{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HO2BLUIFYL75VP7RLM7VSGPFGH","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":"27c264030a3827738c11c6113c646887b09504614f0b86bb4c8227ffb5c9daff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T17:16:27Z","title_canon_sha256":"f308ac39b41f4fa031859e54c1b82d51ce90dedc46da1d86ca2e7dc138ab377c"},"schema_version":"1.0","source":{"id":"2505.11462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11462","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11462v2","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11462","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_12","alias_value":"HO2BLUIFYL75","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_16","alias_value":"HO2BLUIFYL75VP7R","created_at":"2026-07-05T11:26:04Z"},{"alias_kind":"pith_short_8","alias_value":"HO2BLUIF","created_at":"2026-07-05T11:26:04Z"}],"graph_snapshots":[{"event_id":"sha256:082e20b80e4048af0db284ec1eb1cbb2998a5813e1e5bbdda2578941ab34ff91","target":"graph","created_at":"2026-07-05T11:26:04Z","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/2505.11462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Medical reasoning in large language models (LLMs) aims to emulate clinicians' diagnostic thinking, but current benchmarks such as MedQA-USMLE, MedMCQA, and PubMedQA often mix reasoning with factual recall. We address this by separating 11 biomedical QA benchmarks into reasoning- and knowledge-focused subsets using a PubMedBERT classifier that reaches 81 percent accuracy, comparable to human performance. Our analysis shows that only 32.8 percent of questions require complex reasoning. We evaluate biomedical models (HuatuoGPT-o1, MedReason, m1) and general-domain models (DeepSeek-R1, o4-mini, Qw","authors_text":"Angela Zhang, Ben Athiwaratkun, Eric Wu, Haotian Ye, Harrison Zhang, James Zou, Joseph Boen, Kevin Wu, Nevin Aresh, Qingyang Wu, Rahul Thapa, Shriya Reddy, Shuaiwen Leon Song, Suhana Bedi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T17:16:27Z","title":"Disentangling Reasoning and Knowledge in Medical Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11462","kind":"arxiv","version":2},"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":"sha256:1164a2f5b37a6db8aee6ebd8466d6a05a5f3bce82644082e740bdaebe80bccbc","target":"record","created_at":"2026-07-05T11:26:04Z","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":"27c264030a3827738c11c6113c646887b09504614f0b86bb4c8227ffb5c9daff","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T17:16:27Z","title_canon_sha256":"f308ac39b41f4fa031859e54c1b82d51ce90dedc46da1d86ca2e7dc138ab377c"},"schema_version":"1.0","source":{"id":"2505.11462","kind":"arxiv","version":2}},"canonical_sha256":"3bb415d105c2ffdabff15b3f5919e531ff92395c8148768b4e090e08f9649328","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bb415d105c2ffdabff15b3f5919e531ff92395c8148768b4e090e08f9649328","first_computed_at":"2026-07-05T11:26:04.402209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:04.402209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pzZg5RfFOZUoG6+n+v11YCkuOx+3v6qs1crVPOb/fNl/jtpxHF4uesWmD+xr3T+0iEc/UleOfdAQ0mn/NdEABw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:04.402717Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1164a2f5b37a6db8aee6ebd8466d6a05a5f3bce82644082e740bdaebe80bccbc","sha256:082e20b80e4048af0db284ec1eb1cbb2998a5813e1e5bbdda2578941ab34ff91"],"state_sha256":"9797b281b1e2ad945d0eb32ca392805975c99bd219f9abd7e9d93954d341b4d1"}