{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TDXMSYZZEG5CX4UDMAEZYSTNHQ","short_pith_number":"pith:TDXMSYZZ","schema_version":"1.0","canonical_sha256":"98eec9633921ba2bf28360099c4a6d3c0160f9d89e01dad31225f620c74f6a76","source":{"kind":"arxiv","id":"2506.05386","version":3},"attestation_state":"computed","paper":{"title":"Leaps Beyond the Seen: Reinforced Reasoning Augmented Generation for Clinical Notes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengshuai Zhao, Huan Liu, Kun-Ta Chuang, Lo Pang-Yun Ting, Yuan Jee Lim, Yu-Hua Zeng","submitted_at":"2025-06-03T12:59:52Z","abstract_excerpt":"Clinical note generation aims to produce free-text summaries of a patient's condition and diagnostic process, with discharge instructions being a representative long-form example. While recent LLM-based methods pre-trained on general clinical corpora show promise in clinical text generation, they fall short in producing long-form notes from limited patient information. In this paper, we propose ReinRAG, a reinforced reasoning augmented generation (RAG) for long-form discharge instructions based on pre-admission information. ReinRAG retrieves reasoning paths from a medical knowledge graph to pr"},"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":"2506.05386","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T12:59:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"19129f631557b65eb1749708630bc789480d4f0c5e66063e8b3e154ddea001b9","abstract_canon_sha256":"afed1d8dbe8d915296682b4e11bc14d2f7ac6fa6b3d29c919a5db555aba9aab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:28.252621Z","signature_b64":"skjredd5BPMMCywsH14t2bXC+w4SN1u7mRHEHDyiI7r2XqqneoR8KsuLHBInSOFaVFtx2Uh7FCYBZVtE3mqmDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98eec9633921ba2bf28360099c4a6d3c0160f9d89e01dad31225f620c74f6a76","last_reissued_at":"2026-07-05T11:51:28.252124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:28.252124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leaps Beyond the Seen: Reinforced Reasoning Augmented Generation for Clinical Notes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengshuai Zhao, Huan Liu, Kun-Ta Chuang, Lo Pang-Yun Ting, Yuan Jee Lim, Yu-Hua Zeng","submitted_at":"2025-06-03T12:59:52Z","abstract_excerpt":"Clinical note generation aims to produce free-text summaries of a patient's condition and diagnostic process, with discharge instructions being a representative long-form example. While recent LLM-based methods pre-trained on general clinical corpora show promise in clinical text generation, they fall short in producing long-form notes from limited patient information. In this paper, we propose ReinRAG, a reinforced reasoning augmented generation (RAG) for long-form discharge instructions based on pre-admission information. ReinRAG retrieves reasoning paths from a medical knowledge graph to pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05386","kind":"arxiv","version":3},"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/2506.05386/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":"2506.05386","created_at":"2026-07-05T11:51:28.252181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05386v3","created_at":"2026-07-05T11:51:28.252181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05386","created_at":"2026-07-05T11:51:28.252181+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDXMSYZZEG5C","created_at":"2026-07-05T11:51:28.252181+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDXMSYZZEG5CX4UD","created_at":"2026-07-05T11:51:28.252181+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDXMSYZZ","created_at":"2026-07-05T11:51:28.252181+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.01191","citing_title":"Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ","json":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ.json","graph_json":"https://pith.science/api/pith-number/TDXMSYZZEG5CX4UDMAEZYSTNHQ/graph.json","events_json":"https://pith.science/api/pith-number/TDXMSYZZEG5CX4UDMAEZYSTNHQ/events.json","paper":"https://pith.science/paper/TDXMSYZZ"},"agent_actions":{"view_html":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ","download_json":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ.json","view_paper":"https://pith.science/paper/TDXMSYZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05386&json=true","fetch_graph":"https://pith.science/api/pith-number/TDXMSYZZEG5CX4UDMAEZYSTNHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/TDXMSYZZEG5CX4UDMAEZYSTNHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ/action/storage_attestation","attest_author":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ/action/author_attestation","sign_citation":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ/action/citation_signature","submit_replication":"https://pith.science/pith/TDXMSYZZEG5CX4UDMAEZYSTNHQ/action/replication_record"}},"created_at":"2026-07-05T11:51:28.252181+00:00","updated_at":"2026-07-05T11:51:28.252181+00:00"}