{"schema_version":1,"total":1,"offset":0,"limit":100,"observations":[{"id":"public:353e600be2a8e94d00f6109b","benchmark_id":"ugi-writing::snapshot-2026-09-10","subject":{"source_id":"Qwen/Qwen3-4B-Thinking-2507","name":"Qwen/Qwen3-4B-Thinking-2507","model_id":"qwen3-4b-2507::reasoning","variant":null,"harness":null},"value":10.87,"unit":"points","basis":"measured","source":{"url":"https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/raw/main/ugi-leaderboard-data.csv","retrieved_at":"2026-09-10T22:04:13Z","published_at":null,"file":"ops/rebuild-2026-09/evidence/phase-04/sources/supp-6c45283c6461.gz","sha256":"4154635c4557af4b4eebbeaab6970bdf8296aef44e46f6193fdb4976cd8fe7f2","locator":"csv; source row 497; Qwen/Qwen3-4B-Thinking-2507; field Writing ✍️"},"protocol":"Writing ✍️ published composite; Prompt Template=chatml; Test Date=10/18/2025; Model Link=https://huggingface.co/Qwen/Qwen3-4B-Thinking-2507; Is Thinking Model=True","comparison_key":null,"join_note":"Unique exact Hugging Face checkpoint URL in retained catalog metadata; source effort remains as published."}],"divergences":[],"cell":null,"coverage":{"model":null,"benchmark":{"total_models":844,"available":71,"unknown":773,"not_tested":0,"not_published":0,"source_unreachable":0,"contested":0,"measured":71,"self_reported":0,"observations":1252,"unmatched_observations":1181}},"collection":{"benchmark_id":"ugi-writing::snapshot-2026-09-10","status":"collected","source_url":"https://huggingface.co/spaces/DontPlanToEnd/UGI-Leaderboard/raw/main/ugi-leaderboard-data.csv","reason":"1252 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."}