{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WEHDTOJMJDAVHMX6GQN462VHIY","short_pith_number":"pith:WEHDTOJM","schema_version":"1.0","canonical_sha256":"b10e39b92c48c153b2fe341bcf6aa7463c347c0d19fe7d9c704f7aeee98d2c47","source":{"kind":"arxiv","id":"2308.14346","version":1},"attestation_state":"computed","paper":{"title":"DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Zhong, Jiaao Wu, Jiajie Peng, Kuang Ren, Shengze Xiao, Wei Chen, Xuanjing Huang, Zhijie Bao, Zhongyu Wei","submitted_at":"2023-08-28T06:41:49Z","abstract_excerpt":"We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services. To construct high-quality Supervised Fine-Tuning (SFT) datasets, we employ three strategies: utilizing medical knowledge-graphs, reconstructing real-world dialogues, and incorporating human-guided preference rephrasing. These datasets are instrumental in training DISC-MedLLM, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios. Extensive experimental results demonst"},"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":"2308.14346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-28T06:41:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f683a219b84950667b691dfb33c230df878ee5a5fc95c341dfec6ce7d2e7044d","abstract_canon_sha256":"98b4b1eceec7da9d38b338838a2c3f2e6ac6ee79e92b645513f0e1142d3a43f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:25.147095Z","signature_b64":"WE29me3CNzJG+WFntLAl11DLb7Qinzqp+D75wL2UwRqQWRusX+Ou/wkB7OpNqKipV/C0CutG/wz1qeTP7jNCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b10e39b92c48c153b2fe341bcf6aa7463c347c0d19fe7d9c704f7aeee98d2c47","last_reissued_at":"2026-07-05T06:45:25.146665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:25.146665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Zhong, Jiaao Wu, Jiajie Peng, Kuang Ren, Shengze Xiao, Wei Chen, Xuanjing Huang, Zhijie Bao, Zhongyu Wei","submitted_at":"2023-08-28T06:41:49Z","abstract_excerpt":"We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services. To construct high-quality Supervised Fine-Tuning (SFT) datasets, we employ three strategies: utilizing medical knowledge-graphs, reconstructing real-world dialogues, and incorporating human-guided preference rephrasing. These datasets are instrumental in training DISC-MedLLM, surpassing existing medical LLMs in both single-turn and multi-turn consultation scenarios. Extensive experimental results demonst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14346","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/2308.14346/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":"2308.14346","created_at":"2026-07-05T06:45:25.146724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14346v1","created_at":"2026-07-05T06:45:25.146724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14346","created_at":"2026-07-05T06:45:25.146724+00:00"},{"alias_kind":"pith_short_12","alias_value":"WEHDTOJMJDAV","created_at":"2026-07-05T06:45:25.146724+00:00"},{"alias_kind":"pith_short_16","alias_value":"WEHDTOJMJDAVHMX6","created_at":"2026-07-05T06:45:25.146724+00:00"},{"alias_kind":"pith_short_8","alias_value":"WEHDTOJM","created_at":"2026-07-05T06:45:25.146724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28526","citing_title":"A French OSCE Dialogue Dataset and Controllable Virtual Patient System for Clinical Training","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11416","citing_title":"Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":238,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11416","citing_title":"Freeze Deep, Train Shallow: Interpretable Layer Allocation for Continued Pre-Training","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08948","citing_title":"TaxPraBen: A Scalable Benchmark for Structured Evaluation of LLMs in Chinese Real-World Tax Practice","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":103,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY","json":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY.json","graph_json":"https://pith.science/api/pith-number/WEHDTOJMJDAVHMX6GQN462VHIY/graph.json","events_json":"https://pith.science/api/pith-number/WEHDTOJMJDAVHMX6GQN462VHIY/events.json","paper":"https://pith.science/paper/WEHDTOJM"},"agent_actions":{"view_html":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY","download_json":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY.json","view_paper":"https://pith.science/paper/WEHDTOJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14346&json=true","fetch_graph":"https://pith.science/api/pith-number/WEHDTOJMJDAVHMX6GQN462VHIY/graph.json","fetch_events":"https://pith.science/api/pith-number/WEHDTOJMJDAVHMX6GQN462VHIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY/action/storage_attestation","attest_author":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY/action/author_attestation","sign_citation":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY/action/citation_signature","submit_replication":"https://pith.science/pith/WEHDTOJMJDAVHMX6GQN462VHIY/action/replication_record"}},"created_at":"2026-07-05T06:45:25.146724+00:00","updated_at":"2026-07-05T06:45:25.146724+00:00"}