{
 "id": "JackJ3636/when-rubrics-fail",
 "owner": "JackJ3636",
 "name": "when-rubrics-fail",
 "downloads": 45,
 "likes": 0,
 "last_modified": "2026-09-09T21:01:52.000Z",
 "stated_licence": "cc-by-4.0",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [],
 "citation": "@misc{rubric-error-sensitivity,\n  title  = {Rubric-based evaluation does not reliably detect\n            clinically important errors},\n  year   = {2026},\n  note   = {Data: injected medical errors across HealthBench,\n            HealthBench Professional and LiveMedBench}\n}",
 "signal": "permissive",
 "reason": "The declared licence (cc-by-4.0) is classified as permissive.",
 "revision": "bedfe082d5bc3cc84c282038d7842446d276ca5d",
 "stated_evidence": "https://huggingface.co/datasets/JackJ3636/when-rubrics-fail/blob/bedfe082d5bc3cc84c282038d7842446d276ca5d/README.md",
 "file_evidence": "https://huggingface.co/datasets/JackJ3636/when-rubrics-fail/tree/bedfe082d5bc3cc84c282038d7842446d276ca5d",
 "card_nc": false
}