{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MOYDLAEEAKLV65GKHTTQAZUOFM","short_pith_number":"pith:MOYDLAEE","schema_version":"1.0","canonical_sha256":"63b035808402975f74ca3ce700668e2b311b9a2aaf82bccfd21024556af6c073","source":{"kind":"arxiv","id":"2403.09057","version":3},"attestation_state":"computed","paper":{"title":"A Continued Pretrained LLM Approach for Automatic Medical Note Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bharath Chintagunta, Dong Yuan, Eti Rastogi, Fen Zhao, Gautam Naik, Jeff Ward, Sagar Goyal, Sree Prasanna Rajagopal","submitted_at":"2024-03-14T02:55:37Z","abstract_excerpt":"LLMs are revolutionizing NLP tasks. However, the use of the most advanced LLMs, such as GPT-4, is often prohibitively expensive for most specialized fields. We introduce HEAL, the first continuously trained 13B LLaMA2-based LLM that is purpose-built for medical conversations and measured on automated scribing. Our results demonstrate that HEAL outperforms GPT-4 and PMC-LLaMA in PubMedQA, with an accuracy of 78.4\\%. It also achieves parity with GPT-4 in generating medical notes. Remarkably, HEAL surpasses GPT-4 and Med-PaLM 2 in identifying more correct medical concepts and exceeds the performa"},"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":"2403.09057","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T02:55:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d57b2443fcaf97cd983347632a05ef823e37e27919c240459ddf99fde8f28cd1","abstract_canon_sha256":"be94cbce0dabc9fb8d100509394f5d196d52f874ce111f5a122e9c78b9a6a1fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:03.246240Z","signature_b64":"2DjQ+jaNb1rhC+gjqWfvkcskELqsxd1rTUD4skMibF4JztcpWY7eGc6dV0m53SD/hFEW+gMZyqsaF8h0sMXlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b035808402975f74ca3ce700668e2b311b9a2aaf82bccfd21024556af6c073","last_reissued_at":"2026-07-05T08:04:03.245672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:03.245672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Continued Pretrained LLM Approach for Automatic Medical Note Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bharath Chintagunta, Dong Yuan, Eti Rastogi, Fen Zhao, Gautam Naik, Jeff Ward, Sagar Goyal, Sree Prasanna Rajagopal","submitted_at":"2024-03-14T02:55:37Z","abstract_excerpt":"LLMs are revolutionizing NLP tasks. However, the use of the most advanced LLMs, such as GPT-4, is often prohibitively expensive for most specialized fields. We introduce HEAL, the first continuously trained 13B LLaMA2-based LLM that is purpose-built for medical conversations and measured on automated scribing. Our results demonstrate that HEAL outperforms GPT-4 and PMC-LLaMA in PubMedQA, with an accuracy of 78.4\\%. It also achieves parity with GPT-4 in generating medical notes. Remarkably, HEAL surpasses GPT-4 and Med-PaLM 2 in identifying more correct medical concepts and exceeds the performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09057","kind":"arxiv","version":3},"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/2403.09057/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":"2403.09057","created_at":"2026-07-05T08:04:03.245733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09057v3","created_at":"2026-07-05T08:04:03.245733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09057","created_at":"2026-07-05T08:04:03.245733+00:00"},{"alias_kind":"pith_short_12","alias_value":"MOYDLAEEAKLV","created_at":"2026-07-05T08:04:03.245733+00:00"},{"alias_kind":"pith_short_16","alias_value":"MOYDLAEEAKLV65GK","created_at":"2026-07-05T08:04:03.245733+00:00"},{"alias_kind":"pith_short_8","alias_value":"MOYDLAEE","created_at":"2026-07-05T08:04:03.245733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15275","citing_title":"ChiMed 2.0: Advancing Chinese Medical Dataset in Facilitating Large Language Modeling","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM","json":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM.json","graph_json":"https://pith.science/api/pith-number/MOYDLAEEAKLV65GKHTTQAZUOFM/graph.json","events_json":"https://pith.science/api/pith-number/MOYDLAEEAKLV65GKHTTQAZUOFM/events.json","paper":"https://pith.science/paper/MOYDLAEE"},"agent_actions":{"view_html":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM","download_json":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM.json","view_paper":"https://pith.science/paper/MOYDLAEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09057&json=true","fetch_graph":"https://pith.science/api/pith-number/MOYDLAEEAKLV65GKHTTQAZUOFM/graph.json","fetch_events":"https://pith.science/api/pith-number/MOYDLAEEAKLV65GKHTTQAZUOFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM/action/storage_attestation","attest_author":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM/action/author_attestation","sign_citation":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM/action/citation_signature","submit_replication":"https://pith.science/pith/MOYDLAEEAKLV65GKHTTQAZUOFM/action/replication_record"}},"created_at":"2026-07-05T08:04:03.245733+00:00","updated_at":"2026-07-05T08:04:03.245733+00:00"}