data: 9 deleted
This commit is contained in:
parent
658c739058
commit
ba58251e2e
477
.lfs-manifest
477
.lfs-manifest
@ -244,248 +244,239 @@ checkpoints/tapt/modernbert-large/final/model.safetensors bf0c507d25e312d5 59971
|
|||||||
checkpoints/tapt/modernbert-large/final/tokenizer_config.json 112ada643fbc85f4 215 2026-04-05T18:44:01-04:00
|
checkpoints/tapt/modernbert-large/final/tokenizer_config.json 112ada643fbc85f4 215 2026-04-05T18:44:01-04:00
|
||||||
checkpoints/tapt/modernbert-large/final/tokenizer.json 54ec85b5a198a7ec 516851 2026-04-05T18:44:01-04:00
|
checkpoints/tapt/modernbert-large/final/tokenizer.json 54ec85b5a198a7ec 516851 2026-04-05T18:44:01-04:00
|
||||||
checkpoints/tapt/modernbert-large/final/training_args.bin b9eef4bf74c3c09e 2465 2026-04-05T18:44:01-04:00
|
checkpoints/tapt/modernbert-large/final/training_args.bin b9eef4bf74c3c09e 2465 2026-04-05T18:44:01-04:00
|
||||||
data/analysis/corpus-stats.json d0921c5f5d1d803a 187805 2026-04-06T15:50:29-04:00
|
data/analysis/corpus-stats.json d0921c5f5d1d803a 187805 2026-04-06T15:53:02-04:00
|
||||||
data/analysis/corpus-stats.txt 76c7bf60bea553c9 2677 2026-04-06T15:50:30-04:00
|
data/analysis/corpus-stats.txt 76c7bf60bea553c9 2677 2026-04-06T15:53:02-04:00
|
||||||
data/analysis/dedup-analysis.json 3a412f46aec9c3c5 5851 2026-04-06T15:50:29-04:00
|
data/analysis/dedup-analysis.json 3a412f46aec9c3c5 5851 2026-04-06T15:53:02-04:00
|
||||||
data/analysis/dedup-analysis.txt 8b612dd3f091244f 2685 2026-04-06T15:50:29-04:00
|
data/analysis/dedup-analysis.txt 8b612dd3f091244f 2685 2026-04-06T15:53:02-04:00
|
||||||
data/analysis/quality-report.json edec6b974734b0bd 357 2026-04-06T15:50:29-04:00
|
data/analysis/quality-report.json edec6b974734b0bd 357 2026-04-06T15:53:02-04:00
|
||||||
data/analysis/quality-report.txt 5cf9084307d80601 2286 2026-04-06T15:50:30-04:00
|
data/analysis/quality-report.txt 5cf9084307d80601 2286 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/deepseek-r1-0528.jsonl d044dcb77b7007a2 535 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout/deepseek-r1-0528.jsonl d044dcb77b7007a2 535 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/gemini-3.1-pro-preview-errors.jsonl d1d814e1d9eccfd6 362 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout/gemini-3.1-pro-preview-errors.jsonl d1d814e1d9eccfd6 362 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/gemini-3.1-pro-preview.jsonl 7fd40534c1b1d9d7 109025 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout/gemini-3.1-pro-preview.jsonl 7fd40534c1b1d9d7 109025 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/glm-5:exacto-errors.jsonl 3f182ea919a40776 197 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout/glm-5:exacto-errors.jsonl 3f182ea919a40776 197 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/glm-5:exacto.jsonl 2bab470e6a542e8d 141767 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout/glm-5:exacto.jsonl 2bab470e6a542e8d 141767 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/gpt-5.4.jsonl 336ec6c4ff158f75 131184 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout/gpt-5.4.jsonl 336ec6c4ff158f75 131184 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/kimi-k2.5-errors.jsonl a912a706033d2797 455 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout/kimi-k2.5-errors.jsonl a912a706033d2797 455 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/kimi-k2.5.jsonl 88ed309c081870a7 164538 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout/kimi-k2.5.jsonl 88ed309c081870a7 164538 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/llama-4-scout-errors.jsonl 24c08dd5feded133 170 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout/llama-4-scout-errors.jsonl 24c08dd5feded133 170 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/mimo-v2-pro:exacto.jsonl 496b7fd72498a7af 118204 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout/mimo-v2-pro:exacto.jsonl 496b7fd72498a7af 118204 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout/minimax-m2.7:exacto.jsonl 21e4bc7253dd362e 172619 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout/minimax-m2.7:exacto.jsonl 21e4bc7253dd362e 172619 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35b/gpt-5.4.jsonl 527dc5979f1b38bb 4677 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout-v35b/gpt-5.4.jsonl 527dc5979f1b38bb 4677 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/gemini-3.1-pro-preview-errors.jsonl c5f71bebd1406963 354 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout-v35/gemini-3.1-pro-preview-errors.jsonl c5f71bebd1406963 354 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/gemini-3.1-pro-preview.jsonl 1b944dcdbda44dbf 37436 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout-v35/gemini-3.1-pro-preview.jsonl 1b944dcdbda44dbf 37436 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/glm-5:exacto.jsonl 34c2e9e019d275bb 47616 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout-v35/glm-5:exacto.jsonl 34c2e9e019d275bb 47616 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/gpt-5.4.jsonl dac5d724ad42dc16 44162 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout-v35/gpt-5.4.jsonl dac5d724ad42dc16 44162 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/kimi-k2.5.jsonl 04d143aa4fd36bec 56160 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout-v35/kimi-k2.5.jsonl 04d143aa4fd36bec 56160 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/mimo-v2-pro:exacto.jsonl 77a067a0b02e265c 39081 2026-04-06T15:50:30-04:00
|
data/annotations/bench-holdout-v35/mimo-v2-pro:exacto.jsonl 77a067a0b02e265c 39081 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/bench-holdout-v35/minimax-m2.7:exacto.jsonl 2d22ce6fb672895a 58869 2026-04-06T15:50:29-04:00
|
data/annotations/bench-holdout-v35/minimax-m2.7:exacto.jsonl 2d22ce6fb672895a 58869 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/golden/opus-errors.jsonl ad4a73f61bd26979 580 2026-04-06T15:50:29-04:00
|
data/annotations/golden/opus-errors.jsonl ad4a73f61bd26979 580 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/golden/opus-errors.wrong-sample.jsonl 5ea42b7509ae3f2c 161 2026-04-06T15:50:30-04:00
