{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"public:eb3bf56a46512ff02158c73f","benchmark_id":"deepswe::snapshot-2026-09-15","subject":{"source_id":"claude-sonnet-5_low","name":"claude-sonnet-5 (low)","model_id":"claude-sonnet-5::low","variant":null,"harness":"mini-swe-agent"},"value":0.3051224944320713,"unit":"fraction","basis":"measured","source":{"url":"https://epoch.ai/data/benchmark_data.zip","retrieved_at":"2026-09-15T09:05:24Z","published_at":null,"file":"data/raw/benchmarks/daily-evidence/2026-09-15-coding/epoch-deepswe_external.csv.gz","sha256":"7f0ae5e4d772c99b10a8b29ee8e2760771b63fe7f561e90d5ba48a0fae52e686","locator":"csv; source row 49; claude-sonnet-5_low; field Pass@1"},"protocol":"DeepSWE as republished by Epoch AI (deepswe_external.csv); Pass@1 averaged over runs; mini-swe-agent harness; Reasoning effort=low; Runs=4; Pass@4=0.5752212389380531; 95% CI half-width=0.011260175414427497","comparison_key":null,"join_note":"Reviewed identity map 2026-09-15: label states model claude-sonnet-5 and effort low; exact catalog configuration claude-sonnet-5::low"}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":924,"available":64,"unknown":860,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":63,"self_reported":0,"observations":70,"unmatched_observations":6,"preliminary":1}},"collection":{"benchmark_id":"deepswe::snapshot-2026-09-15","status":"collected","source_url":"https://epoch.ai/data/benchmark_data.zip","reason":"69 source results parsed; configurations remain separate; unmatched model identities are retained."},"coverage_note":"Denominators are catalog model configurations × versioned registry entries; capability_available excludes Efficiency (cost) boards. Basis counts count covered cells, not runs; measured and self_reported may overlap. Unmatched source identities remain in observations and never inflate catalog coverage."}