{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.15735", "kind": "paper", "url": "https://arxiv.org/abs/2606.15735"}], "authors": ["Jiyoun Kim", "Muhan Yeo", "Eunhye Jang", "Jeewon Yang", "Hangyul Yoon", "Su Ji Lee", "Hee Jo Han", "Hee-Jae Jung", "Doyun Kwon", "Jun young Lee", "Jaehun Lee", "Jung-Oh Lee", "Sunjun Kweon", "Jong Hak Moon", "Daseul Kim", "Minjae Cho", "Edward Choi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.15735", "source_url": "https://arxiv.org/abs/2606.15735"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.CL"], "description": {"en": "EHRNote-ChatQA is a benchmark for evidence-grounded multi-turn clinical QA over longitudinal discharge summaries. Built from MIMIC-IV, it includes 967 patient-level samples and 16,072 expert-verified QA pairs across eight clinical categories, with evidence-grounding QA pairs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.15735", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.15735", "title": "EHRNote-ChatQA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Korea Advanced Institute of Science and Technology", "Seoul National University", "Seoul National University Bundang Hospital", "Sungkyunkwan University", "Yonsei University", "Severance Hospital", "Seoul Medical Center", "Gangnam Severance Hospital", "Seoul National University Hospital", "Icahn School of Medicine at Mount Sinai", "Samsung Medical Center"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.15735", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.15735", "source_url": "https://openalex.org/W7164958737"}, "key": "claire-radar:2606.15735", "modality": null, "name": "EHRNote-ChatQA", "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_ehrnote-chatqa_748f904b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e77928a4d11632c50a70a2d1703b4deb6f802a0325a9f9b54a39b7616488c003", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.15735"}, "publisher": null, "released": "2026-06-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.15735", "source_url": "https://arxiv.org/abs/2606.15735"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-15735", "source": "claire_radar", "source_benchmark_id": "2606.15735", "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/2606.15735", "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": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "30890303f5a28845d1ffb75f3a6909cb92ebca9063463fb54f4261ca16723aea", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "EHRNote-ChatQA is a benchmark for evidence-grounded multi-turn clinical QA over longitudinal discharge summaries. Built from MIMIC-IV, it includes 967 patient-level samples and 16,072 expert-verified QA pairs across eight clinical categories, with evidence-grounding QA pairs.", "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": "We introduce EHRNote-ChatQA, the first benchmark for evidence-grounded multi-turn clinical question answering over patients' multiple discharge summaries."}, "familyId": "bmf_6bcd9830c15b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_ehrnote-chatqa_748f904b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.15735", "paper": "https://arxiv.org/abs/2606.15735", "pdf": "https://arxiv.org/pdf/2606.15735", "project": null, "report": "https://arxiv.org/abs/2606.15735"}, "metrics": [], "motivation": "Discharge summaries are crucial clinical documents containing the context of a patient's overall hospital stay, and are routinely reviewed by medical experts for patient readmission, ongoing care, and diagnostic decision-making.", "name": "EHRNote-ChatQA", "oneLine": "EHRNote-ChatQA is a benchmark for evidence-grounded multi-turn clinical QA over longitudinal discharge summaries. Built from MIMIC-IV, it includes 967 patient-level samples and 16,072 expert-verified QA pairs across eight clinical categories, with evidence-grounding QA pairs.", "paperTitle": "EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.15735", "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": "2026-06-14", "source": {"authors": ["Jiyoun Kim", "Muhan Yeo", "Eunhye Jang", "Jeewon Yang", "Hangyul Yoon", "Su Ji Lee", "Hee Jo Han", "Hee-Jae Jung", "Doyun Kwon", "Jun young Lee", "Jaehun Lee", "Jung-Oh Lee", "Sunjun Kweon", "Jong Hak Moon", "Daseul Kim", "Minjae Cho", "Edward Choi"], "categories": ["cs.CL", "cs.AI"], "id": "2606.15735", "title": "EHRNote-ChatQA: A Benchmark for Evidence-Grounded Multi-Turn Clinical Question Answering over Longitudinal Discharge Summaries", "type": "arxiv", "url": "https://arxiv.org/abs/2606.15735"}, "sourceUpdatedAt": "2026-06-16T10:33:24Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "EHRNote-ChatQA addresses the gap in evaluating clinical QA systems on multi-turn, evidence-grounded reasoning over multiple documents, which reflects real clinical review workflows. It provides a rigorous benchmark for assessing evidence grounding and the compounding of errors over turns."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
