{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAB3GZTRDAMIV5TKYKLUPVTKIO","short_pith_number":"pith:FAB3GZTR","schema_version":"1.0","canonical_sha256":"2803b3667118188af66ac29747d66a43a7df23a84d76f5b1a9bc61115c85f7ff","source":{"kind":"arxiv","id":"2508.00669","version":1},"attestation_state":"computed","paper":{"title":"Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaming Ji, Jie Liu, Linlin Shen, Meidan Ding, Shengyuan Liu, Shiyi Zheng, Wenting Chen, Wenxuan Wang, Xiang Li, Yixuan Yuan, Zizhan Ma","submitted_at":"2025-08-01T14:41:31Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning)"},"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":"2508.00669","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T14:41:31Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"392aedbbe59967dcd953920a3700db194a98585635996ab6a3780b5ca3330a59","abstract_canon_sha256":"862530a0b6f8c843b95c83fdd259734028053a8a17d37c30b8bfd6eaa057fbc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:01.138710Z","signature_b64":"aSGYk4O8q8RfTcrReqlD3iZt847Xd6XbtqjEYvdagEx9E69FGTHwzXGol77wP+f6gNKALDSw9GtiP9v3T1U0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2803b3667118188af66ac29747d66a43a7df23a84d76f5b1a9bc61115c85f7ff","last_reissued_at":"2026-07-05T11:47:01.138216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:01.138216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiaming Ji, Jie Liu, Linlin Shen, Meidan Ding, Shengyuan Liu, Shiyi Zheng, Wenting Chen, Wenxuan Wang, Xiang Li, Yixuan Yuan, Zizhan Ma","submitted_at":"2025-08-01T14:41:31Z","abstract_excerpt":"The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00669","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/2508.00669/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":"2508.00669","created_at":"2026-07-05T11:47:01.138280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00669v1","created_at":"2026-07-05T11:47:01.138280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00669","created_at":"2026-07-05T11:47:01.138280+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAB3GZTRDAMI","created_at":"2026-07-05T11:47:01.138280+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAB3GZTRDAMIV5TK","created_at":"2026-07-05T11:47:01.138280+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAB3GZTR","created_at":"2026-07-05T11:47:01.138280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":288,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09584","citing_title":"CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO","json":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO.json","graph_json":"https://pith.science/api/pith-number/FAB3GZTRDAMIV5TKYKLUPVTKIO/graph.json","events_json":"https://pith.science/api/pith-number/FAB3GZTRDAMIV5TKYKLUPVTKIO/events.json","paper":"https://pith.science/paper/FAB3GZTR"},"agent_actions":{"view_html":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO","download_json":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO.json","view_paper":"https://pith.science/paper/FAB3GZTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00669&json=true","fetch_graph":"https://pith.science/api/pith-number/FAB3GZTRDAMIV5TKYKLUPVTKIO/graph.json","fetch_events":"https://pith.science/api/pith-number/FAB3GZTRDAMIV5TKYKLUPVTKIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO/action/storage_attestation","attest_author":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO/action/author_attestation","sign_citation":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO/action/citation_signature","submit_replication":"https://pith.science/pith/FAB3GZTRDAMIV5TKYKLUPVTKIO/action/replication_record"}},"created_at":"2026-07-05T11:47:01.138280+00:00","updated_at":"2026-07-05T11:47:01.138280+00:00"}