Spaces:
Running
Running
| fbc9d05f2ac88afcd89a9bc02eb66fb63d8640e3cef6926a88a247a46a9ba09b README.md | |
| 0b30ba55bacd444c300ed9b60f032db63c3dd43578532aefdfbc2b036cdfda8e UPLOAD_ALLOWLIST.txt | |
| 87e2be07b2fbcca08d414287fd263dcd4f65e12a81db13504ced98b0b5c9ab20 code/claim4_exact_gate.py | |
| 805ccc2fa6c8713add8aa7d0a033f6fd49024e19f792b47c913a33d00a130b30 code/claim5_exact_gate.py | |
| 2928d876f0ab83b84b98883c1611a583f6bf180e215ee4fec8221b4a1ee56f80 code/run_campaign.py | |
| 98c2c405a81ee5b2ac72ec0bc5db5f342f209b3308143816c70e77852f118198 code/verify_candidate_space.py | |
| 8ad8643e580c5db898181e6f71dde59e0927f11a53971ed8e7fa78b844299768 code/verify_claim4_audit.py | |
| 1a143e8c823e7d502ffbfc9694abaec99b10044dac78665db314cf58d9b35532 code/verify_claim4_final.py | |
| f424d02838fdc551d32baee4558f4fa3941033b4f43fb919aac5a38cd11b7119 code/verify_claim5_audit.py | |
| 5c435b918103ac979d8e521272dd3a98a0d063f7690a61b5a06d1519d51c256f code/verify_claim5_final.py | |
| 4448bbfbb3cb8bb1585309669b3d8a437c59b2e72e3a514ef2e586ca16d515fb code/verify_cumulative.py | |
| 5753cda80c9d161bf4a146b0455bd436061b1f4f8f29dde2f5725048975f58d1 code/verify_cumulative_space.py | |
| 9f86516f3761dede165fdab9c4b5d37a5647e1c70d1c03d8c6b44c9397f6d129 code/verify_space_release.py | |
| 7b55f8e67b5623c4bef3fa691288da9437d79d3aba156de48d481db32ac7d16d environment/.python-version | |
| 6e68a8b82e20775a6630629e8eed46320dc9764dc49b352494137f7c7819dcb8 environment/pyproject.toml | |
| 70c5e58a019f7a3101ece3b72baf454fce3903014736416797920f2a87b5b067 environment/uv.lock | |
| 3041d045c6aeee94048640a3022f05e2a5dfb59a688ed72c19534761cb7ccd45 evidence/claim4/EVAL.md | |
| 9562f5ed0625be92fd37adbde07ea4f18f0723d3823337a61e7b15648114d2f9 evidence/claim4/calibration_independent_checker_output.json | |
| a24f9db5f78942c894556e0dc69f704b15fe728f8ca5f4ffddaae9be075edbb0 evidence/claim4/claim_contract.json | |
| 9d062c854fb829f04ff3aaa2e06d6595e15d241ad397ddd903ac0e307841661b evidence/claim4/four_routes.json | |
| 1cfa008bde46c6a299dcf6d37f3912c491cb8975f1379dddab62f141cf5b94e5 evidence/claim4/limitations.md | |
| 7a1e4664215f0a80632fea7607502c87ee32424fff0c9c4a5245842ab40f36a4 evidence/claim4/method.md | |
| 253254264fd8b0e33c714fa60c99ad7582d57b4bd4068ca5fea757e2832f2530 evidence/claim4/negative_control_output.json | |
| 2a5fd5284da6dacca769a19a1b0ee23b4e76d2f09bf8bf31675a02e5bc67b20a evidence/claim4/raw_audit_output.json | |
| 57b561e79778bd300be508af341e16ffd6e87dcb8a36b4e69d42c99eb9f4ca42 evidence/claim4/raw_calibration_output.json | |
| da4cc439c535f1b029544c98a1090d178828d428728eefb85150f49aa3405598 evidence/claim4/released_audit_independent_checker_output.json | |
| 754fc772470a1eb27167deb66667c5cf090fd66dd85b784b762a93dcf60b6ffc evidence/claim4/runtime.json | |
| 817a66d4bb05c348fe962bb52853b1f5e321ba9d010786cff2c7b02db5dc15f7 evidence/claim4/source_audit.md | |
| d2ef5162f1ee621a88cba7845cb054405ceef9c125bd4aadde4cc32a07767057 evidence/claim5/EVAL.md | |
| 08cedb57d99c343281dd6eaddd594a843bef84f3324732222125a30d3e2589ff evidence/claim5/claim_contract.json | |
| e86eaa13ece1c9559fa35e67e267a0a7f47f0d1c3de913a2b49c922c62634c93 evidence/claim5/four_routes.json | |
| 3c290177888395877db099e608a8ffbf642e4c4bc1b8c222f596ae52f77c1ba5 evidence/claim5/independent_checker_output.json | |
| c540dee46a38b53c369dfd3dcc03c1e237b84cf08e4718e880b7ef6957616e8c evidence/claim5/limitations.md | |
| c83c0ce9bbb929f4c6ccda8fa9a77c71db51730ee8b1060e8e53d8d4c30fa113 evidence/claim5/method.md | |
