{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.07796", "kind": "paper", "url": "https://arxiv.org/abs/2608.07796"}], "authors": ["Veronica Chatrath", "Bryan Zhu", "George Pu", "Jingxuan Fan", "Apaar Shanker", "Varun Ursekar", "Anahita Sharma", "Jason Qin", "Keqi Han", "Soham Dinesh Tiwari", "Soham Dan", "Vijay Kalmath", "Yuan Li", "Daniel Yue Zhang", "Chenguang Wang", "Zainab Doctor", "Zhijun Yin", "Nigam H. Shah", "Yuan Xue"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.07796", "source_url": "https://arxiv.org/abs/2608.07796"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "Reasoning"], "description": {"en": "CliniCARE-Bench evaluates clinical agents on retrospective audit tasks over longitudinal EHR data, measuring verdict accuracy, evidence grounding, process adherence, calibrated abstention, reliability, and efficiency."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.07796", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.07796", "title": "CliniCARE-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hochschule Aalen", "Emory University", "University of California, Santa Cruz", "Vanderbilt University Medical Center"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.07796", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.07796", "source_url": "https://openalex.org/W7202202844"}, "key": "claire-radar:2608.07796", "modality": null, "name": "CliniCARE-Bench", "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_clinicare-bench_6faa931e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1110a6898971567e30b9fc448e1f319480a334066627d6be2851adcba4bf7747", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.07796"}, "publisher": null, "released": "2026-08-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.07796", "source_url": "https://arxiv.org/abs/2608.07796"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-07796", "source": "claire_radar", "source_benchmark_id": "2608.07796", "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/2608.07796", "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": "71096404cea83d695392b31e689eaf23aa9d62f96a486bcbb0535b76d507d261", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CliniCARE-Bench evaluates clinical agents on retrospective audit tasks over longitudinal EHR data, measuring verdict accuracy, evidence grounding, process adherence, calibrated abstention, reliability, and efficiency.", "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 introduce CliniCARE-Bench (Clinical Calibrated Audit of Medical Reasoning in EHR), a benchmark for retrospective clinical audit: 25 clinician-validated scenarios instantiated as 750 patient-specific cases over real-patient-derived MIMIC-IV data."}, "familyId": "bmf_23f50f44501d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_clinicare-bench_6faa931e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.07796", "paper": "https://arxiv.org/abs/2608.07796", "pdf": "https://arxiv.org/pdf/2608.07796", "project": null, "report": "https://arxiv.org/abs/2608.07796"}, "metrics": [], "motivation": "Large language models perform strongly on medical knowledge benchmarks, but reliable clinical deployment requires agents to conduct defensible investigations over heterogeneous, longitudinal records: determining what evidence is needed, retrieving and reconciling structured and free-text data, grounding conclusions in verifiable evidence, and deferring cases that cannot be resolved reliably.", "name": "CliniCARE-Bench", "oneLine": "CliniCARE-Bench evaluates clinical agents on retrospective audit tasks over longitudinal EHR data, measuring verdict accuracy, evidence grounding, process adherence, calibrated abstention, reliability, and efficiency.", "paperTitle": "CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.07796", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-07", "source": {"authors": ["Veronica Chatrath", "Bryan Zhu", "George Pu", "Jingxuan Fan", "Apaar Shanker", "Varun Ursekar", "Anahita Sharma", "Jason Qin", "Keqi Han", "Soham Dinesh Tiwari", "Soham Dan", "Vijay Kalmath", "Yuan Li", "Daniel Yue Zhang", "Chenguang Wang", "Zainab Doctor", "Zhijun Yin", "Nigam H.Shah", "Yuan Xue"], "categories": ["cs.AI"], "id": "2608.07796", "title": "CliniCARE-Bench: Clinical Calibrated Audit of Medical Reasoning in EHR", "type": "arxiv", "url": "https://arxiv.org/abs/2608.07796"}, "sourceUpdatedAt": "2026-08-07T22:39:13Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Provides a deployment-oriented benchmark for clinical agents, assessing not just accuracy but also defensibility and calibration, which are essential for trustworthy clinical decision support."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
