{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FMNFMRH57VTJJVZU34WC6LAT5B","short_pith_number":"pith:FMNFMRH5","schema_version":"1.0","canonical_sha256":"2b1a5644fdfd6694d734df2c2f2c13e871c54a0f3e1356b2569f4418e497dbac","source":{"kind":"arxiv","id":"2507.05319","version":1},"attestation_state":"computed","paper":{"title":"LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyang Zhong, Cheng Yuan, Jiacheng Wang, Tong Ruan, Weiyan Zhang, Xinkai Rui, Yawei Fan, Yongqi Fan","submitted_at":"2025-07-07T15:25:52Z","abstract_excerpt":"Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid sources. In addition, electronic medical records (EMRs) typically consist of long-form data, making it challenging for LLMs to attribute the generated content to the sources. To address these challenges, we propose LCDS, a Logic-Controlled Discharge Summary generation system. LCDS constructs a source mapping table by calculating textual similarity between EMRs and"},"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":"2507.05319","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T15:25:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cf6367827812106fa11c5e76f07cafbced436cf5c2b0b93490d0b47812dcbf45","abstract_canon_sha256":"ab5020f161800d5efda19eb6d557d993a5802192a8c96b6ad39cc9d2aa6f3936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:28.228497Z","signature_b64":"hwbHTkaotqRNeVplGtr7+S9sf/veESVWfOyzKgOoIcFXjl1YrgcJlJjeVTbSD0PZ20mks2c5IcRoXZTFBAhLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b1a5644fdfd6694d734df2c2f2c13e871c54a0f3e1356b2569f4418e497dbac","last_reissued_at":"2026-07-05T11:33:28.228007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:28.228007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyang Zhong, Cheng Yuan, Jiacheng Wang, Tong Ruan, Weiyan Zhang, Xinkai Rui, Yawei Fan, Yongqi Fan","submitted_at":"2025-07-07T15:25:52Z","abstract_excerpt":"Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid sources. In addition, electronic medical records (EMRs) typically consist of long-form data, making it challenging for LLMs to attribute the generated content to the sources. To address these challenges, we propose LCDS, a Logic-Controlled Discharge Summary generation system. LCDS constructs a source mapping table by calculating textual similarity between EMRs and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05319","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/2507.05319/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":"2507.05319","created_at":"2026-07-05T11:33:28.228065+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05319v1","created_at":"2026-07-05T11:33:28.228065+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05319","created_at":"2026-07-05T11:33:28.228065+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMNFMRH57VTJ","created_at":"2026-07-05T11:33:28.228065+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMNFMRH57VTJJVZU","created_at":"2026-07-05T11:33:28.228065+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMNFMRH5","created_at":"2026-07-05T11:33:28.228065+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/FMNFMRH57VTJJVZU34WC6LAT5B","json":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B.json","graph_json":"https://pith.science/api/pith-number/FMNFMRH57VTJJVZU34WC6LAT5B/graph.json","events_json":"https://pith.science/api/pith-number/FMNFMRH57VTJJVZU34WC6LAT5B/events.json","paper":"https://pith.science/paper/FMNFMRH5"},"agent_actions":{"view_html":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B","download_json":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B.json","view_paper":"https://pith.science/paper/FMNFMRH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05319&json=true","fetch_graph":"https://pith.science/api/pith-number/FMNFMRH57VTJJVZU34WC6LAT5B/graph.json","fetch_events":"https://pith.science/api/pith-number/FMNFMRH57VTJJVZU34WC6LAT5B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B/action/storage_attestation","attest_author":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B/action/author_attestation","sign_citation":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B/action/citation_signature","submit_replication":"https://pith.science/pith/FMNFMRH57VTJJVZU34WC6LAT5B/action/replication_record"}},"created_at":"2026-07-05T11:33:28.228065+00:00","updated_at":"2026-07-05T11:33:28.228065+00:00"}