{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XSKPLRKA7TMISTJW5AQXTNROBV","short_pith_number":"pith:XSKPLRKA","schema_version":"1.0","canonical_sha256":"bc94f5c540fcd8894d36e82179b62e0d495afe884d1b701040830587067c019c","source":{"kind":"arxiv","id":"2409.18170","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Brian Patterson, Cherodeep Goswami, Elliot First, Emma Croxford, Frank J. Liao, Graham Wills, Karen K. Wong, Majid Afshar, Nicholas Pellegrino, Yanjun Gao","submitted_at":"2024-09-26T17:58:26Z","abstract_excerpt":"Large Language Models have advanced clinical Natural Language Generation, creating opportunities to manage the volume of medical text. However, the high-stakes nature of medicine requires reliable evaluation, which remains a challenge. In this narrative review, we assess the current evaluation state for clinical summarization tasks and propose future directions to address the resource constraints of expert human evaluation."},"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":"2409.18170","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T17:58:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c3b01f4429da67fdcd7be45ff32b1f2e528c8451c1b8d5ab08161c8fc56af8b8","abstract_canon_sha256":"08ee4d675eb1e5910930ac8a49c3de9235b7434f97230cb36ea9dc401d6b4865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:32.039369Z","signature_b64":"W5hewRb0jwf+0craUqbB9t1fqHLCcSIdRJB1E7buUxg+8gZUxiwuR5hdtrzh+qZXbJ2ftzEnEPeQ7rSKkYyTBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc94f5c540fcd8894d36e82179b62e0d495afe884d1b701040830587067c019c","last_reissued_at":"2026-07-05T09:12:32.038886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:32.038886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Brian Patterson, Cherodeep Goswami, Elliot First, Emma Croxford, Frank J. Liao, Graham Wills, Karen K. Wong, Majid Afshar, Nicholas Pellegrino, Yanjun Gao","submitted_at":"2024-09-26T17:58:26Z","abstract_excerpt":"Large Language Models have advanced clinical Natural Language Generation, creating opportunities to manage the volume of medical text. However, the high-stakes nature of medicine requires reliable evaluation, which remains a challenge. In this narrative review, we assess the current evaluation state for clinical summarization tasks and propose future directions to address the resource constraints of expert human evaluation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18170","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/2409.18170/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":"2409.18170","created_at":"2026-07-05T09:12:32.038944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18170v1","created_at":"2026-07-05T09:12:32.038944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18170","created_at":"2026-07-05T09:12:32.038944+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSKPLRKA7TMI","created_at":"2026-07-05T09:12:32.038944+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSKPLRKA7TMISTJW","created_at":"2026-07-05T09:12:32.038944+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSKPLRKA","created_at":"2026-07-05T09:12:32.038944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV","json":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV.json","graph_json":"https://pith.science/api/pith-number/XSKPLRKA7TMISTJW5AQXTNROBV/graph.json","events_json":"https://pith.science/api/pith-number/XSKPLRKA7TMISTJW5AQXTNROBV/events.json","paper":"https://pith.science/paper/XSKPLRKA"},"agent_actions":{"view_html":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV","download_json":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV.json","view_paper":"https://pith.science/paper/XSKPLRKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18170&json=true","fetch_graph":"https://pith.science/api/pith-number/XSKPLRKA7TMISTJW5AQXTNROBV/graph.json","fetch_events":"https://pith.science/api/pith-number/XSKPLRKA7TMISTJW5AQXTNROBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV/action/storage_attestation","attest_author":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV/action/author_attestation","sign_citation":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV/action/citation_signature","submit_replication":"https://pith.science/pith/XSKPLRKA7TMISTJW5AQXTNROBV/action/replication_record"}},"created_at":"2026-07-05T09:12:32.038944+00:00","updated_at":"2026-07-05T09:12:32.038944+00:00"}