{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TB2SDYXPBYXIYEPKBUAR6M62OU","short_pith_number":"pith:TB2SDYXP","schema_version":"1.0","canonical_sha256":"987521e2ef0e2e8c11ea0d011f33da750ec326d3cb96ba8ba4c51e6413a5ae0b","source":{"kind":"arxiv","id":"2509.05878","version":1},"attestation_state":"computed","paper":{"title":"MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Swaminathan, April S. Liang, Asad Aali, Christina F. Lin, Emily Alsentzer, Fateme N. Haredasht, Fran\\c{c}ois Grolleau, Jason Hom, Jingkun Yang, Jonathan H. Chen, Kameron C. Black, Kevin Schulman, Natasha Z. Steele, Nigam H. Shah, Philip Chung, Stephen P. Ma, Thomas Lew, Timothy Keyes, Tridu Huynh, Weihan Chu","submitted_at":"2025-09-07T00:41:47Z","abstract_excerpt":"Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an \"LLM Jury\"--a multi-LLM majority vote--assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-qua"},"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":"2509.05878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T00:41:47Z","cross_cats_sorted":[],"title_canon_sha256":"3115aaaa52ab0fb09b76c9e8d75c3de3078756b25a448b2dbb1a6991fdb89438","abstract_canon_sha256":"2ab0fa343c5788e5230bddf77681c0256072c4f535e5a73263ac9c5d7aa5ac12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:25.739874Z","signature_b64":"BTgn8lWiXnAq92zwiE+ldfbXElxt4AF8uFWHm14+4OrqSFHYA5jOcQWk8szyvLczVD6+3aUhm6gVmdK6I+KsAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"987521e2ef0e2e8c11ea0d011f33da750ec326d3cb96ba8ba4c51e6413a5ae0b","last_reissued_at":"2026-07-05T12:06:25.739263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:25.739263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akshay Swaminathan, April S. Liang, Asad Aali, Christina F. Lin, Emily Alsentzer, Fateme N. Haredasht, Fran\\c{c}ois Grolleau, Jason Hom, Jingkun Yang, Jonathan H. Chen, Kameron C. Black, Kevin Schulman, Natasha Z. Steele, Nigam H. Shah, Philip Chung, Stephen P. Ma, Thomas Lew, Timothy Keyes, Tridu Huynh, Weihan Chu","submitted_at":"2025-09-07T00:41:47Z","abstract_excerpt":"Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an \"LLM Jury\"--a multi-LLM majority vote--assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-qua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05878","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/2509.05878/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":"2509.05878","created_at":"2026-07-05T12:06:25.739341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05878v1","created_at":"2026-07-05T12:06:25.739341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05878","created_at":"2026-07-05T12:06:25.739341+00:00"},{"alias_kind":"pith_short_12","alias_value":"TB2SDYXPBYXI","created_at":"2026-07-05T12:06:25.739341+00:00"},{"alias_kind":"pith_short_16","alias_value":"TB2SDYXPBYXIYEPK","created_at":"2026-07-05T12:06:25.739341+00:00"},{"alias_kind":"pith_short_8","alias_value":"TB2SDYXP","created_at":"2026-07-05T12:06:25.739341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08969","citing_title":"CARE: A Conformal Safety Layer for Medical Summarization","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU","json":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU.json","graph_json":"https://pith.science/api/pith-number/TB2SDYXPBYXIYEPKBUAR6M62OU/graph.json","events_json":"https://pith.science/api/pith-number/TB2SDYXPBYXIYEPKBUAR6M62OU/events.json","paper":"https://pith.science/paper/TB2SDYXP"},"agent_actions":{"view_html":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU","download_json":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU.json","view_paper":"https://pith.science/paper/TB2SDYXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05878&json=true","fetch_graph":"https://pith.science/api/pith-number/TB2SDYXPBYXIYEPKBUAR6M62OU/graph.json","fetch_events":"https://pith.science/api/pith-number/TB2SDYXPBYXIYEPKBUAR6M62OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU/action/storage_attestation","attest_author":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU/action/author_attestation","sign_citation":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU/action/citation_signature","submit_replication":"https://pith.science/pith/TB2SDYXPBYXIYEPKBUAR6M62OU/action/replication_record"}},"created_at":"2026-07-05T12:06:25.739341+00:00","updated_at":"2026-07-05T12:06:25.739341+00:00"}