|
data/annotations/golden/opus-errors.wrong-sample.jsonl 5ea42b7509ae3f2c 161 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/golden/opus.jsonl 686d62a133070ec3 654749 2026-04-06T15:50:30-04:00
|
data/annotations/golden/opus.jsonl 686d62a133070ec3 654749 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/golden/opus.wrong-sample.jsonl a0a1508da86d90f6 364794 2026-04-06T15:50:30-04:00
|
data/annotations/golden/opus.wrong-sample.jsonl a0a1508da86d90f6 364794 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/golden-v35/opus.jsonl b5464fc1dc3f9c83 152361 2026-04-06T15:50:29-04:00
|
data/annotations/golden-v35/opus.jsonl b5464fc1dc3f9c83 152361 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/stage1-corrections.jsonl 44b16213759cb0d6 9333 2026-04-06T15:50:29-04:00
|
data/annotations/stage1-corrections.jsonl 44b16213759cb0d6 9333 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/stage1-gemini-grok.jsonl 14908eb36c1fc074 7811066 2026-04-06T15:50:29-04:00
|
data/annotations/stage1-gemini-grok.jsonl 14908eb36c1fc074 7811066 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/stage1.jsonl 9a447b31df1d566c 12041387 2026-04-06T15:50:30-04:00
|
data/annotations/stage1.jsonl 9a447b31df1d566c 12041387 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/stage1-nano-panel.jsonl 71faf9d54f87cc12 11763064 2026-04-06T15:50:30-04:00
|
data/annotations/stage1-nano-panel.jsonl 71faf9d54f87cc12 11763064 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/stage1-orphan-rerun.jsonl 6b90cc841d4961b4 372904 2026-04-06T15:50:30-04:00
|
data/annotations/stage1-orphan-rerun.jsonl 6b90cc841d4961b4 372904 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/stage1.patched.jsonl 62bd6b35a05f1ca5 12061314 2026-04-06T15:50:29-04:00
|
data/annotations/stage1.patched.jsonl 62bd6b35a05f1ca5 12061314 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gemini-3.1-flash-lite-preview.jsonl 5f4059540660cf24 133639 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/gemini-3.1-flash-lite-preview.jsonl 5f4059540660cf24 133639 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gemini-3.1-pro-preview.jsonl da144bcc19f61a84 134337 2026-04-06T15:50:29-04:00
|
data/annotations/v2-bench/gemini-3.1-pro-preview.jsonl da144bcc19f61a84 134337 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/glm-5:exacto-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/glm-5:exacto-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/glm-5:exacto.jsonl 7490642453b1ef32 174236 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/glm-5:exacto.jsonl 7490642453b1ef32 174236 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gpt-5.4.jsonl 8a79338cde4fb874 174625 2026-04-06T15:50:29-04:00
|
data/annotations/v2-bench/gpt-5.4.jsonl 8a79338cde4fb874 174625 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gpt-5.4.v4.0.jsonl 5f6dceef9ff1b551 26750 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/gpt-5.4.v4.0.jsonl 5f6dceef9ff1b551 26750 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gpt-5.4.v4.1.jsonl 211024aab28bcc0d 26915 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/gpt-5.4.v4.1.jsonl 211024aab28bcc0d 26915 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gpt-5.4.v4.2.jsonl 180804f86231a7bb 26975 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/gpt-5.4.v4.2.jsonl 180804f86231a7bb 26975 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gpt-5.4.v4.3.jsonl 79b183f7ac33caa1 26673 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/gpt-5.4.v4.3.jsonl 79b183f7ac33caa1 26673 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/gpt-5.4.v4.4.jsonl acec171884d1a47a 132177 2026-04-06T15:50:29-04:00
|
data/annotations/v2-bench/gpt-5.4.v4.4.jsonl acec171884d1a47a 132177 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/grok-4.1-fast-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/grok-4.1-fast-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/grok-4.1-fast.jsonl c0680275bea76879 164226 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/grok-4.1-fast.jsonl c0680275bea76879 164226 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/grok-rerun/grok-4.1-fast.jsonl bde4cb4fcb7eddb8 10202 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/grok-rerun/grok-4.1-fast.jsonl bde4cb4fcb7eddb8 10202 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/kimi-k2.5-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/kimi-k2.5-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/kimi-k2.5.jsonl 69dc8e24487bc308 198863 2026-04-06T15:50:29-04:00
|
data/annotations/v2-bench/kimi-k2.5.jsonl 69dc8e24487bc308 198863 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/mimo-v2-flash-errors.jsonl a41f62c2199a4a5c 12815 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/mimo-v2-flash-errors.jsonl a41f62c2199a4a5c 12815 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/mimo-v2-flash.jsonl 1e81ff86ebd6364e 95393 2026-04-06T15:50:29-04:00
|
data/annotations/v2-bench/mimo-v2-flash.jsonl 1e81ff86ebd6364e 95393 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/mimo-v2-pro:exacto-errors.jsonl 13cc28d8b7c95e66 6954 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/mimo-v2-pro:exacto-errors.jsonl 13cc28d8b7c95e66 6954 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/mimo-v2-pro:exacto.jsonl fcfe9cf05963081a 135709 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/mimo-v2-pro:exacto.jsonl fcfe9cf05963081a 135709 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/minimax-m2.7:exacto-errors.jsonl 73dc5d07828ada68 562 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/minimax-m2.7:exacto-errors.jsonl 73dc5d07828ada68 562 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/minimax-m2.7:exacto.jsonl 24d336d1dc1bd8d5 221198 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/minimax-m2.7:exacto.jsonl 24d336d1dc1bd8d5 221198 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/opus-4.6-errors.jsonl 571d4184a686ea1a 22611 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/opus-4.6-errors.jsonl 571d4184a686ea1a 22611 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/opus-4.6.jsonl 49b93441b703c009 314622 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/opus-4.6.jsonl 49b93441b703c009 314622 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/qwen3-235b-a22b-2507.jsonl 6bae2d69df93bba7 41737 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/qwen3-235b-a22b-2507.jsonl 6bae2d69df93bba7 41737 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/qwen3.5-flash-02-23-errors.jsonl d7151129d58c6603 2810 2026-04-06T15:50:29-04:00
