{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C2LEHLDI33K7CERO5ZSU7MVZR2","short_pith_number":"pith:C2LEHLDI","schema_version":"1.0","canonical_sha256":"169643ac68ded5f1122eee654fb2b98ebce2cc3eccaf39bd9d981a82336d1a14","source":{"kind":"arxiv","id":"2303.14070","version":5},"attestation_state":"computed","paper":{"title":"ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Zhang, Ruilong Dan, Steve Jiang, You Zhang, Yunxiang Li, Zihan Li","submitted_at":"2023-03-24T15:29:16Z","abstract_excerpt":"The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a specialized language model with enhanced accuracy in medical advice. We achieved this by adapting and refining the large language model meta-AI (LLaMA) using a large dataset of 100,000 patient-doctor dialogues sourced from a widely used online medical consultation platform. These conversations were cleaned and anonymized to respect privacy concerns. In addition to the model refinement, we incorporated a self-directed informat"},"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":"2303.14070","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-24T15:29:16Z","cross_cats_sorted":[],"title_canon_sha256":"56a96ee4cb921b1cb72400ef5211d732b4d984cb0c12299869e5d1d4a044e7af","abstract_canon_sha256":"a9a8bb797aa63579bf18997db651f99dca2fdcf3975b9bc2f01e9148a6672bd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:11.833769Z","signature_b64":"DzmNo24y/r/abr4vmauMEax56LugcLB5CWZ8BCPCCF+k+wPEplabbSaE8i4hB/fjwghffSNqZ3W3MepKIxUzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"169643ac68ded5f1122eee654fb2b98ebce2cc3eccaf39bd9d981a82336d1a14","last_reissued_at":"2026-07-05T06:24:11.833358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:11.833358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kai Zhang, Ruilong Dan, Steve Jiang, You Zhang, Yunxiang Li, Zihan Li","submitted_at":"2023-03-24T15:29:16Z","abstract_excerpt":"The primary aim of this research was to address the limitations observed in the medical knowledge of prevalent large language models (LLMs) such as ChatGPT, by creating a specialized language model with enhanced accuracy in medical advice. We achieved this by adapting and refining the large language model meta-AI (LLaMA) using a large dataset of 100,000 patient-doctor dialogues sourced from a widely used online medical consultation platform. These conversations were cleaned and anonymized to respect privacy concerns. In addition to the model refinement, we incorporated a self-directed informat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14070","kind":"arxiv","version":5},"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/2303.14070/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":"2303.14070","created_at":"2026-07-05T06:24:11.833411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14070v5","created_at":"2026-07-05T06:24:11.833411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14070","created_at":"2026-07-05T06:24:11.833411+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2LEHLDI33K7","created_at":"2026-07-05T06:24:11.833411+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2LEHLDI33K7CERO","created_at":"2026-07-05T06:24:11.833411+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2LEHLDI","created_at":"2026-07-05T06:24:11.833411+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10217","citing_title":"Alignment Defends LLMs from Property Inference Attacks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31171","citing_title":"Cross-Domain Feature Expansion for Tabular Medical Data via Knowledge Graphs Injection","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2306.00890","citing_title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11354","citing_title":"Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05740","citing_title":"RECOVER: Designing a Large Language Model-based Remote Patient Monitoring System for Postoperative Gastrointestinal Cancer Care","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20591","citing_title":"Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06166","citing_title":"One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01077","citing_title":"Teaching LLMs Brazilian Healthcare: Injecting Knowledge from Official Clinical Guidelines","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06154","citing_title":"Exclusive Unlearning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2","json":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2.json","graph_json":"https://pith.science/api/pith-number/C2LEHLDI33K7CERO5ZSU7MVZR2/graph.json","events_json":"https://pith.science/api/pith-number/C2LEHLDI33K7CERO5ZSU7MVZR2/events.json","paper":"https://pith.science/paper/C2LEHLDI"},"agent_actions":{"view_html":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2","download_json":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2.json","view_paper":"https://pith.science/paper/C2LEHLDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14070&json=true","fetch_graph":"https://pith.science/api/pith-number/C2LEHLDI33K7CERO5ZSU7MVZR2/graph.json","fetch_events":"https://pith.science/api/pith-number/C2LEHLDI33K7CERO5ZSU7MVZR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2/action/storage_attestation","attest_author":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2/action/author_attestation","sign_citation":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2/action/citation_signature","submit_replication":"https://pith.science/pith/C2LEHLDI33K7CERO5ZSU7MVZR2/action/replication_record"}},"created_at":"2026-07-05T06:24:11.833411+00:00","updated_at":"2026-07-05T06:24:11.833411+00:00"}