{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZAWB77MZE7WBOAXW6TJSZUVTOW","short_pith_number":"pith:ZAWB77MZ","schema_version":"1.0","canonical_sha256":"c82c1ffd9927ec1702f6f4d32cd2b375973c2da7deae3cbd89e411b365d5b95e","source":{"kind":"arxiv","id":"2411.05897","version":2},"attestation_state":"computed","paper":{"title":"Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","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","submitted_at":"2024-11-08T15:50:19Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.05897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-08T15:50:19Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"07d00bf42503c170774925f7710223db98056942f1f1a973d8cc4f92e67abfe8","abstract_canon_sha256":"4338b8f9060e009588c2c6fa1e6d465edc7fcf62e815e203a67dcf650db72a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:06.511110Z","signature_b64":"bmPOZFUxU12Ggs70ewJNvjQAo3+s3Zac9TKxEFpdzCPnQUPCI/Tr03n8va4mOHukKLOkrScRWLuMOiq1EfxcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c82c1ffd9927ec1702f6f4d32cd2b375973c2da7deae3cbd89e411b365d5b95e","last_reissued_at":"2026-07-05T10:37:06.510478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:06.510478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Humans and Large Language Models in Clinical Decision Support: A Study with Medical Calculators","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","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","submitted_at":"2024-11-08T15:50:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05897","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.05897/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.05897","created_at":"2026-07-05T10:37:06.510545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05897v2","created_at":"2026-07-05T10:37:06.510545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05897","created_at":"2026-07-05T10:37:06.510545+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAWB77MZE7WB","created_at":"2026-07-05T10:37:06.510545+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAWB77MZE7WBOAXW","created_at":"2026-07-05T10:37:06.510545+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAWB77MZ","created_at":"2026-07-05T10:37:06.510545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW","json":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW.json","graph_json":"https://pith.science/api/pith-number/ZAWB77MZE7WBOAXW6TJSZUVTOW/graph.json","events_json":"https://pith.science/api/pith-number/ZAWB77MZE7WBOAXW6TJSZUVTOW/events.json","paper":"https://pith.science/paper/ZAWB77MZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW","download_json":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW.json","view_paper":"https://pith.science/paper/ZAWB77MZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05897&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAWB77MZE7WBOAXW6TJSZUVTOW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAWB77MZE7WBOAXW6TJSZUVTOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW/action/storage_attestation","attest_author":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW/action/author_attestation","sign_citation":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW/action/citation_signature","submit_replication":"https://pith.science/pith/ZAWB77MZE7WBOAXW6TJSZUVTOW/action/replication_record"}},"created_at":"2026-07-05T10:37:06.510545+00:00","updated_at":"2026-07-05T10:37:06.510545+00:00"}