{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.15166", "kind": "paper", "url": "https://arxiv.org/abs/2607.15166"}], "authors": ["Goktug Ozkan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.15166", "source_url": "https://arxiv.org/abs/2607.15166"}, "categories": ["Biology & Drug Discovery", "Safety", "Safety & Trustworthiness"], "description": {"en": "The evaluation object is unclear from the provided information."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.15166", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.15166", "title": "MedFailBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.15166", "modality": null, "name": "MedFailBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_medfailbench_90f26faa", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "c8fcb0c9fe3c597f0677debe6aa3ce339ebd6d80aa6d99af2eaa5e4daf4f7ba3", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.15166"}, "publisher": null, "released": "2026-07-16", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.15166", "source_url": "https://arxiv.org/abs/2607.15166"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-15166", "source": "claire_radar", "source_benchmark_id": "2607.15166", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Biology & Drug Discovery"], "area": "Safety & Trustworthiness", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.15166", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d16bb94e520321bc9eeeedb4468346730904d1df61f48a1b5bec2c0246ef335e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "The evaluation object is unclear from the provided information.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present a synthetic benchmark and failure atlas built by a clinician."}, "familyId": "bmf_539cc8579836", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_medfailbench_90f26faa", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.15166", "paper": "https://arxiv.org/abs/2607.15166", "pdf": "https://arxiv.org/pdf/2607.15166", "project": null, "report": "https://arxiv.org/abs/2607.15166"}, "metrics": [], "motivation": "Most medical AI benchmarks measure whether a model knows the correct answer.", "name": "MedFailBench", "oneLine": "The evaluation object is unclear from the provided information.", "paperTitle": "MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.15166", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-16", "source": {"authors": ["Goktug Ozkan"], "categories": ["cs.AI", "cs.CL"], "id": "2607.15166", "title": "MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection", "type": "arxiv", "url": "https://arxiv.org/abs/2607.15166"}, "sourceUpdatedAt": "2026-07-27T06:11:24Z", "topics": ["Safety"], "venueAttempts": [], "whyItMatters": "The evaluation gap and practical decision value are unclear."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
