{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5SRZDBSGVC77BEYKMQY72NWGIQ","short_pith_number":"pith:5SRZDBSG","schema_version":"1.0","canonical_sha256":"eca3918646a8bff0930a6431fd36c6441157d28634eb7effadf8bfe7b30ede61","source":{"kind":"arxiv","id":"2307.08922","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models Perform Diagnostic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Kuang Wu, Hsin-Hsi Chen, Wei-Lin Chen","submitted_at":"2023-07-18T01:43:00Z","abstract_excerpt":"We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demonstrate that by simply prompting large language models trained only on general text corpus with two DR-CoT exemplars, the diagnostic accuracy improves by 15% comparing to standard prompting. Moreover, the gap reaches a pronounced 18% in out-domain settings. Our findings suggest expert-knowledge reasoning in large language models can be elicited through proper"},"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":"2307.08922","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-18T01:43:00Z","cross_cats_sorted":[],"title_canon_sha256":"dcebcf8254d3fe6a602765c595ae26b6af8f063214e139cd97245b24ed86c477","abstract_canon_sha256":"97c91e8fc9534e2f34731b91ebf553c453da9376f992193e7e1f4631f1e8dc04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:36.154825Z","signature_b64":"tXeCIhyUpoZMAV07VvsHySHhJiXO3srHrf2bPDNC+76IAgjGRj2fDkxyf5b6vN2wW5Lg916SypdFQSsdkKnQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eca3918646a8bff0930a6431fd36c6441157d28634eb7effadf8bfe7b30ede61","last_reissued_at":"2026-07-05T06:31:36.154372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:36.154372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Perform Diagnostic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng-Kuang Wu, Hsin-Hsi Chen, Wei-Lin Chen","submitted_at":"2023-07-18T01:43:00Z","abstract_excerpt":"We explore the extension of chain-of-thought (CoT) prompting to medical reasoning for the task of automatic diagnosis. Motivated by doctors' underlying reasoning process, we present Diagnostic-Reasoning CoT (DR-CoT). Empirical results demonstrate that by simply prompting large language models trained only on general text corpus with two DR-CoT exemplars, the diagnostic accuracy improves by 15% comparing to standard prompting. Moreover, the gap reaches a pronounced 18% in out-domain settings. Our findings suggest expert-knowledge reasoning in large language models can be elicited through proper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08922","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/2307.08922/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":"2307.08922","created_at":"2026-07-05T06:31:36.154430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08922v1","created_at":"2026-07-05T06:31:36.154430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08922","created_at":"2026-07-05T06:31:36.154430+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SRZDBSGVC77","created_at":"2026-07-05T06:31:36.154430+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SRZDBSGVC77BEYK","created_at":"2026-07-05T06:31:36.154430+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SRZDBSG","created_at":"2026-07-05T06:31:36.154430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.20325","citing_title":"GUARD: Guideline Upholding Test through Adaptive Role-play and Jailbreak Diagnostics for LLMs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08559","citing_title":"Medical Reasoning with Large Language Models: A Survey and MR-Bench","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ","json":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ.json","graph_json":"https://pith.science/api/pith-number/5SRZDBSGVC77BEYKMQY72NWGIQ/graph.json","events_json":"https://pith.science/api/pith-number/5SRZDBSGVC77BEYKMQY72NWGIQ/events.json","paper":"https://pith.science/paper/5SRZDBSG"},"agent_actions":{"view_html":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ","download_json":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ.json","view_paper":"https://pith.science/paper/5SRZDBSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08922&json=true","fetch_graph":"https://pith.science/api/pith-number/5SRZDBSGVC77BEYKMQY72NWGIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5SRZDBSGVC77BEYKMQY72NWGIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ/action/storage_attestation","attest_author":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ/action/author_attestation","sign_citation":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ/action/citation_signature","submit_replication":"https://pith.science/pith/5SRZDBSGVC77BEYKMQY72NWGIQ/action/replication_record"}},"created_at":"2026-07-05T06:31:36.154430+00:00","updated_at":"2026-07-05T06:31:36.154430+00:00"}