{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5426EBKHTH7YUMDAWXK5H6Z524","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":"16cd043f18c26c7f6359b345e238b81856895e717652ee30d07e06c6cf7e1d5b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-14T14:46:18Z","title_canon_sha256":"4205395cd9be82bef3c9059ddc74189fbbfbf61ce722a17c26a684c4fecb02fd"},"schema_version":"1.0","source":{"id":"2412.10849","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10849","created_at":"2026-07-05T11:14:25Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10849v3","created_at":"2026-07-05T11:14:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10849","created_at":"2026-07-05T11:14:25Z"},{"alias_kind":"pith_short_12","alias_value":"5426EBKHTH7Y","created_at":"2026-07-05T11:14:25Z"},{"alias_kind":"pith_short_16","alias_value":"5426EBKHTH7YUMDA","created_at":"2026-07-05T11:14:25Z"},{"alias_kind":"pith_short_8","alias_value":"5426EBKH","created_at":"2026-07-05T11:14:25Z"}],"graph_snapshots":[{"event_id":"sha256:b89c0f9020e63d97138b639b971b3711939c3275f5e5df67f46c50ad38cb6ee4","target":"graph","created_at":"2026-07-05T11:14:25Z","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/2412.10849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A seminal paper published by Ledley and Lusted in 1959 introduced complex clinical diagnostic reasoning cases as the gold standard for the evaluation of expert medical computing systems, a standard that has held ever since. Here, we report the results of a physician evaluation of a large language model (LLM) on challenging clinical cases against a baseline of hundreds of physicians. We conduct five experiments to measure clinical reasoning across differential diagnosis generation, display of diagnostic reasoning, triage differential diagnosis, probabilistic reasoning, and management reasoning,","authors_text":"Adam Rodman, Adrian D. Haimovich, Andrew Olson, Arjun K. Manrai, Christopher Lucas, Daniele Restifo, Daniel J. Morgan, Daniel Restrepo, Eric Horvitz, Ethan Goh, Evelyn Bin Ling, Haadi Mombini, Jason A. Freed, Jason Hom, Jonathan Chen, Liam G. McCoy, Matthew Gwiazdon, Misha Fotoohi, Peter G. Brodeur, Priyank Jain, Raja-Elie Abdulnour, Robert Gallo, Stephanie Cabral, Thomas A. Buckley, Zahir Kanjee","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-14T14:46:18Z","title":"Superhuman performance of a large language model on the reasoning tasks of a physician"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10849","kind":"arxiv","version":3},"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":"sha256:41e86f47f1b5e38ce4aaba13ce038e6ea73f2c679dd087a359f5e6c4bf04a57b","target":"record","created_at":"2026-07-05T11:14:25Z","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":"16cd043f18c26c7f6359b345e238b81856895e717652ee30d07e06c6cf7e1d5b","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-14T14:46:18Z","title_canon_sha256":"4205395cd9be82bef3c9059ddc74189fbbfbf61ce722a17c26a684c4fecb02fd"},"schema_version":"1.0","source":{"id":"2412.10849","kind":"arxiv","version":3}},"canonical_sha256":"ef35e2054799ff8a3060b5d5d3fb3dd70fe5bbef9aa98d43fe2a7f498fe6b25f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef35e2054799ff8a3060b5d5d3fb3dd70fe5bbef9aa98d43fe2a7f498fe6b25f","first_computed_at":"2026-07-05T11:14:25.982249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:25.982249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sTQGMaQA1YMFYMmMpdDNVL5Op4ErhDnV3xX0f2VSDRhqqyLiywCRIMdr/pop2Rj72pkX1c9ZEC+hYteXX1K/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:25.982755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10849","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e86f47f1b5e38ce4aaba13ce038e6ea73f2c679dd087a359f5e6c4bf04a57b","sha256:b89c0f9020e63d97138b639b971b3711939c3275f5e5df67f46c50ad38cb6ee4"],"state_sha256":"09d3a145b1e62a52bc97a5a6b8ad6708e966d4f9192f2fe59c93c99f18765227"}