{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZTNJ7IVEDPDLTK4NHE23452OMN","short_pith_number":"pith:ZTNJ7IVE","schema_version":"1.0","canonical_sha256":"ccda9fa2a41bc6b9ab8d3935be774e634e4742524dbf3c0a9d3a0918de614e94","source":{"kind":"arxiv","id":"2402.02008","version":1},"attestation_state":"computed","paper":{"title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ally Cassasola, Angela Zhang, Daniel E. Ho, Eric Wu, James Zou, Kevin Wei, Kevin Wu, Patricia Shi Riantawan, Sith Riantawan, Teresa Nguyen","submitted_at":"2024-02-03T03:44:57Z","abstract_excerpt":"Large language models (LLMs) are currently being used to answer medical questions across a variety of clinical domains. Recent top-performing commercial LLMs, in particular, are also capable of citing sources to support their responses. In this paper, we ask: do the sources that LLMs generate actually support the claims that they make? To answer this, we propose three contributions. First, as expert medical annotations are an expensive and time-consuming bottleneck for scalable evaluation, we demonstrate that GPT-4 is highly accurate in validating source relevance, agreeing 88% of the time wit"},"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":"2402.02008","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T03:44:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8ae533cde398de9e2c9dd16e9639a5d8a35c56034912947d08682203b5efc99","abstract_canon_sha256":"88c42ca177cd0b4d1b2ffcf4fe4056592aef73b400be0442a1b69c9fce3cce83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:09.676245Z","signature_b64":"lQMw6UUIyM0NDw3zrRGTz3nvKAz2euK46JXSCiP57djYLUcPYxNnY8zFRM7ZioMRFhob86ywZwNgkRJ1EfhBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccda9fa2a41bc6b9ab8d3935be774e634e4742524dbf3c0a9d3a0918de614e94","last_reissued_at":"2026-07-05T07:41:09.675773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:09.675773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ally Cassasola, Angela Zhang, Daniel E. Ho, Eric Wu, James Zou, Kevin Wei, Kevin Wu, Patricia Shi Riantawan, Sith Riantawan, Teresa Nguyen","submitted_at":"2024-02-03T03:44:57Z","abstract_excerpt":"Large language models (LLMs) are currently being used to answer medical questions across a variety of clinical domains. Recent top-performing commercial LLMs, in particular, are also capable of citing sources to support their responses. In this paper, we ask: do the sources that LLMs generate actually support the claims that they make? To answer this, we propose three contributions. First, as expert medical annotations are an expensive and time-consuming bottleneck for scalable evaluation, we demonstrate that GPT-4 is highly accurate in validating source relevance, agreeing 88% of the time wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02008","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/2402.02008/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":"2402.02008","created_at":"2026-07-05T07:41:09.675827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.02008v1","created_at":"2026-07-05T07:41:09.675827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02008","created_at":"2026-07-05T07:41:09.675827+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTNJ7IVEDPDL","created_at":"2026-07-05T07:41:09.675827+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTNJ7IVEDPDLTK4N","created_at":"2026-07-05T07:41:09.675827+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTNJ7IVE","created_at":"2026-07-05T07:41:09.675827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22728","citing_title":"When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04990","citing_title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04990","citing_title":"From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2504.07738","citing_title":"Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18416","citing_title":"Capabilities of Gemini Models in Medicine","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19429","citing_title":"Discerning Authorship in Online Health Communities: Experience, Trust, and Transparency Implications for Moderating AI","ref_index":86,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN","json":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN.json","graph_json":"https://pith.science/api/pith-number/ZTNJ7IVEDPDLTK4NHE23452OMN/graph.json","events_json":"https://pith.science/api/pith-number/ZTNJ7IVEDPDLTK4NHE23452OMN/events.json","paper":"https://pith.science/paper/ZTNJ7IVE"},"agent_actions":{"view_html":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN","download_json":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN.json","view_paper":"https://pith.science/paper/ZTNJ7IVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.02008&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTNJ7IVEDPDLTK4NHE23452OMN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTNJ7IVEDPDLTK4NHE23452OMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN/action/storage_attestation","attest_author":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN/action/author_attestation","sign_citation":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN/action/citation_signature","submit_replication":"https://pith.science/pith/ZTNJ7IVEDPDLTK4NHE23452OMN/action/replication_record"}},"created_at":"2026-07-05T07:41:09.675827+00:00","updated_at":"2026-07-05T07:41:09.675827+00:00"}