{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.03028", "kind": "paper", "url": "https://arxiv.org/abs/2608.03028"}], "authors": ["Zhitian Hou", "Yuhang Liu", "Pengkai Wang", "Zeyu Liu", "Guanghao Zhu", "Zheng Liu", "Shuo Cai", "Congkai Xie", "Zhijie Sang", "Kun Zeng", "Hongxia Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.03028", "source_url": "https://arxiv.org/abs/2608.03028"}, "categories": ["Biology & Drug Discovery", "Cybersecurity", "Reasoning", "Safety", "Safety & Trustworthiness"], "description": {"en": "MedPIC-Bench evaluates patient-specific medication-safety reasoning in LLMs using guideline-following and paired counterfactual questions, with 467 questions annotated across six dimensions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.03028", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.03028", "title": "MedPIC-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hong Kong Polytechnic University", "Sun Yat-sen University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.03028", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.03028", "source_url": "https://openalex.org/W7172485967"}, "key": "claire-radar:2608.03028", "modality": null, "name": "MedPIC-Bench", "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_medpic-bench_f4184b8f", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "16b4121339817a38198c1cd16aeb69c2f628e5939b2724bd02b02a8a00505e5e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.03028"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.03028", "source_url": "https://arxiv.org/abs/2608.03028"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-03028", "source": "claire_radar", "source_benchmark_id": "2608.03028", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity", "Biology & Drug Discovery"], "area": "Safety & Trustworthiness", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.03028", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "20a8f713b6ed5f6b35987cf9f11377968ea22af6f25c06e64ea06d1ae59835cb", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MedPIC-Bench evaluates patient-specific medication-safety reasoning in LLMs using guideline-following and paired counterfactual questions, with 467 questions annotated across six dimensions.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "To address this gap, we introduce MedPIC-Bench, a benchmark of source-verifiable recommendations and expert-validated questions for patient-specific medication-safety reasoning."}, "familyId": "bmf_f9677fb45e23", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_medpic-bench_f4184b8f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Cybersecurity", "Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.03028", "paper": "https://arxiv.org/abs/2608.03028", "pdf": "https://arxiv.org/pdf/2608.03028", "project": null, "report": "https://arxiv.org/abs/2608.03028"}, "metrics": [], "motivation": "Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision.", "name": "MedPIC-Bench", "oneLine": "MedPIC-Bench evaluates patient-specific medication-safety reasoning in LLMs using guideline-following and paired counterfactual questions, with 467 questions annotated across six dimensions.", "paperTitle": "Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.03028", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-08-04", "source": {"authors": ["Zhitian Hou", "Yuhang Liu", "Pengkai Wang", "Zeyu Liu", "Guanghao Zhu", "Zheng Liu", "Shuo Cai", "Congkai Xie", "Zhijie Sang", "Kun Zeng", "Hongxia Yang"], "categories": ["cs.AI"], "id": "2608.03028", "title": "Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.03028"}, "sourceUpdatedAt": "2026-08-04T02:17:16Z", "topics": ["Safety", "Reasoning"], "venueAttempts": [], "whyItMatters": "Static medication-safety accuracy may not reflect whether models use patient information to determine rule applicability. This benchmark aims to make conditional rule application measurable."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
