{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03157", "kind": "paper", "url": "https://arxiv.org/abs/2606.03157"}], "authors": ["Ruihui Hou", "Siyi Zhu", "Ziyue Huai", "Guangya Yu", "Yongqi Fan", "Chunming Wang", "Tong Ruan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03157", "source_url": "https://arxiv.org/abs/2606.03157"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.AI"], "description": {"en": "ClinicalMC evaluates LLM clinical decision-making across multi-course patient trajectories, with 1,275 Chinese and 5,804 English samples spanning four stages from admission to discharge. Includes triage, examination, diagnosis, treatment, and final diagnosis."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03157", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03157", "title": "ClinicalMC"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["East China University of Science and Technology", "Shanghai Jiao Tong University", "Renji Hospital"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.03157", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.03157", "source_url": "https://openalex.org/W7163420784"}, "key": "claire-radar:2606.03157", "modality": null, "name": "ClinicalMC", "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_clinicalmc_22427e9b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "311fefac15467de4359a16956658318c8c2d6fad763b3fead857f1c5a0a755ab", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03157"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03157", "source_url": "https://arxiv.org/abs/2606.03157"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03157", "source": "claire_radar", "source_benchmark_id": "2606.03157", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "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/2606.03157", "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": [], "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": "6376e4263cd7f0f2ac1d5cfd8a45f693e5bf8729c2a91823ffa73bfd38025e94", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ClinicalMC evaluates LLM clinical decision-making across multi-course patient trajectories, with 1,275 Chinese and 5,804 English samples spanning four stages from admission to discharge. Includes triage, examination, diagnosis, treatment, and final diagnosis.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address this gap, we propose ClinicalMC, a benchmark for multi-course clinical decision-making."}, "familyId": "bmf_297bec9ba523", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_clinicalmc_22427e9b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.03157", "paper": "https://arxiv.org/abs/2606.03157", "pdf": "https://arxiv.org/pdf/2606.03157", "project": null, "report": "https://arxiv.org/abs/2606.03157"}, "metrics": [], "motivation": "Large language models (LLMs) have been widely adopted in healthcare, yet they still encounter significant challenges in complex clinical decision-making scenarios.", "name": "ClinicalMC", "oneLine": "ClinicalMC evaluates LLM clinical decision-making across multi-course patient trajectories, with 1,275 Chinese and 5,804 English samples spanning four stages from admission to discharge. Includes triage, examination, diagnosis, treatment, and final diagnosis.", "paperTitle": "ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03157", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Ruihui Hou", "Siyi Zhu", "Ziyue Huai", "Guangya Yu", "Yongqi Fan", "Chunming Wang", "Tong Ruan"], "categories": ["cs.AI"], "id": "2606.03157", "title": "ClinicalMC: A Benchmark for Multi-Course Clinical Decision-Making with Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03157"}, "sourceUpdatedAt": "2026-06-02T05:09:18Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing clinical benchmarks focus on single-course scenarios, missing the complexity of evolving patient conditions. ClinicalMC enables evaluation of dynamic multi-turn decision-making, supporting safer LLM deployment in healthcare."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
