audio media_type: synthetic - - name: v25-Fake-qwen-clones-4m-en-audio-train-00000-of-00080 + - name: qwen-clones-4m-en-audio-train-00000-of-00080 path: SynDataLab-EN/qwen-clones-4m-en hf_revision: 38769c7d96e5767035555a66ce57b1076a7dccf1 media_per_archive: 1000 @@ -926,7 +926,7 @@ datasets: - audio modality: audio media_type: synthetic - - name: v25-Fake-qwen-clones-4m-en-audio-train-00035-of-00080 + - name: qwen-clones-4m-en-audio-train-00035-of-00080 path: SynDataLab-EN/qwen-clones-4m-en hf_revision: 38769c7d96e5767035555a66ce57b1076a7dccf1 media_per_archive: 1000 @@ -938,7 +938,7 @@ datasets: - audio modality: audio media_type: synthetic - - name: v25-Fake-qwen-clones-4m-en-audio-train-00052-of-00080 + - name: qwen-clones-4m-en-audio-train-00052-of-00080 path: SynDataLab-EN/qwen-clones-4m-en hf_revision: 38769c7d96e5767035555a66ce57b1076a7dccf1 media_per_archive: 1000 @@ -950,7 +950,7 @@ datasets: - audio modality: audio media_type: synthetic - - name: v25-Fake-qwen-clones-4m-en-audio-train-00074-of-00080 + - name: qwen-clones-4m-en-audio-train-00074-of-00080 path: SynDataLab-EN/qwen-clones-4m-en hf_revision: 38769c7d96e5767035555a66ce57b1076a7dccf1 media_per_archive: 1000 @@ -962,7 +962,7 @@ datasets: - audio modality: audio media_type: synthetic - - name: v26-synthetic-echo-clones-4m-en + - name: echo-clones-4m-en path: SynDataLab-EN/echo-clones-4m-en hf_revision: aebc7c787c64e918b0130c04d3878f17a602c1df media_per_archive: 1000 @@ -974,7 +974,7 @@ datasets: - audio modality: audio media_type: synthetic - - name: v26-synthetic-steak + - name: steak path: DEEL-AI/STEAK hf_revision: 4ee840a09e582d23d2ce88b7f99a1996ffe9aec6 media_per_archive: 1000 diff --git a/src/gasbench/dataset/configs/synthetic_images.yaml b/src/gasbench/dataset/configs/synthetic_images.yaml index 5c1d9b0..bf891b9 100644 --- a/src/gasbench/dataset/configs/synthetic_images.yaml +++ b/src/gasbench/dataset/configs/synthetic_images.yaml @@ -1175,7 +1175,7 @@ datasets: hf_revision: 5649a33952bb8faabf3b861ad3b5024374509e72 # Released v26 holdouts — pinned upstream HF sources. - - name: v25-synthetic-10D-500K-images-Animals-bagel + - name: 10d-500k-animals-bagel path: addisonwu05/10D-500K hf_revision: d5e2472237a1dc612d9b1d1bfaed8b9b90fbc0e1 media_per_archive: 1000 @@ -1190,7 +1190,7 @@ datasets: model: bagel modality: image media_type: synthetic - - name: v25-synthetic-10D-500K-images-Buildings-emu + - name: 10d-500k-buildings-emu path: addisonwu05/10D-500K hf_revision: d5e2472237a1dc612d9b1d1bfaed8b9b90fbc0e1 media_per_archive: 1000 @@ -1205,7 +1205,7 @@ datasets: model: emu modality: image media_type: synthetic - - name: v25-synthetic-10D-500K-images-Food_and_Drinks-janus + - name: 10d-500k-food-and-drinks-janus path: addisonwu05/10D-500K hf_revision: d5e2472237a1dc612d9b1d1bfaed8b9b90fbc0e1 media_per_archive: 1000 @@ -1220,7 +1220,7 @@ datasets: model: janus modality: image media_type: synthetic - - name: v25-synthetic-10D-500K-images-Interior_Spaces-mmada + - name: 10d-500k-interior-spaces-mmada path: addisonwu05/10D-500K hf_revision: d5e2472237a1dc612d9b1d1bfaed8b9b90fbc0e1 media_per_archive: 1000 @@ -1235,7 +1235,7 @@ datasets: model: mmada modality: image media_type: synthetic - - name: v25-synthetic-10D-500K-images-People-showo2 + - name: 10d-500k-people-showo2 path: addisonwu05/10D-500K hf_revision: d5e2472237a1dc612d9b1d1bfaed8b9b90fbc0e1 media_per_archive: 1000 @@ -1250,7 +1250,7 @@ datasets: model: showo2 modality: image