| 05e6273f19961fe97a9bb2d3ddf20c08025e543fb133d3210d6b996f49d4ca28 evidence/claim5/negative_control_output.json | |
| b9f6bb82cd1de2c2d30d85feee301b89042c69e6cab3bbd33bcb30587ad13762 evidence/claim5/raw_audit_output.json | |
| 1fc06c96c9b8b3c5323e6e09530168124d51e600f8a497e65bdc72ff3af5906c evidence/claim5/runtime.json | |
| 5e916fc8243bee34c529ed4b430ffd876443c3e76f43c9f024ff717ab44f9940 evidence/claim5/source_audit.md | |
| 2c6179685a3f0bbb548f2f2de8959019f92a58efd0461c542dfa9f08b9223040 evidence/cumulative/EVAL.md | |
| 4e69dedd8af077c301e7fbd7952ad74dc81665803f0e374adac1575a2d61786c evidence/cumulative/apps_n40_canonical.csv | |
| c308b125870dff89027ddc0476b09fba03af87f4e17e3bac3807ff9e0cd8facc evidence/cumulative/apps_n40_canonical.json | |
| 4daa16713091c9d9b5729113d7361d8d6b741f5e80ecbf93066d0227b38d709c evidence/cumulative/apps_n40_independent_verification.json | |
| 4659c268278604331daf3c1e9e6f571be7e9955a949b6d737825e4e4986619af evidence/cumulative/claim1_source_audit.json | |
| d2064218dabca9cefb191a5bf3b7349ecb484ed9ea04d87faaeaa5367190de93 evidence/cumulative/claim1_validation.json | |
| 6db09c81c024e2968872de67274412743992194ede4dbcecc4705dfbaf247acb evidence/cumulative/claim_contract.json | |
| 96a9c72779a660d082f93bd21dbe6ac44a2ab69491f8d640c1adff7585c72a3e evidence/cumulative/codenet_independent_verification.json | |
| 593e11f76f498d2c858cbec94f2bf8b0e5bf161099efeafa69cfb6e5edf306b6 evidence/cumulative/evidence_bundle_verification.json | |
| cce8e9f7a7cce75c07356515bfe2bcadd3aaf5f246c0722ad412f8c739a7e042 evidence/cumulative/expected_output.json | |
| 7843f75c38b9ee0bf3f15d796f151808fc01a526c704f429049016d57538f390 evidence/cumulative/full_gpu_n200.csv | |
| 46c1a86358244f8c0bcc024a561174ff946cdd3cd84545a0a150e4b707eef2da evidence/cumulative/full_gpu_n200.json | |
| c0306d4e5f6de32c1cb8787376ff8d5bd30dc06b77a1dbaebf32217fae80876f evidence/cumulative/full_gpu_n200_verification.json | |
| 3016dfb245deb56b3d0d3d06f902471bc415f80196d61ecf4d49eb773f1edd76 evidence/cumulative/full_n512.csv | |
| 5b103f87b7736f58bcf0efdb7fb81c83ae1010fab3bd2a80516c1b2ae74cc882 evidence/cumulative/full_n512.json | |
| 451d8e22fdea6a8625e88d36547148efeaa8017f24fe97295fc080ce05916a97 evidence/cumulative/limitations.md | |
| b0960a8f2cbde04c81ec2ff80c7926ad0c7611a38b912228fbb008285b15605d evidence/cumulative/method.md | |
| 0ac0ec3dea88d8d630d5068e76cb5c6b8d14ed133f044f37f57a40986c37a7d7 evidence/cumulative/regresslm_table3_results.csv | |
| 173dbce239ca51269d3b231dd851b7fb299dffc82d2b0eede75f61ae6a835dc2 evidence/cumulative/table3_results.json | |
| 97f2e2cd48aa0f4854c67afe177a07b43df65285178d2c0d00e1126c670b2430 logbook.json | |
| af79806345fd90ca0a442572d0991d3127d2a6b448ce2972c7b228b52558fac7 pages/claim-4-kendall-ranking/page.md | |
| 603a8d41e177484005163dddcb9cac68e240d26c4d4887aad442bf5e95c9cdfd pages/claim-5-ablation-scaling/page.md | |
| af13b86afdc3a95207ee4c24d6a365dd10d50b634f1bd4f86f14e99241c660b2 pages/current-claim-1/page.md | |
| f770dda6fd1d240ab30ac424d6adcd1e1b36fb2c6ce666efd5ce66acbe0b4c6e pages/current-claim-2/page.md | |
| 59cf02764afc3391c54742e418095bece4c03070a0caa18023a1bd2976403b5b pages/current-claim-3/page.md | |
| e325c177204410f2685196dcfe0425d32c74c1bddc2491d62a03cac9a0921c83 pages/current-cumulative-verification/page.md | |
| 0dfe5f05a171d420aaefd821f3c9ae6165117cdfcdfb453dc02746451e969e18 pages/current-index/page.md | |
| d2001aa92527f6e37cb985c95d8d83bcbc1808dfe9b99f8d3d46706a0c8b8568 pages/release-report/page.md | |