{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZOGW2EZ5CHYNGSAJCFDUYMUO33","short_pith_number":"pith:ZOGW2EZ5","schema_version":"1.0","canonical_sha256":"cb8d6d133d11f0d3480911474c328edeed9dfc46e28f94f1cfd747f38cd73cf4","source":{"kind":"arxiv","id":"2410.12858","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models for Medical OSCE Assessment: A Novel Approach to Transcript Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ameer Hamza Shakur, Andrew R. Jamieson, Daniel J. Scott, David Hein, Krystle K. Campbell, Michael J. Holcomb, Shinyoung Kang, Thomas O. Dalton","submitted_at":"2024-10-11T19:16:03Z","abstract_excerpt":"Grading Objective Structured Clinical Examinations (OSCEs) is a time-consuming and expensive process, traditionally requiring extensive manual effort from human experts. In this study, we explore the potential of Large Language Models (LLMs) to assess skills related to medical student communication. We analyzed 2,027 video-recorded OSCE examinations from the University of Texas Southwestern Medical Center (UTSW), spanning four years (2019-2022), and several different medical cases or \"stations.\" Specifically, our focus was on evaluating students' ability to summarize patients' medical history:"},"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":"2410.12858","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-11T19:16:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"167c30f3dbf8235cb66d8451820f32957c5a238329b247adbfaaa7dbd94993f4","abstract_canon_sha256":"1854a20d9a79405a61d21fa30db671b349e1a6475a37c02500b255c0523645dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:52.024636Z","signature_b64":"5iQmFmebAumdhNrmmaQy4cljMR7YTHVx8j7vuzzGF1T/DEiUVZsycT8gic7bPPCHr34kYmnH6CVxcdmPndhwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb8d6d133d11f0d3480911474c328edeed9dfc46e28f94f1cfd747f38cd73cf4","last_reissued_at":"2026-07-05T09:21:52.024156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:52.024156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models for Medical OSCE Assessment: A Novel Approach to Transcript Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ameer Hamza Shakur, Andrew R. Jamieson, Daniel J. Scott, David Hein, Krystle K. Campbell, Michael J. Holcomb, Shinyoung Kang, Thomas O. Dalton","submitted_at":"2024-10-11T19:16:03Z","abstract_excerpt":"Grading Objective Structured Clinical Examinations (OSCEs) is a time-consuming and expensive process, traditionally requiring extensive manual effort from human experts. In this study, we explore the potential of Large Language Models (LLMs) to assess skills related to medical student communication. We analyzed 2,027 video-recorded OSCE examinations from the University of Texas Southwestern Medical Center (UTSW), spanning four years (2019-2022), and several different medical cases or \"stations.\" Specifically, our focus was on evaluating students' ability to summarize patients' medical history:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12858","kind":"arxiv","version":1},"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/2410.12858/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":"2410.12858","created_at":"2026-07-05T09:21:52.024212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12858v1","created_at":"2026-07-05T09:21:52.024212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12858","created_at":"2026-07-05T09:21:52.024212+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOGW2EZ5CHYN","created_at":"2026-07-05T09:21:52.024212+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOGW2EZ5CHYNGSAJ","created_at":"2026-07-05T09:21:52.024212+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOGW2EZ5","created_at":"2026-07-05T09:21:52.024212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28526","citing_title":"A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08126","citing_title":"LLM-Based Data Generation and Clinical Skills Evaluation for Low-Resource French OSCEs","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33","json":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33.json","graph_json":"https://pith.science/api/pith-number/ZOGW2EZ5CHYNGSAJCFDUYMUO33/graph.json","events_json":"https://pith.science/api/pith-number/ZOGW2EZ5CHYNGSAJCFDUYMUO33/events.json","paper":"https://pith.science/paper/ZOGW2EZ5"},"agent_actions":{"view_html":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33","download_json":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33.json","view_paper":"https://pith.science/paper/ZOGW2EZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12858&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOGW2EZ5CHYNGSAJCFDUYMUO33/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOGW2EZ5CHYNGSAJCFDUYMUO33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33/action/storage_attestation","attest_author":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33/action/author_attestation","sign_citation":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33/action/citation_signature","submit_replication":"https://pith.science/pith/ZOGW2EZ5CHYNGSAJCFDUYMUO33/action/replication_record"}},"created_at":"2026-07-05T09:21:52.024212+00:00","updated_at":"2026-07-05T09:21:52.024212+00:00"}