{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZAWB77MZE7WBOAXW6TJSZUVTOW","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":"4338b8f9060e009588c2c6fa1e6d465edc7fcf62e815e203a67dcf650db72a38","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T15:50:19Z","title_canon_sha256":"07d00bf42503c170774925f7710223db98056942f1f1a973d8cc4f92e67abfe8"},"schema_version":"1.0","source":{"id":"2411.05897","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05897","created_at":"2026-07-05T10:37:06Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05897v2","created_at":"2026-07-05T10:37:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05897","created_at":"2026-07-05T10:37:06Z"},{"alias_kind":"pith_short_12","alias_value":"ZAWB77MZE7WB","created_at":"2026-07-05T10:37:06Z"},{"alias_kind":"pith_short_16","alias_value":"ZAWB77MZE7WBOAXW","created_at":"2026-07-05T10:37:06Z"},{"alias_kind":"pith_short_8","alias_value":"ZAWB77MZ","created_at":"2026-07-05T10:37:06Z"}],"graph_snapshots":[{"event_id":"sha256:8aaa1df47e7da38d7d269ff7996d77180a55b3cc8525a67d0d67327be32b9879","target":"graph","created_at":"2026-07-05T10:37:06Z","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/2411.05897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although large language models (LLMs) have been assessed for general medical knowledge using licensing exams, their ability to support clinical decision-making, such as selecting medical calculators, remains uncertain. We assessed nine LLMs, including open-source, proprietary, and domain-specific models, with 1,009 multiple-choice question-answer pairs across 35 clinical calculators and compared LLMs to humans on a subset of questions. While the highest-performing LLM, OpenAI o1, provided an answer accuracy of 66.0% (CI: 56.7-75.3%) on the subset of 100 questions, two human annotators nominall","authors_text":"Aidan Gilson, Aidong Zhang, Guangzhi Xiong, Joey Chan, Nicholas Wan, Qiao Jin, Qingyu Chen, R. Andrew Taylor, Reid McMurry, Serina Applebaum, Zhiyong Lu","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T15:50:19Z","title":"Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05897","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:de53237fbea1d932dfef20aedf4d1d966e1fdfba8ec8eacbe900b224376cb18c","target":"record","created_at":"2026-07-05T10:37:06Z","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":"4338b8f9060e009588c2c6fa1e6d465edc7fcf62e815e203a67dcf650db72a38","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T15:50:19Z","title_canon_sha256":"07d00bf42503c170774925f7710223db98056942f1f1a973d8cc4f92e67abfe8"},"schema_version":"1.0","source":{"id":"2411.05897","kind":"arxiv","version":2}},"canonical_sha256":"c82c1ffd9927ec1702f6f4d32cd2b375973c2da7deae3cbd89e411b365d5b95e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c82c1ffd9927ec1702f6f4d32cd2b375973c2da7deae3cbd89e411b365d5b95e","first_computed_at":"2026-07-05T10:37:06.510478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:06.510478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bmPOZFUxU12Ggs70ewJNvjQAo3+s3Zac9TKxEFpdzCPnQUPCI/Tr03n8va4mOHukKLOkrScRWLuMOiq1EfxcDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:06.511110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05897","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de53237fbea1d932dfef20aedf4d1d966e1fdfba8ec8eacbe900b224376cb18c","sha256:8aaa1df47e7da38d7d269ff7996d77180a55b3cc8525a67d0d67327be32b9879"],"state_sha256":"1bf7495af8c229013710a47c8bad47ace4f303b56cb0af957d0c17eea178a68f"}