{"confidence":0.95,"evidence_repo_slug":"owner__repository","generated_for_snapshot":"2026-11-01T11:12:16+00:00","metric_definition":"API calls; sums of observed assistant response usage, missing is null","publication_hashes":{"tools/build_site.py":"53f163ffa2fac7a6c0d91604d456fef55960e4563152b2483cbc84bb8838b78b","tools/limit-observation.json":"5e322cf8413511966cb21d1ccd6d48f68bd439d34c705a6491551bb4a8dd5185","tools/pack_evidence.py":"4b99fcf2b5d39f61a01d50e46304f49def9864a6ba6bd0aa1ebf6d2d7f266f36","tools/partners.json":"e385d4e3a6c588b0d527064407aa04d2486e2d884a6467fc53ce7049a57f5882","tools/projects.json":"5186a0bd0b0a83b7f03ab189f2ea1aacb7fa5d8c2a3cf7ab89c041f90c4f3d38","tools/site_assets/charts.js":"3deb88205204b4c636c704b673811b55eed0980e40fb686ba336c575938a1892","tools/site_assets/infrastructure.html":"53c1951e8463fb89a75cc0e893d6b27a9f6c6a604744298647344bd16f5d2981","tools/site_assets/research.html":"b7d6516a590ad8e3bcc64b5b403d828de6f18cf79c589d6008ca4e5145f82cb4","tools/site_assets/site.css":"71c06f05c2b3f189e12c906075294027c4ac046cef904e4ca1c3c3b6d9b77e8b","tools/site_assets/site.js":"6663350b0761c9ad44a2f5b28c6b96d4046a337cf5b01ff06b2fcee1d52578cd","tools/site_assets/theme.js":"d5e0c98c9780c04538357acf8aceebd5dfbe91ec7baa2f75c4277330a26ec304","vendor/echarts/VENDORED.json":"d7bb67c8e9e0d5aaa94b7364c870312f55189199861d0ac9e2417196431774b9"},"publish":true,"source_commit":"de695ed5124d14c16116d060b674ad37293f62ef","source_hashes":{"PUBLICATION.md":"06b8296cda26e23bc44486ee85a4d9b63f697440c0fac772b1ee3a8d61045485","README.md":"abd9af1073e49c935b8157e37b2e1d3582dbe23ee61c1cf6dcf80d25ec4f9dde","STATUS.md":"d51fc90f182584a2b4756b1c92842bc8e44047aeddb0d793826c0c23e78210c5","artifacts/datasets/SWE-bench_Lite.jsonl":"7393711dc0e108ae044a8f62f657d68fd4883eb4a8eb4f94a0925ccde4616f43","artifacts/datasets/SWE-bench_Verified.jsonl":"82029e78b26e1da0ddc01653c98db18443fab1993e28dff052a38b01c3fd77f7","artifacts/datasets/agent-input.jsonl":"9b7c800c4a85105ff9ac05219e3d784e81aa765cabff70f18f1007eaa408404b","artifacts/fleet.json":"1819a5a66703406088ba4265dd5701f6e7a9dac076e72a54d4b99774bbbf7a22","artifacts/leaderboards.json":"83cd949a9582f4dd68b0a07148cd86ff0eae6a05b0f2d2298a8f3717baf89d2d","artifacts/official-comparison.json":"4e044de80fc811e77e98d1eb3691e669ac0059cb99f15419433f82c3c335fe48","artifacts/report/generation-outcomes.json":"8b9c5c06a837321694df7576f44ffc8e2adc860b33cb606ab9c55dc2aa2e4758","artifacts/report/grading-amendments.json":"6356235ccc9ed3870cf76e310357c058099716eb2518ef1188e778d5e6de8854","artifacts/report/instances.csv":"2ee5dd84ddf3133f6eed90b5a3226a2f36fa239114a69a33299b844ed0cc962a","artifacts/report/model-pauses.json":"ce625b6773270f206134df30c27cf911a922098d85932a6cfd99fa5c616f2fdb","artifacts/report/repositories.json":"4b9884fb69762bb22b7909de03340420cf4c0b7ced48557ddd3fffdecb088f16","artifacts/report/subsets.json":"a29fad40bb9f52f4e77777c89acfcd57e36e45e750805ebffebd090035ddc18a","artifacts/report/summary.json":"a33cfe3d1b56de8600501dd546e4399653406f9d736e65ada165d4546d08a695","artifacts/report/test-timeout-reviews.json":"2e3bd0ee73ab94737caa3726d4a1044bbf12db39ee41af74113b91da56f05bc5","artifacts/report/timeout-adjudications.json":"d2334d41f91fc9e72ec22a3b314d2052ffdcfbdde711d295503e5bc975881cb8","artifacts/report/transport-amendments.json":"77ff1c36b1e767102d806940daa9fb38de368732910c3fc7f762d2ac07457410","artifacts/telemetry-history.jsonl":"f5380e3ad8d7a9863f86d75420d28d497ddd84770ea702cc3135637b3e5149f1","artifacts/upgrade-v2.json":"7d89b869774cd415cd635a954e738a77bdf8ef6dd5256007705149040b6a1fbd","configs/experiment.json":"85db7cba92d2a27b1a245350b4b1091e485114cfef84dd9ecfa9b37411c0fd82","configs/protocol.json":"fcf0b9b4529a36a72a1267b4ea93cb46a814467c765b44c071b98ceac6258b75","configs/request-nonce.json":"e6f5b78a710adbe10081be662c0b22026433ad9aa2909b3410e96c812840faec","scripts/bootstrap.sh":"d60a8f38cd24d91134e22a568fa86ca95904470a2bf1bff2b3e49f5d5f856dbc","scripts/fleet.py":"f748a2187a39f40e283d489b33cef2a5b834bedbfccfac207c99e13ba129d744","scripts/render_report.py":"35fbd33f3f01717becb89e34b94ecab847ad8e22347768dffed8a38a08dfee21","scripts/report.py":"872ee760320a61e7ba7181d875317faaae08c08a5e235de5297403e953dda734","scripts/run_job.py":"544dcd92a44c89b9c659696b4a5ac6aff5826ea93b35f66facc4710c652dfcc2","scripts/subsets.py":"f850ec00dea07607a4fcda6d0ea4099b6cdf02f1d779e6eaf5212732a1ae17de","scripts/upgrade_fleet.py":"f577768820c3e8749219047a03520ecbaad04fadd027a5277b3d694b467cf124","scripts/worker_v2.py":"f25c3d67c3a758e2961ac0252c16802ccbc5ef20d4de758a9534025cab8e00fd"},"source_policy":"Validated report exports; no source scripts executed","staging":false,"trajectory_limit_per_model":null,"unavailable":["outage rerun attribution","gateway-stall timeout attribution"],"verified_policy":"subsets.py export; supplemental astropy__astropy-7606 contract"}