|
data/annotations/v2-bench/qwen3.5-flash-02-23-errors.jsonl d7151129d58c6603 2810 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/qwen3.5-flash-02-23.jsonl b70635222e981c16 15548 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/qwen3.5-flash-02-23.jsonl b70635222e981c16 15548 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/seed-1.6-flash.jsonl d4b9772675c80b69 32319 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/seed-1.6-flash.jsonl d4b9772675c80b69 32319 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-bench/v45-test/gpt-5.4.jsonl 611356d785c78351 10255 2026-04-06T15:50:30-04:00
|
data/annotations/v2-bench/v45-test/gpt-5.4.jsonl 611356d785c78351 10255 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/consensus.jsonl e17c36e9d9dc5013 5134699 2026-04-06T15:50:29-04:00
|
data/annotations/v2-stage1/consensus.jsonl e17c36e9d9dc5013 5134699 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/dataset_dict.json c12b7d448ef66f58 42 2026-04-06T15:50:29-04:00
|
data/annotations/v2-stage1/grok-4.1-fast.run1-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/test/cache-c4785d17222d453a.arrow 96c71a55a44c7aba 607370 2026-04-06T15:50:29-04:00
|
data/annotations/v2-stage1/grok-4.1-fast.run1.jsonl 14cec0b5494bd421 8012148 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/test/data-00000-of-00001.arrow 95a83d5b8f9be95d 602094 2026-04-06T15:50:29-04:00
|
data/annotations/v2-stage1/grok-4.1-fast.run2-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/test/dataset_info.json 77ad4f3297dfe866 206 2026-04-06T15:50:29-04:00
|
data/annotations/v2-stage1/grok-4.1-fast.run2.jsonl af8cdff93948895f 8022743 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/test/state.json 2cb29c5ad9d17486 171 2026-04-06T15:50:30-04:00
|
data/annotations/v2-stage1/grok-4.1-fast.run3-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/train/cache-5355f45235674123.arrow 372dd433852605a3 3994160 2026-04-06T15:50:30-04:00
|
data/annotations/v2-stage1/grok-4.1-fast.run3.jsonl 669457d629de44b2 8002607 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/train/data-00000-of-00001.arrow 1f7abc955e25da83 3990243 2026-04-06T15:50:30-04:00
|
data/annotations/v2-stage1/judge.jsonl b5d7459d9431007f 50908 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/train/dataset_info.json 77ad4f3297dfe866 206 2026-04-06T15:50:30-04:00
|
data/bench/bytedance-seed_seed-2.0-lite.jsonl dc8bad7bde94659e 52855 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/.finetune_data_cache/train/state.json 52628c28a837c786 168 2026-04-06T15:50:30-04:00
|
data/bench/bytedance-seed_seed-2.0-lite.report.json 048616bb5fde6f9b 382 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/grok-4.1-fast.run1-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:50:29-04:00
|
data/bench/judges/anthropic_claude-sonnet-4.6.jsonl f1fd26ebf4fec150 13964 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/grok-4.1-fast.run1.jsonl 14cec0b5494bd421 8012148 2026-04-06T15:50:29-04:00
|
data/bench/judges/anthropic_claude-sonnet-4.6.report.json c2bb4a24fcd82483 234 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/grok-4.1-fast.run2-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:50:30-04:00
|
data/bench/judges/disagreements.json 7dee81e954b19982 7930 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/grok-4.1-fast.run2.jsonl af8cdff93948895f 8022743 2026-04-06T15:50:30-04:00
|
data/bench/judges/gold-adjudicated.json 325eeaa00041d5c4 2961 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/grok-4.1-fast.run3-errors.jsonl 2d06800538d394c2 13 2026-04-06T15:50:29-04:00
|
data/bench/judges/gold-a.json 39ecee3541d0ff60 3654 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/grok-4.1-fast.run3.jsonl 669457d629de44b2 8002607 2026-04-06T15:50:29-04:00
|
data/bench/judges/gold-b.json 8087e1eae3e29348 4230 2026-04-06T15:53:02-04:00
|
||||||
data/annotations/v2-stage1/judge.jsonl b5d7459d9431007f 50908 2026-04-06T15:50:30-04:00
|
data/bench/judges/gold-c.json 11549b51203a67d6 6215 2026-04-06T15:53:02-04:00
|
||||||
data/bench/bytedance-seed_seed-2.0-lite.jsonl dc8bad7bde94659e 52855 2026-04-06T15:50:29-04:00
|
data/bench/judges/gold-final.json 9620f5687b1266c0 1293 2026-04-06T15:53:02-04:00
|
||||||
data/bench/bytedance-seed_seed-2.0-lite.report.json 048616bb5fde6f9b 382 2026-04-06T15:50:29-04:00
|
data/bench/judges/gold-input.json 0daf776a85425ae4 21630 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/anthropic_claude-sonnet-4.6.jsonl f1fd26ebf4fec150 13964 2026-04-06T15:50:29-04:00
|
data/bench/judges/google_gemini-3-flash-preview.jsonl b47a66f8a9f0e163 8652 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/anthropic_claude-sonnet-4.6.report.json c2bb4a24fcd82483 234 2026-04-06T15:50:29-04:00
|
data/bench/judges/google_gemini-3-flash-preview.report.json f53de9a8b9d611e6 238 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/disagreements.json 7dee81e954b19982 7930 2026-04-06T15:50:29-04:00
|
data/bench/judges/judge-sample.jsonl f9d0b0dac42ce369 1036 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/gold-adjudicated.json 325eeaa00041d5c4 2961 2026-04-06T15:50:29-04:00
|
data/bench/judges/moonshotai_kimi-k2.5.jsonl 66f8782b6354faad 8629 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/gold-a.json 39ecee3541d0ff60 3654 2026-04-06T15:50:29-04:00
|
data/bench/judges/openai_gpt-5.4.jsonl c667e182380c52ba 9761 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/gold-b.json 8087e1eae3e29348 4230 2026-04-06T15:50:29-04:00
|
