{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.14015", "kind": "paper", "url": "https://arxiv.org/abs/2608.14015"}, {"kind": "website", "url": "https://fyycs.github.io/medclaw/"}], "authors": ["Yingying Fan", "Penghui Du", "Leyan Zhu", "Runze He", "Zimeng Wu", "Yuxuan Zhang", "Liang Chen", "Jiahao Xie", "Jiangtang Wang", "Shuai Shao", "Anchao Yang", "Yutong Bai", "Yan Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14015", "source_url": "https://arxiv.org/abs/2608.14015"}, "categories": ["Agents", "General AI", "Reasoning", "Vision & 3D"], "description": {"en": "MedClawBench evaluates long-horizon temporal reasoning in surgical videos through 1,123 doctor-grounded questions over self-built long neurosurgery recordings and a public lecture-video test split, with fixed evaluation dimensions for comparison."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14015", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14015", "title": "MedClawBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Beijing Jiaotong University", "Capital Medical University", "Beijing Tian Tan Hospital"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.14015", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.14015", "source_url": "https://openalex.org/W7203603198"}, "key": "claire-radar:2608.14015", "modality": null, "name": "MedClawBench", "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_medclawbench_bcd0f6e4", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "789deca314a374b0ca1b4f6a683ea2441966bec6d9042e0f557b2338506db259", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.14015"}, "publisher": null, "released": "2026-08-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14015", "source_url": "https://arxiv.org/abs/2608.14015"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14015", "source": "claire_radar", "source_benchmark_id": "2608.14015", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.14015", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "7156f19c8562b3031ef6b9a38928e198f2688ff963fa2e2732adb09d9170c6a8", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MedClawBench evaluates long-horizon temporal reasoning in surgical videos through 1,123 doctor-grounded questions over self-built long neurosurgery recordings and a public lecture-video test split, with fixed evaluation dimensions for comparison.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To evaluate this agent, we introduce MedClawBench, a de-leaked, doctor-grounded benchmark of 1,123 questions over self-built long neurosurgery recordings and a held-out public lecture-video test split."}, "familyId": "bmf_56afb80b1bd4", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_medclawbench_bcd0f6e4", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.14015", "paper": "https://arxiv.org/abs/2608.14015", "pdf": "https://arxiv.org/pdf/2608.14015", "project": "https://fyycs.github.io/medclaw/", "report": "https://arxiv.org/abs/2608.14015"}, "metrics": [], "motivation": "Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time.", "name": "MedClawBench", "oneLine": "MedClawBench evaluates long-horizon temporal reasoning in surgical videos through 1,123 doctor-grounded questions over self-built long neurosurgery recordings and a public lecture-video test split, with fixed evaluation dimensions for comparison.", "paperTitle": "MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14015", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MedClaw team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://fyycs.github.io/medclaw/"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Inspectable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-08-14", "source": {"authors": ["Yingying Fan", "Penghui Du", "Leyan Zhu", "Runze He", "Zimeng Wu", "Yuxuan Zhang", "Liang Chen", "Jiahao Xie", "Jiangtang Wang", "Shuai Shao", "Anchao Yang", "Yutong Bai", "Yan Wang"], "categories": ["cs.CV", "cs.AI"], "id": "2608.14015", "title": "MedClaw: Heuristic Agent Harness for Long-Horizon Surgical Video Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14015"}, "sourceUpdatedAt": "2026-08-14T07:03:06Z", "topics": ["Agents", "Reasoning"], "venueAttempts": [], "whyItMatters": "Existing VLM benchmarks fail to capture temporal dependencies in long surgical videos. MedClawBench provides a reproducible, doctor-grounded dataset to assess video reasoning capabilities beyond short clips, aiding progress in surgical AI systems."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
