{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GGXGBCOMAGQOSUB25JATMDK7VN","short_pith_number":"pith:GGXGBCOM","schema_version":"1.0","canonical_sha256":"31ae6089cc01a0e9503aea41360d5fab725c4ebc1791d236a83ef106c8fa685f","source":{"kind":"arxiv","id":"2311.02271","version":2},"attestation_state":"computed","paper":{"title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nan Zhang, Prasenjit Mitra, Rui Zhang, Wu Guo, Yusen Zhang","submitted_at":"2023-11-03T23:25:53Z","abstract_excerpt":"Summaries of medical text shall be faithful by being consistent and factual with source inputs, which is an important but understudied topic for safety and efficiency in healthcare. In this paper, we investigate and improve faithfulness in summarization on a broad range of medical summarization tasks. Our investigation reveals that current summarization models often produce unfaithful outputs for medical input text. We then introduce FaMeSumm, a framework to improve faithfulness by fine-tuning pre-trained language models based on medical knowledge. FaMeSumm performs contrastive learning on des"},"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":"2311.02271","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-03T23:25:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0c7b2c5c1e55ea99d535aa21c5fb44a56b7f19c1b744524f76244ca7069e606e","abstract_canon_sha256":"858543b4ad49f3a056c9f258ca1bc786bf445f740b391cde536a2d23324ccb63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:51.012838Z","signature_b64":"cajfMj1vH6Ww5jPngbzg5wDRzsiKQf17VE4wuNvwkhTxwT5EpKoTHG101Ep4XBXy5KcFPBcn7q4voZG2ea8wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31ae6089cc01a0e9503aea41360d5fab725c4ebc1791d236a83ef106c8fa685f","last_reissued_at":"2026-07-05T07:10:51.012430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:51.012430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FaMeSumm: Investigating and Improving Faithfulness of Medical Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Nan Zhang, Prasenjit Mitra, Rui Zhang, Wu Guo, Yusen Zhang","submitted_at":"2023-11-03T23:25:53Z","abstract_excerpt":"Summaries of medical text shall be faithful by being consistent and factual with source inputs, which is an important but understudied topic for safety and efficiency in healthcare. In this paper, we investigate and improve faithfulness in summarization on a broad range of medical summarization tasks. Our investigation reveals that current summarization models often produce unfaithful outputs for medical input text. We then introduce FaMeSumm, a framework to improve faithfulness by fine-tuning pre-trained language models based on medical knowledge. FaMeSumm performs contrastive learning on des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02271","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/2311.02271/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":"2311.02271","created_at":"2026-07-05T07:10:51.012487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02271v2","created_at":"2026-07-05T07:10:51.012487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02271","created_at":"2026-07-05T07:10:51.012487+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGXGBCOMAGQO","created_at":"2026-07-05T07:10:51.012487+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGXGBCOMAGQOSUB2","created_at":"2026-07-05T07:10:51.012487+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGXGBCOM","created_at":"2026-07-05T07:10:51.012487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05319","citing_title":"LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN","json":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN.json","graph_json":"https://pith.science/api/pith-number/GGXGBCOMAGQOSUB25JATMDK7VN/graph.json","events_json":"https://pith.science/api/pith-number/GGXGBCOMAGQOSUB25JATMDK7VN/events.json","paper":"https://pith.science/paper/GGXGBCOM"},"agent_actions":{"view_html":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN","download_json":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN.json","view_paper":"https://pith.science/paper/GGXGBCOM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02271&json=true","fetch_graph":"https://pith.science/api/pith-number/GGXGBCOMAGQOSUB25JATMDK7VN/graph.json","fetch_events":"https://pith.science/api/pith-number/GGXGBCOMAGQOSUB25JATMDK7VN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN/action/storage_attestation","attest_author":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN/action/author_attestation","sign_citation":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN/action/citation_signature","submit_replication":"https://pith.science/pith/GGXGBCOMAGQOSUB25JATMDK7VN/action/replication_record"}},"created_at":"2026-07-05T07:10:51.012487+00:00","updated_at":"2026-07-05T07:10:51.012487+00:00"}