data/bench/judges/openai_gpt-5.4-mini.jsonl b00f8f8e5044df80 10086 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/gold-c.json 11549b51203a67d6 6215 2026-04-06T15:50:30-04:00
|
data/bench/judges/openai_gpt-5.4-mini.report.json 8818cd966d1e6539 326 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/gold-final.json 9620f5687b1266c0 1293 2026-04-06T15:50:30-04:00
|
data/bench/judges/openai_gpt-5.4-mini.v1-baseline.jsonl 6414d689ba8e3e35 8537 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/gold-input.json 0daf776a85425ae4 21630 2026-04-06T15:50:30-04:00
|
data/bench/judges/openai_gpt-5.4-mini.v1-baseline.report.json 12b5195e24a47017 224 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/google_gemini-3-flash-preview.jsonl b47a66f8a9f0e163 8652 2026-04-06T15:50:30-04:00
|
data/bench/judges/openai_gpt-5.4.report.json cc4fdd98be32727c 225 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/google_gemini-3-flash-preview.report.json f53de9a8b9d611e6 238 2026-04-06T15:50:30-04:00
|
data/bench/judges/x-ai_grok-4.20-beta.jsonl d23dc0c7af532e81 10257 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/judge-sample.jsonl f9d0b0dac42ce369 1036 2026-04-06T15:50:29-04:00
|
data/bench/judges/x-ai_grok-4.20-beta.report.json 68545585888c3085 229 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/moonshotai_kimi-k2.5.jsonl 66f8782b6354faad 8629 2026-04-06T15:50:29-04:00
|
data/bench/judges/xiaomi_mimo-v2-pro.jsonl b0b04e2c09eae38d 7914 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/openai_gpt-5.4.jsonl c667e182380c52ba 9761 2026-04-06T15:50:30-04:00
|
data/bench/judges/xiaomi_mimo-v2-pro.report.json e3baad5bbb63f92e 230 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/openai_gpt-5.4-mini.jsonl b00f8f8e5044df80 10086 2026-04-06T15:50:29-04:00
|
data/bench/judges/z-ai_glm-5.jsonl edb530666db4e0db 12029 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/openai_gpt-5.4-mini.report.json 8818cd966d1e6539 326 2026-04-06T15:50:29-04:00
|
data/bench/judges/z-ai_glm-5.report.json 7b43e4799fce7031 332 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/openai_gpt-5.4-mini.v1-baseline.jsonl 6414d689ba8e3e35 8537 2026-04-06T15:50:29-04:00
|
data/bench/judges/z-ai_glm-5.v1-baseline.jsonl 612da087189b9a69 9655 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/openai_gpt-5.4-mini.v1-baseline.report.json 12b5195e24a47017 224 2026-04-06T15:50:30-04:00
|
data/bench/judges/z-ai_glm-5.v1-baseline.report.json 46ad665c2507d6e9 230 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/openai_gpt-5.4.report.json cc4fdd98be32727c 225 2026-04-06T15:50:29-04:00
|
data/bench/judges/z-ai_glm-5.v2-structured.jsonl 29319e94abf51d16 13358 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/x-ai_grok-4.20-beta.jsonl d23dc0c7af532e81 10257 2026-04-06T15:50:29-04:00
|
data/bench/judges/z-ai_glm-5.v2-structured.report.json d5217fc845ac312c 328 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/x-ai_grok-4.20-beta.report.json 68545585888c3085 229 2026-04-06T15:50:29-04:00
|
data/bench/judges/z-ai_glm-5.v3-toolcalling.jsonl 197196b9e66bf970 9957 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/xiaomi_mimo-v2-pro.jsonl b0b04e2c09eae38d 7914 2026-04-06T15:50:30-04:00
|
data/bench/judges/z-ai_glm-5.v3-toolcalling.report.json 509d59ded0584dd4 325 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/xiaomi_mimo-v2-pro.report.json e3baad5bbb63f92e 230 2026-04-06T15:50:30-04:00
|
data/bench/minimax_minimax-m2.5.jsonl 32c5ff26e28701ae 67861 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.jsonl edb530666db4e0db 12029 2026-04-06T15:50:30-04:00
|
data/bench/minimax_minimax-m2.5.report.json ecc5f631c86325d1 369 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.report.json 7b43e4799fce7031 332 2026-04-06T15:50:30-04:00
|
data/bench/mistralai_mistral-small-2603.jsonl b7aaa4b22509d7e6 50883 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.v1-baseline.jsonl 612da087189b9a69 9655 2026-04-06T15:50:29-04:00
|
data/bench/mistralai_mistral-small-2603.report.json e52c5a5b241db435 361 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.v1-baseline.report.json 46ad665c2507d6e9 230 2026-04-06T15:50:30-04:00
|
data/bench/nvidia_nemotron-3-super-120b-a12b.jsonl bea808613ed82726 60277 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.v2-structured.jsonl 29319e94abf51d16 13358 2026-04-06T15:50:29-04:00
|
data/bench/nvidia_nemotron-3-super-120b-a12b.report.json dd33cf60c0250798 380 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.v2-structured.report.json d5217fc845ac312c 328 2026-04-06T15:50:30-04:00
|
data/bench/xiaomi_mimo-v2-flash.jsonl b4a101e5350b6668 52898 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.v3-toolcalling.jsonl 197196b9e66bf970 9957 2026-04-06T15:50:29-04:00
|
data/bench/xiaomi_mimo-v2-flash.report.json ced1ffcd4066c1d2 369 2026-04-06T15:53:02-04:00
|
||||||
data/bench/judges/z-ai_glm-5.v3-toolcalling.report.json 509d59ded0584dd4 325 2026-04-06T15:50:30-04:00
|
data/bench/z-ai_glm-4.5-air.jsonl dd0786e4cc575354 50195 2026-04-06T15:53:02-04:00
|
||||||
data/bench/minimax_minimax-m2.5.jsonl 32c5ff26e28701ae 67861 2026-04-06T15:50:30-04:00
|
data/bench/z-ai_glm-4.5-air.report.json 8a062136ce5204a7 367 2026-04-06T15:53:02-04:00
|
||||||
data/bench/minimax_minimax-m2.5.report.json ecc5f631c86325d1 369 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-000.jsonl 51f94f05ee193fc5 42029481 2026-04-06T15:53:02-04:00
|
||||||
data/bench/mistralai_mistral-small-2603.jsonl b7aaa4b22509d7e6 50883 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-001.jsonl 47694862f087dc97 48796003 2026-04-06T15:53:02-04:00
|
||||||
data/bench/mistralai_mistral-small-2603.report.json e52c5a5b241db435 361 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-002.jsonl 16f7d345cb0e2e3e 59824120 2026-04-06T15:53:02-04:00
|
||||||
data/bench/nvidia_nemotron-3-super-120b-a12b.jsonl bea808613ed82726 60277 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-003.jsonl 544f29f612583f46 50200580 2026-04-06T15:53:02-04:00
|
||||||
data/bench/nvidia_nemotron-3-super-120b-a12b.report.json dd33cf60c0250798 380 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-004.jsonl 1b702fe9e09b18b1 30977355 2026-04-06T15:53:02-04:00
