{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZTNJ7IVEDPDLTK4NHE23452OMN","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":"88c42ca177cd0b4d1b2ffcf4fe4056592aef73b400be0442a1b69c9fce3cce83","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T03:44:57Z","title_canon_sha256":"c8ae533cde398de9e2c9dd16e9639a5d8a35c56034912947d08682203b5efc99"},"schema_version":"1.0","source":{"id":"2402.02008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02008","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02008v1","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02008","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"ZTNJ7IVEDPDL","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_16","alias_value":"ZTNJ7IVEDPDLTK4N","created_at":"2026-07-05T07:41:09Z"},{"alias_kind":"pith_short_8","alias_value":"ZTNJ7IVE","created_at":"2026-07-05T07:41:09Z"}],"graph_snapshots":[{"event_id":"sha256:2f8d3c550692ad367aa65cb283c92161405c55fcafbce59ee5e75911f46ca64f","target":"graph","created_at":"2026-07-05T07:41:09Z","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/2402.02008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ally Cassasola, Angela Zhang, Daniel E. Ho, Eric Wu, James Zou, Kevin Wei, Kevin Wu, Patricia Shi Riantawan, Sith Riantawan, Teresa Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T03:44:57Z","title":"How well do LLMs cite relevant medical references? An evaluation framework and analyses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02008","kind":"arxiv","version":1},"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":"sha256:8c205241009cdff925ab51d599ab0eba700348b6b5786955a207a2150511bb42","target":"record","created_at":"2026-07-05T07:41:09Z","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":"88c42ca177cd0b4d1b2ffcf4fe4056592aef73b400be0442a1b69c9fce3cce83","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-03T03:44:57Z","title_canon_sha256":"c8ae533cde398de9e2c9dd16e9639a5d8a35c56034912947d08682203b5efc99"},"schema_version":"1.0","source":{"id":"2402.02008","kind":"arxiv","version":1}},"canonical_sha256":"ccda9fa2a41bc6b9ab8d3935be774e634e4742524dbf3c0a9d3a0918de614e94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccda9fa2a41bc6b9ab8d3935be774e634e4742524dbf3c0a9d3a0918de614e94","first_computed_at":"2026-07-05T07:41:09.675773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:09.675773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lQMw6UUIyM0NDw3zrRGTz3nvKAz2euK46JXSCiP57djYLUcPYxNnY8zFRM7ZioMRFhob86ywZwNgkRJ1EfhBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:09.676245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c205241009cdff925ab51d599ab0eba700348b6b5786955a207a2150511bb42","sha256:2f8d3c550692ad367aa65cb283c92161405c55fcafbce59ee5e75911f46ca64f"],"state_sha256":"68baa4ab498b064714a0490cdc36caa64c544c7f84e0da42f0f55146cfa2ccf7"}