{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.18613", "kind": "paper", "url": "https://arxiv.org/abs/2606.18613"}], "authors": ["Tianming Du", "Peijie Yu", "Sihan Shang", "Danli Shi", "My Linh Nguyen", "Shengbo Gao", "Guangyuan Li", "Yinghong Yu", "Yan Jiang", "Qianlong Zhao", "Behzad Bozorgtabar", "Shaoxiong Ji", "Jiazhen Pan", "Daniel Rueckert", "Jiancheng Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.18613", "source_url": "https://arxiv.org/abs/2606.18613"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.CL"], "description": {"en": "PhysAssistBench evaluates interactive doctor-patient-EHR assistance. It contains 1,296 physician-validated turns from MIMIC-IV cases, testing coordination of clinical knowledge, patient communication, and EHR tool use."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.18613", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.18613", "title": "PhysAssistBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.18613", "modality": null, "name": "PhysAssistBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_physassistbench_d86f4b50", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "1e8dbe8bf146b318cd47b462a26568ec4defd183df05aeab67b0a1b64019d195", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.18613"}, "publisher": null, "released": "2026-06-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.18613", "source_url": "https://arxiv.org/abs/2606.18613"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-18613", "source": "claire_radar", "source_benchmark_id": "2606.18613", "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/2606.18613", "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": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "8d021bcb71432ace8c07aa507b4ec7027bf6656593c92cc97484ab5efc69aded", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "PhysAssistBench evaluates interactive doctor-patient-EHR assistance. It contains 1,296 physician-validated turns from MIMIC-IV cases, testing coordination of clinical knowledge, patient communication, and EHR tool use.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "We introduce PhysAssistBench, a benchmark for interactive doctor-patient-EHR assistance."}, "familyId": "bmf_2c7c02cd01ab", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_physassistbench_d86f4b50", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.18613", "paper": "https://arxiv.org/abs/2606.18613", "pdf": "https://arxiv.org/pdf/2606.18613", "project": null, "report": "https://arxiv.org/abs/2606.18613"}, "metrics": [], "motivation": "The most plausible near-term role of medical LLMs is to assist rather than replace physicians, yet current evaluations often test isolated capabilities: clinical knowledge, EHR system interaction, or patient communication.", "name": "PhysAssistBench", "oneLine": "PhysAssistBench evaluates interactive doctor-patient-EHR assistance. It contains 1,296 physician-validated turns from MIMIC-IV cases, testing coordination of clinical knowledge, patient communication, and EHR tool use.", "paperTitle": "Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.18613", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-17", "source": {"authors": ["Tianming Du", "Peijie Yu", "Sihan Shang", "Danli Shi", "My Linh Nguyen", "Shengbo Gao", "Guangyuan Li", "Yinghong Yu", "Yan Jiang", "Qianlong Zhao", "Behzad Bozorgtabar", "Shaoxiong Ji", "Jiazhen Pan", "Daniel Rueckert", "Jiancheng Yang"], "categories": ["cs.CL", "cs.AI"], "id": "2606.18613", "title": "Are LLMs Ready to Assist Physicians? PhysAssistBench for Interactive Doctor-Patient-EHR Assistance", "type": "arxiv", "url": "https://arxiv.org/abs/2606.18613"}, "sourceUpdatedAt": "2026-07-10T11:43:07Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Current medical LLM evaluations isolate capabilities, but real physician assistance requires integrating knowledge, communication, and systems. PhysAssistBench provides a realistic interaction setting to assess readiness for clinical deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