|
||||||
data/bench/xiaomi_mimo-v2-flash.jsonl b4a101e5350b6668 52898 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-005.jsonl 51a3965fe8fd195b 41153794 2026-04-06T15:53:02-04:00
|
||||||
data/bench/xiaomi_mimo-v2-flash.report.json ced1ffcd4066c1d2 369 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-006.jsonl b1ba25f4763746cf 47585910 2026-04-06T15:53:02-04:00
|
||||||
data/bench/z-ai_glm-4.5-air.jsonl dd0786e4cc575354 50195 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-007.jsonl daf238d703a61d31 46349482 2026-04-06T15:53:02-04:00
|
||||||
data/bench/z-ai_glm-4.5-air.report.json 8a062136ce5204a7 367 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-008.jsonl d2894ed0b521cbed 39324191 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-000.jsonl 51f94f05ee193fc5 42029481 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-009.jsonl 6421e1e946832e63 56200667 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-001.jsonl 47694862f087dc97 48796003 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-010.jsonl 02049ca9a1f7c0b2 55309009 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-002.jsonl 16f7d345cb0e2e3e 59824120 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-011.jsonl 3523e9e67a92ccdb 48628875 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-003.jsonl 544f29f612583f46 50200580 2026-04-06T15:50:29-04:00
|
data/dapt-corpus/shard-012.jsonl 140247cc3a597c64 43126961 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-004.jsonl 1b702fe9e09b18b1 30977355 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-013.jsonl 2f765a955ade0195 20972632 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-005.jsonl 51a3965fe8fd195b 41153794 2026-04-06T15:50:30-04:00
|
data/dapt-corpus/shard-014.jsonl 0c4ab7d2286e8ff3 13205532 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-006.jsonl b1ba25f4763746cf 47585910 2026-04-06T15:50:29-04:00
|
data/gold/annotators.json 23bff763a2f2106e 216 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-007.jsonl daf238d703a61d31 46349482 2026-04-06T15:50:30-04:00
|
data/gold/charts/01_kappa_heatmaps.png 14f53079f9d86e82 102360 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-008.jsonl d2894ed0b521cbed 39324191 2026-04-06T15:50:29-04:00
|
data/gold/charts/02_category_distribution_all.png 578c9243b0dfa2e4 77798 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-009.jsonl 6421e1e946832e63 56200667 2026-04-06T15:50:29-04:00
|
data/gold/charts/02_category_distribution.png b4438d832c1facc7 51544 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-010.jsonl 02049ca9a1f7c0b2 55309009 2026-04-06T15:50:30-04:00
|
data/gold/charts/03_specificity_distribution_all.png 14cb589482bb70a2 79373 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-011.jsonl 3523e9e67a92ccdb 48628875 2026-04-06T15:50:29-04:00
|
data/gold/charts/03_specificity_distribution.png a553171a235c1b2c 51737 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-012.jsonl 140247cc3a597c64 43126961 2026-04-06T15:50:30-04:00
|
data/gold/charts/04_human_confusion.png 260a2289d64e492e 65851 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-013.jsonl 2f765a955ade0195 20972632 2026-04-06T15:50:29-04:00
|
data/gold/charts/05_cross_source_category.png db9d72c8e9f13dbc 31295 2026-04-06T15:53:02-04:00
|
||||||
data/dapt-corpus/shard-014.jsonl 0c4ab7d2286e8ff3 13205532 2026-04-06T15:50:30-04:00
|
data/gold/charts/05_genai_agreement_matrix.png b0119c9e50caf8b5 157570 2026-04-06T15:53:02-04:00
|
||||||
data/gold/annotators.json 23bff763a2f2106e 216 2026-04-06T15:50:30-04:00
|
data/gold/charts/06_cross_source_category.png 6eecda054587ea03 66073 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/01_kappa_heatmaps.png 14f53079f9d86e82 102360 2026-04-06T15:50:29-04:00
|
data/gold/charts/06_cross_source_specificity.png c7e338a6b560b433 24181 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/02_category_distribution_all.png 578c9243b0dfa2e4 77798 2026-04-06T15:50:30-04:00
|
data/gold/charts/07_annotator_vs_references.png 713e961b4e87450b 45022 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/02_category_distribution.png b4438d832c1facc7 51544 2026-04-06T15:50:30-04:00
|
data/gold/charts/07_cross_source_specificity.png 808c745b09ba0812 51415 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/03_specificity_distribution_all.png 14cb589482bb70a2 79373 2026-04-06T15:50:30-04:00
|
data/gold/charts/08_adjudication_tiers.png 0e9adb495cf05a70 66328 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/03_specificity_distribution.png a553171a235c1b2c 51737 2026-04-06T15:50:30-04:00
|
data/gold/charts/08_agreement_by_wordcount.png 8dbb6c16746443e5 41417 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/04_human_confusion.png 260a2289d64e492e 65851 2026-04-06T15:50:29-04:00
|
data/gold/charts/09_model_accuracy_vs_opus.png 04c443366a6a7ca2 70132 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/05_cross_source_category.png db9d72c8e9f13dbc 31295 2026-04-06T15:50:30-04:00
|
data/gold/charts/09_time_vs_agreement.png dd0d4cd29c8310bf 40983 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/05_genai_agreement_matrix.png b0119c9e50caf8b5 157570 2026-04-06T15:50:30-04:00
|
data/gold/charts/10_cost_vs_accuracy.png 0e5623062a10057e 62786 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/06_cross_source_category.png 6eecda054587ea03 66073 2026-04-06T15:50:29-04:00
|
data/gold/charts/10_none_other_analysis.png 0822d42de7b3b235 37207 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/06_cross_source_specificity.png c7e338a6b560b433 24181 2026-04-06T15:50:29-04:00
|
data/gold/charts/11_outlier_annotator.png 4b6b56278cc1c9bb 39742 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/07_annotator_vs_references.png 713e961b4e87450b 45022 2026-04-06T15:50:30-04:00
|
data/gold/charts/11_per_category_accuracy.png 6b73b2a1647ca49e 98929 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/07_cross_source_specificity.png 808c745b09ba0812 51415 2026-04-06T15:50:29-04:00
|
