{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EBABOF74UFSY4IA3UQWN6AZKRJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"15395aeed66e3cf77a448acf52ad7c9e810f0120b09539972d1b80ee72dcc769","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-13T15:03:34Z","title_canon_sha256":"2542b988ecd2d2adbd9530844602b56df66a5d8bc61ed8e6fc3c7f9c100fdc98"},"schema_version":"1.0","source":{"id":"2509.10843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10843","created_at":"2026-07-05T12:11:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10843v1","created_at":"2026-07-05T12:11:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10843","created_at":"2026-07-05T12:11:29Z"},{"alias_kind":"pith_short_12","alias_value":"EBABOF74UFSY","created_at":"2026-07-05T12:11:29Z"},{"alias_kind":"pith_short_16","alias_value":"EBABOF74UFSY4IA3","created_at":"2026-07-05T12:11:29Z"},{"alias_kind":"pith_short_8","alias_value":"EBABOF74","created_at":"2026-07-05T12:11:29Z"}],"graph_snapshots":[{"event_id":"sha256:ba92bd0764f2dd43d15fc2421676ff8993fe798971157286a6616a1281cf4cf6","target":"graph","created_at":"2026-07-05T12:11:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.10843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated substantial progress in biomedical and clinical applications, motivating rigorous evaluation of their ability to answer nuanced, evidence-based questions. We curate a multi-source benchmark drawing from Cochrane systematic reviews and clinical guidelines, including structured recommendations from the American Heart Association and narrative guidance used by insurers. Using GPT-4o-mini and GPT-5, we observe consistent performance patterns across sources and clinical domains: accuracy is highest on structured guideline recommendations (90%) and lowe","authors_text":"Can Wang, Yiqun Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-13T15:03:34Z","title":"Evaluating Large Language Models for Evidence-Based Clinical Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10843","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a459d1abb8c2400e36de62d61a18df8392fcc0493390748c893e21e128834b9b","target":"record","created_at":"2026-07-05T12:11:29Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"15395aeed66e3cf77a448acf52ad7c9e810f0120b09539972d1b80ee72dcc769","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-13T15:03:34Z","title_canon_sha256":"2542b988ecd2d2adbd9530844602b56df66a5d8bc61ed8e6fc3c7f9c100fdc98"},"schema_version":"1.0","source":{"id":"2509.10843","kind":"arxiv","version":1}},"canonical_sha256":"20401717fca1658e201ba42cdf032a8a60fa6b326e070a0f5e1c783aa095ebac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20401717fca1658e201ba42cdf032a8a60fa6b326e070a0f5e1c783aa095ebac","first_computed_at":"2026-07-05T12:11:29.026245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:29.026245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q2Dlg83H9A8CcsolJS1xMeChYTJaxu1T35NDHc2toD/X5ZYbbmBvUvPhl59N5N+X2TYmGqjxCNh+W/MmGiQ0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:29.026811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.10843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a459d1abb8c2400e36de62d61a18df8392fcc0493390748c893e21e128834b9b","sha256:ba92bd0764f2dd43d15fc2421676ff8993fe798971157286a6616a1281cf4cf6"],"state_sha256":"9e97a87f33bbd86ae8c3afd6988e1a0e70faf3630b62f4931d7a6897f2f53a91"}