media_type: synthetic - - name: v25-synthetic-Persona-Fluxed-10k-2608_brazil-train + - name: persona-fluxed-10k-2608-brazil-train path: retowyss/Persona-Fluxed-10k-2608 hf_revision: abd1938c598a1f67a242bb35cd9740a5e1870e78 media_per_archive: 1000 @@ -1260,7 +1260,7 @@ datasets: - brazil/train/ modality: image media_type: synthetic - - name: v25-synthetic-Persona-Fluxed-10k-2608_france-train + - name: persona-fluxed-10k-2608-france-train path: retowyss/Persona-Fluxed-10k-2608 hf_revision: abd1938c598a1f67a242bb35cd9740a5e1870e78 media_per_archive: 1000 @@ -1270,7 +1270,7 @@ datasets: - france/train/ modality: image media_type: synthetic - - name: v25-synthetic-Persona-Fluxed-10k-2608_japan-train + - name: persona-fluxed-10k-2608-japan-train path: retowyss/Persona-Fluxed-10k-2608 hf_revision: abd1938c598a1f67a242bb35cd9740a5e1870e78 media_per_archive: 1000 @@ -1280,7 +1280,7 @@ datasets: - japan/train/ modality: image media_type: synthetic - - name: v25-synthetic-Syn-Vis-v0-images-headshot + - name: syn-vis-v0-headshot path: retowyss/Syn-Vis-v0 hf_revision: 100262732989e77f38cd831d70a376a93735006a media_per_archive: 1000 @@ -1290,7 +1290,7 @@ datasets: - images/headshot/ modality: image media_type: synthetic - - name: v26-synthetic-per-400k + - name: per-400k path: a1557811266/Per-400k hf_revision: bbb01675182feca1434ae3fbb97a9355d9337a25 media_per_archive: 1000 @@ -1300,7 +1300,7 @@ datasets: - person_data/img/ modality: image media_type: synthetic - - name: v26-synthetic-sora-explore-dataset + - name: sora-explore-dataset path: abrar71/sora-explore-dataset hf_revision: 79559046d3782bb69147209bbbd72a787a326452 media_per_archive: 1000 @@ -1312,7 +1312,7 @@ datasets: - image modality: image media_type: synthetic - - name: v26-synthetic-stylegan-face + - name: stylegan-face path: gojay/StyleGAN-Face hf_revision: d7592242ec59376dd1c418dd0353c2361631ac6e media_per_archive: 1000 diff --git a/src/gasbench/dataset/configs/synthetic_videos.yaml b/src/gasbench/dataset/configs/synthetic_videos.yaml index 626b709..91f731e 100644 --- a/src/gasbench/dataset/configs/synthetic_videos.yaml +++ b/src/gasbench/dataset/configs/synthetic_videos.yaml @@ -1299,7 +1299,7 @@ datasets: hf_revision: fa7713f57249caf009200ab0f875c07cd3e20986 # Released v26 holdouts — pinned upstream HF sources. - - name: v26-semisynthetic-vera-layered-video-dataset + - name: vera-layered-video-dataset path: netflix/Vera-Layered-Video-Dataset hf_revision: 8e0b98ee9bce66fdae345e75aa766ef7c0a04d4e media_per_archive: 250 @@ -1310,7 +1310,7 @@ datasets: - train-set/81-frames/synthetic-obj-add/composite/ modality: video media_type: semisynthetic - - name: v26-synthetic-text-2-video-human-preferences-genmo-mochi-1 + - name: text-2-video-human-preferences-genmo-mochi-1 path: Rapidata/text-2-video-human-preferences-genmo-mochi-1 hf_revision: 9b8c6dbba6ba4e034adaa509550e53d81e3b7148 media_per_archive: 250 @@ -1320,7 +1320,7 @@ datasets: - Videos/ modality: video media_type: synthetic - - name: v26-synthetic-vbench-2-0-sampled-videos + - name: vbench-2-0-sampled-videos path: Vchitect/VBench-2.0_sampled_videos hf_revision: f9ee15efcfb86d96bd5379e8d85f8d69b901aad1 media_per_archive: 250 @@ -1328,7 +1328,7 @@ datasets: source_format: mp4 modality: video media_type: synthetic - - name: v26-synthetic-vbench-i2v-sampled-video + - name: vbench-i2v-sampled-video path: Vchitect/VBench-I2V_sampled_video hf_revision: d1977eff951fad22ac7ac11059f6939f570a78eb media_per_archive: 250