data/gold/charts/12_ensemble_accuracy.png 0daf85041839cf1b 57776 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/08_adjudication_tiers.png 0e9adb495cf05a70 66328 2026-04-06T15:50:30-04:00
|
data/gold/charts/12_human_vs_genai_consensus.png 0691dd402878024b 64060 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/08_agreement_by_wordcount.png 8dbb6c16746443e5 41417 2026-04-06T15:50:29-04:00
|
data/gold/charts/13_agreement_by_wordcount.png 31d460ae03f4c4ce 50997 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/09_model_accuracy_vs_opus.png 04c443366a6a7ca2 70132 2026-04-06T15:50:30-04:00
|
data/gold/charts/13_specificity_bias.png a7c0f9ec19fcf84d 47231 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/09_time_vs_agreement.png dd0d4cd29c8310bf 40983 2026-04-06T15:50:30-04:00
|
data/gold/charts/14_disagreement_axes.png 4fbf5da38e54b8eb 46339 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/10_cost_vs_accuracy.png 0e5623062a10057e 62786 2026-04-06T15:50:29-04:00
|
data/gold/charts/14_time_vs_agreement.png 044672584ddf135e 42593 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/10_none_other_analysis.png 0822d42de7b3b235 37207 2026-04-06T15:50:30-04:00
|
data/gold/charts/15_outlier_annotator.png 83ca085e779e1b0c 32827 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/11_outlier_annotator.png 4b6b56278cc1c9bb 39742 2026-04-06T15:50:29-04:00
|
data/gold/charts/15_quiz_vs_quality.png 52ae938872b80537 53319 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/11_per_category_accuracy.png 6b73b2a1647ca49e 98929 2026-04-06T15:50:29-04:00
|
data/gold/charts/16_with_without_outlier.png fbab8eb884a40e57 65080 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/12_ensemble_accuracy.png 0daf85041839cf1b 57776 2026-04-06T15:50:29-04:00
|
data/gold/charts/17_disagreement_axes.png 940927f1bdb156dc 49858 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/12_human_vs_genai_consensus.png 0691dd402878024b 64060 2026-04-06T15:50:30-04:00
|
data/gold/charts/18_none_other_analysis.png 2ffeeccdc3cadfc7 37539 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/13_agreement_by_wordcount.png 31d460ae03f4c4ce 50997 2026-04-06T15:50:29-04:00
|
data/gold/charts/19_specificity_bias_all.png b03a14efe8abbbdd 77943 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/13_specificity_bias.png a7c0f9ec19fcf84d 47231 2026-04-06T15:50:30-04:00
|
data/gold/charts/20_quiz_vs_quality.png c00b1d4c81b9e9ce 50648 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/14_disagreement_axes.png 4fbf5da38e54b8eb 46339 2026-04-06T15:50:29-04:00
|
data/gold/charts/21_human_vs_genai_consensus.png 1897cd93299b882a 51587 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/14_time_vs_agreement.png 044672584ddf135e 42593 2026-04-06T15:50:29-04:00
|
data/gold/charts/22_signal_agreement_dist.png a6dd2e6dfd70d374 56609 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/15_outlier_annotator.png 83ca085e779e1b0c 32827 2026-04-06T15:50:29-04:00
|
data/gold/charts/23_annotator_vs_references.png d891eb9e18ccf6a2 44124 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/15_quiz_vs_quality.png 52ae938872b80537 53319 2026-04-06T15:50:30-04:00
|
data/gold/charts/24_hard_paragraphs.png 303fbd4e993eb82c 261294 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/16_with_without_outlier.png fbab8eb884a40e57 65080 2026-04-06T15:50:30-04:00
|
data/gold/charts/25_model_vs_human_per_category.png f9ad740001ef0622 97278 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/17_disagreement_axes.png 940927f1bdb156dc 49858 2026-04-06T15:50:30-04:00
|
data/gold/charts/26_prompt_version_effect.png 7e39ba2f577278b2 77437 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/18_none_other_analysis.png 2ffeeccdc3cadfc7 37539 2026-04-06T15:50:30-04:00
|
data/gold/charts/27_conditional_agreement.png c6de99b305f627ce 56635 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/19_specificity_bias_all.png b03a14efe8abbbdd 77943 2026-04-06T15:50:30-04:00
|
data/gold/charts/28_model_clustering.png d624f73bcdf8178d 124924 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/20_quiz_vs_quality.png c00b1d4c81b9e9ce 50648 2026-04-06T15:50:29-04:00
|
data/gold/charts/29_spec_calibration.png 0c4e839192edec90 147385 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/21_human_vs_genai_consensus.png 1897cd93299b882a 51587 2026-04-06T15:50:29-04:00
|
data/gold/charts/30_latency_vs_accuracy.png 05233f152a3fdbe9 58876 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/22_signal_agreement_dist.png a6dd2e6dfd70d374 56609 2026-04-06T15:50:29-04:00
|
data/gold/charts/gold-adjudication-overview.png f2a1f6951d1a2a31 99582 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/23_annotator_vs_references.png d891eb9e18ccf6a2 44124 2026-04-06T15:50:30-04:00
|
data/gold/charts/gold-category-shift.png d3812cdd947bdcbf 47937 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/24_hard_paragraphs.png 303fbd4e993eb82c 261294 2026-04-06T15:50:30-04:00
|
data/gold/charts/gold-t5-analysis.png 7b4e921701461b16 82995 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/25_model_vs_human_per_category.png f9ad740001ef0622 97278 2026-04-06T15:50:29-04:00
|
data/gold/charts/gold-tier-source.png 48bf298bf1da444e 29803 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/26_prompt_version_effect.png 7e39ba2f577278b2 77437 2026-04-06T15:50:29-04:00
|
data/gold/charts/gold-v1-v2-comparison.png 42597924f25ceefd 61014 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/27_conditional_agreement.png c6de99b305f627ce 56635 2026-04-06T15:50:29-04:00
|
data/gold/gold-adjudicated.jsonl 86f70006fcef7a20 32100 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/28_model_clustering.png d624f73bcdf8178d 124924 2026-04-06T15:50:29-04:00
|
data/gold/holdout-rerun-v35b.jsonl 8090e63f750d95c8 589 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/29_spec_calibration.png 0c4e839192edec90 147385 2026-04-06T15:50:29-04:00
|
data/gold/holdout-rerun-v35.jsonl d68711d6ed2420b9 9018 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/30_latency_vs_accuracy.png 05233f152a3fdbe9 58876 2026-04-06T15:50:29-04:00
