{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GYTGEGPLPFOXLSJ2A54XSIFMXN","short_pith_number":"pith:GYTGEGPL","schema_version":"1.0","canonical_sha256":"36266219eb795d75c93a07797920acbb49183828c3d2840c85dcf112f0a305e4","source":{"kind":"arxiv","id":"2311.00204","version":1},"attestation_state":"computed","paper":{"title":"Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yining Hua, Zhen Guo","submitted_at":"2023-11-01T00:18:00Z","abstract_excerpt":"Large language models exhibit promising general capabilities but often lack specialized knowledge for domain-specific tasks. Developing domain experts from a base model enables a range of applications without prohibitive training costs. This work demonstrates a method using continuous training and instruction fine-tuning to rapidly adapt Llama 2 base models to the Chinese medical domain. We first conduct continuous training on 1B tokens from Chinese medical references to teach relevant vocabulary and knowledge. The models are then fine-tuned on 54K examples sourced from the Chinese National Me"},"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":"2311.00204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T00:18:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fb4cc7267dfd51efaf12e746a3ca6b4af4b0c32279b80a64956ac28b2fd9f67f","abstract_canon_sha256":"1a93a28389c1854e1e9ae349dcf53c5510f9c0f15eb74f4a63d0b609e4ba6e9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:43.849840Z","signature_b64":"R9J+bdI7ZXPC7IAgF1yN7Ofg3elWG3+c/UdbJVHLYSkOL1njLiLVKDtmsLaSvOMUbhkg6wAYqZlRIKFmjFWTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36266219eb795d75c93a07797920acbb49183828c3d2840c85dcf112f0a305e4","last_reissued_at":"2026-07-05T07:07:43.849334Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:43.849334Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Training and Fine-tuning for Domain-Specific Language Models in Medical Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Yining Hua, Zhen Guo","submitted_at":"2023-11-01T00:18:00Z","abstract_excerpt":"Large language models exhibit promising general capabilities but often lack specialized knowledge for domain-specific tasks. Developing domain experts from a base model enables a range of applications without prohibitive training costs. This work demonstrates a method using continuous training and instruction fine-tuning to rapidly adapt Llama 2 base models to the Chinese medical domain. We first conduct continuous training on 1B tokens from Chinese medical references to teach relevant vocabulary and knowledge. The models are then fine-tuned on 54K examples sourced from the Chinese National Me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00204","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/2311.00204/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":"2311.00204","created_at":"2026-07-05T07:07:43.849394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00204v1","created_at":"2026-07-05T07:07:43.849394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00204","created_at":"2026-07-05T07:07:43.849394+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYTGEGPLPFOX","created_at":"2026-07-05T07:07:43.849394+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYTGEGPLPFOXLSJ2","created_at":"2026-07-05T07:07:43.849394+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYTGEGPL","created_at":"2026-07-05T07:07:43.849394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13603","citing_title":"Continual Pre-Training is (not) What You Need in Domain Adaption","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN","json":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN.json","graph_json":"https://pith.science/api/pith-number/GYTGEGPLPFOXLSJ2A54XSIFMXN/graph.json","events_json":"https://pith.science/api/pith-number/GYTGEGPLPFOXLSJ2A54XSIFMXN/events.json","paper":"https://pith.science/paper/GYTGEGPL"},"agent_actions":{"view_html":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN","download_json":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN.json","view_paper":"https://pith.science/paper/GYTGEGPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00204&json=true","fetch_graph":"https://pith.science/api/pith-number/GYTGEGPLPFOXLSJ2A54XSIFMXN/graph.json","fetch_events":"https://pith.science/api/pith-number/GYTGEGPLPFOXLSJ2A54XSIFMXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN/action/storage_attestation","attest_author":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN/action/author_attestation","sign_citation":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN/action/citation_signature","submit_replication":"https://pith.science/pith/GYTGEGPLPFOXLSJ2A54XSIFMXN/action/replication_record"}},"created_at":"2026-07-05T07:07:43.849394+00:00","updated_at":"2026-07-05T07:07:43.849394+00:00"}