|
data/gold/human-labels-aaryan-v1.jsonl e6d0bb72bc2fa4d4 20631 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/gold-adjudication-overview.png f2a1f6951d1a2a31 99582 2026-04-06T15:50:30-04:00
|
data/gold/human-labels-raw.jsonl 4c2c393723e983a0 86753 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/gold-category-shift.png d3812cdd947bdcbf 47937 2026-04-06T15:50:30-04:00
|
data/gold/metrics.json 700cfac67fbe1044 1664 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/gold-t5-analysis.png 7b4e921701461b16 82995 2026-04-06T15:50:30-04:00
|
data/gold/opus-to-db-id-map.json 84301dc96bb926d3 28940 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/gold-tier-source.png 48bf298bf1da444e 29803 2026-04-06T15:50:29-04:00
|
data/gold/paragraphs-holdout.jsonl 81a9426214bb334f 6055010 2026-04-06T15:53:02-04:00
|
||||||
data/gold/charts/gold-v1-v2-comparison.png 42597924f25ceefd 61014 2026-04-06T15:50:30-04:00
|
data/gold/quiz-sessions.jsonl bd8dfa57cd36c979 2962 2026-04-06T15:53:02-04:00
|
||||||
data/gold/gold-adjudicated.jsonl 86f70006fcef7a20 32100 2026-04-06T15:50:30-04:00
|
data/gold/regression-pids.json c64ed5c4b1885337 670 2026-04-06T15:53:02-04:00
|
||||||
data/gold/holdout-rerun-v35b.jsonl 8090e63f750d95c8 589 2026-04-06T15:50:30-04:00
|
data/gold/v2-holdout-ids.json bd9545ef0c3d5347 21951 2026-04-06T15:53:02-04:00
|
||||||
data/gold/holdout-rerun-v35.jsonl d68711d6ed2420b9 9018 2026-04-06T15:50:30-04:00
|
data/gold/v2-holdout-manifest.jsonl e03bd04c938ef6f5 81455 2026-04-06T15:53:02-04:00
|
||||||
data/gold/human-labels-aaryan-v1.jsonl e6d0bb72bc2fa4d4 20631 2026-04-06T15:50:30-04:00
|
data/gold/v45-test-ids.json 6e7411bf0af3289f 1037 2026-04-06T15:53:02-04:00
|
||||||
data/gold/human-labels-raw.jsonl 4c2c393723e983a0 86753 2026-04-06T15:50:30-04:00
|
data/paragraphs/paragraphs-8k.jsonl b05d63ed3ff8fd06 32140 2026-04-06T15:53:02-04:00
|
||||||
data/gold/metrics.json 700cfac67fbe1044 1664 2026-04-06T15:50:30-04:00
|
data/paragraphs/paragraphs-clean.jsonl 93c892cda940cc80 6412741 2026-04-06T15:53:02-04:00
|
||||||
data/gold/opus-to-db-id-map.json 84301dc96bb926d3 28940 2026-04-06T15:50:30-04:00
|
data/paragraphs/paragraphs-clean.patched.jsonl 3b1e7f2b8170fd16 6418159 2026-04-06T15:53:02-04:00
|
||||||
data/gold/paragraphs-holdout.jsonl 81a9426214bb334f 6055010 2026-04-06T15:50:30-04:00
|
data/paragraphs/paragraphs.jsonl 559f215d9de29347 6410094 2026-04-06T15:53:02-04:00
|
||||||
data/gold/quiz-sessions.jsonl bd8dfa57cd36c979 2962 2026-04-06T15:50:29-04:00
|
data/paragraphs/paragraphs.patched.jsonl 6d5b26c913dc0315 6412390 2026-04-06T15:53:02-04:00
|
||||||
data/gold/regression-pids.json c64ed5c4b1885337 670 2026-04-06T15:50:30-04:00
|
data/paragraphs/paragraphs-processed.jsonl fcb75c63f40cc5f4 78111 2026-04-06T15:53:02-04:00
|
||||||
data/gold/v2-holdout-ids.json bd9545ef0c3d5347 21951 2026-04-06T15:50:30-04:00
|
data/paragraphs/patches/colon-heading-patches.jsonl 40935e0b22d1a1a4 13136 2026-04-06T15:53:02-04:00
|
||||||
data/gold/v2-holdout-manifest.jsonl e03bd04c938ef6f5 81455 2026-04-06T15:50:29-04:00
|
data/paragraphs/patches/heading-strip-html-patches.jsonl 14791076d34ae050 14784 2026-04-06T15:53:02-04:00
|
||||||
data/gold/v45-test-ids.json 6e7411bf0af3289f 1037 2026-04-06T15:50:30-04:00
|
data/paragraphs/patches/heading-strip-patches.jsonl baf4143b90081c6c 208237 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/paragraphs-8k.jsonl b05d63ed3ff8fd06 32140 2026-04-06T15:50:29-04:00
|
data/paragraphs/patches/heading-strip-v2-patches.jsonl ff364a1b9407ec64 7914 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/paragraphs-clean.jsonl 93c892cda940cc80 6412741 2026-04-06T15:50:30-04:00
|
data/paragraphs/patches/orphan-word-patches.jsonl eaebac43e2b30b42 84381 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/paragraphs-clean.patched.jsonl 3b1e7f2b8170fd16 6418159 2026-04-06T15:50:30-04:00
|
data/paragraphs/quality/ambiguous-filings.txt f07b50e143d6b933 16449 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/paragraphs.jsonl 559f215d9de29347 6410094 2026-04-06T15:50:29-04:00
|
data/paragraphs/quality/filing-headings.jsonl 946a5237f408995a 48460 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/paragraphs.patched.jsonl 6d5b26c913dc0315 6412390 2026-04-06T15:50:30-04:00
|
data/paragraphs/quality/generator-tags.jsonl 5b5c75587e6fd726 43156 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/paragraphs-processed.jsonl fcb75c63f40cc5f4 78111 2026-04-06T15:50:30-04:00
|
data/paragraphs/quality/quality-scores.jsonl 0f335ec332b0ecf0 1543336 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/patches/colon-heading-patches.jsonl 40935e0b22d1a1a4 13136 2026-04-06T15:50:30-04:00
|
data/paragraphs/training.jsonl 41fe844c9887082c 5501536 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/patches/heading-strip-html-patches.jsonl 14791076d34ae050 14784 2026-04-06T15:50:29-04:00
|
data/paragraphs/training.patched.jsonl be909f24b3b810c3 6349423 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/patches/heading-strip-patches.jsonl baf4143b90081c6c 208237 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-mimo-flash.jsonl b4a101e5350b6668 52898 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/patches/heading-strip-v2-patches.jsonl ff364a1b9407ec64 7914 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-report-v2.2.txt 2b24d63888f716a8 58701 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/patches/orphan-word-patches.jsonl eaebac43e2b30b42 84381 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-report-v2.3.txt 0b2f59144b6722ef 51796 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/quality/ambiguous-filings.txt f07b50e143d6b933 16449 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-report-v2.4.txt 1e7406efa571e86a 43023 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/quality/filing-headings.jsonl 946a5237f408995a 48460 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-report-v2.5.txt 848da5501833be65 38987 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/quality/generator-tags.jsonl 5b5c75587e6fd726 43156 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-report-v2.6.txt 2896f27d5285db2c 42711 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/quality/quality-scores.jsonl 0f335ec332b0ecf0 1543336 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-report-v2.7.txt eecbdbf50245e400 42104 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/training.jsonl 41fe844c9887082c 5501536 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-results.jsonl 642405cef676c776 16515 2026-04-06T15:53:02-04:00
|
||||||
data/paragraphs/training.patched.jsonl be909f24b3b810c3 6349423 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-results-v1.1.jsonl 27e47027e59b0ade 16441 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-mimo-flash.jsonl b4a101e5350b6668 52898 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-results-v1.2.jsonl 1904cdbc3eca363b 16431 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-report-v2.2.txt 2b24d63888f716a8 58701 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-results-v2.1.jsonl c3c25b46f8474454 14212 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-report-v2.3.txt 0b2f59144b6722ef 51796 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-results-v2.2.jsonl d4fb7b32ec04621b 143040 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-report-v2.4.txt 1e7406efa571e86a 43023 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-results-v2.2-n40.jsonl 8b412ad86890098f 14757 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-report-v2.5.txt 848da5501833be65 38987 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-results-v2.3.jsonl 5a3d1717d4d7d5ff 143936 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-report-v2.6.txt 2896f27d5285db2c 42711 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-results-v2.4.jsonl d8a4cc8ec0699e86 141156 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-report-v2.7.txt eecbdbf50245e400 42104 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-results-v2.5.jsonl 8caad5176a378658 141036 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results.jsonl 642405cef676c776 16515 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-results-v2.6.jsonl 8c81e50c6fde2d3c 142293 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v1.1.jsonl 27e47027e59b0ade 16441 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-results-v2.7.jsonl a5b08496dc881304 140259 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v1.2.jsonl 1904cdbc3eca363b 16431 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-sample.jsonl b5edcb6420ed1727 14048 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.1.jsonl c3c25b46f8474454 14212 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-sample-v2.2.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.2.jsonl d4fb7b32ec04621b 143040 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-sample-v2.3.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.2-n40.jsonl 8b412ad86890098f 14757 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-sample-v2.4.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.3.jsonl 5a3d1717d4d7d5ff 143936 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-sample-v2.5.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.4.jsonl d8a4cc8ec0699e86 141156 2026-04-06T15:50:30-04:00
|
data/pilot/pilot-sample-v2.6.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.5.jsonl 8caad5176a378658 141036 2026-04-06T15:50:29-04:00
|
data/pilot/pilot-sample-v2.7.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:53:02-04:00
|
||||||
data/pilot/pilot-results-v2.6.jsonl 8c81e50c6fde2d3c 142293 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-results-v2.7.jsonl a5b08496dc881304 140259 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-sample.jsonl b5edcb6420ed1727 14048 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-sample-v2.2.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:50:29-04:00
|
|
||||||
data/pilot/pilot-sample-v2.3.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-sample-v2.4.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-sample-v2.5.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-sample-v2.6.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:50:30-04:00
|
|
||||||
data/pilot/pilot-sample-v2.7.jsonl 1a09bf3a0619960d 107910 2026-04-06T15:50:30-04:00
|
|
||||||
# Generated by scripts/data-push.sh — do not edit manually
|
# Generated by scripts/data-push.sh — do not edit manually
|
||||||
# .lfs-manifest — path, xxh3, compressed_bytes, timestamp
|
# .lfs-manifest — path, xxh3, compressed_bytes, timestamp
|
||||||
|
|||||||
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/dataset_dict.json.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/dataset_dict.json.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/cache-c4785d17222d453a.arrow.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/cache-c4785d17222d453a.arrow.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/data-00000-of-00001.arrow.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/data-00000-of-00001.arrow.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/dataset_info.json.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/dataset_info.json.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/state.json.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/test/state.json.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/cache-5355f45235674123.arrow.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/cache-5355f45235674123.arrow.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/data-00000-of-00001.arrow.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/data-00000-of-00001.arrow.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/dataset_info.json.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/dataset_info.json.zst
(Stored with Git LFS)
Binary file not shown.
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/state.json.zst
(Stored with Git LFS)
BIN
.lfs-store/data/annotations/v2-stage1/.finetune_data_cache/train/state.json.zst
(Stored with Git LFS)
Binary file not shown.
Loading…
x
Reference in New Issue
Block a user