{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YZPAYXZBVCDJX4EZK3AGG3OMSA","short_pith_number":"pith:YZPAYXZB","schema_version":"1.0","canonical_sha256":"c65e0c5f21a8869bf09956c0636dcc903c10b395b5538d48542063217d42826d","source":{"kind":"arxiv","id":"2309.12625","version":2},"attestation_state":"computed","paper":{"title":"DRG-LLaMA : Tuning LLaMA Model to Predict Diagnosis-related Group for Hospitalized Patients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bryan Hull, Christopher Dantona, Chufan Gao, Hanyin Wang, Jimeng Sun","submitted_at":"2023-09-22T05:18:54Z","abstract_excerpt":"In the U.S. inpatient payment system, the Diagnosis-Related Group (DRG) is pivotal, but its assignment process is inefficient. The study introduces DRG-LLaMA, an advanced large language model (LLM) fine-tuned on clinical notes to enhance DRGs assignment. Utilizing LLaMA as the foundational model and optimizing it through Low-Rank Adaptation (LoRA) on 236,192 MIMIC-IV discharge summaries, our DRG-LLaMA-7B model exhibited a noteworthy macro-averaged F1 score of 0.327, a top-1 prediction accuracy of 52.0%, and a macro-averaged Area Under the Curve (AUC) of 0.986, with a maximum input token length"},"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":"2309.12625","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-09-22T05:18:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b4da202bb39ea49889c77845e85acb7a4f8ad2e1827248cee19b84c20e321b2f","abstract_canon_sha256":"e4b64141abafaa0e28b59ce379c8eb93acc477884a6c01b72722084e172b3a3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:25.092323Z","signature_b64":"cYuTbFWUrmf1OUg4m/aRgdNSGmA5/h1r7tE7oSo73e8xGQ69jWJ/8ckKqrfZ0ajzBa7rsC1laHfBNTxBjSesAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c65e0c5f21a8869bf09956c0636dcc903c10b395b5538d48542063217d42826d","last_reissued_at":"2026-07-05T06:55:25.091858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:25.091858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DRG-LLaMA : Tuning LLaMA Model to Predict Diagnosis-related Group for Hospitalized Patients","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bryan Hull, Christopher Dantona, Chufan Gao, Hanyin Wang, Jimeng Sun","submitted_at":"2023-09-22T05:18:54Z","abstract_excerpt":"In the U.S. inpatient payment system, the Diagnosis-Related Group (DRG) is pivotal, but its assignment process is inefficient. The study introduces DRG-LLaMA, an advanced large language model (LLM) fine-tuned on clinical notes to enhance DRGs assignment. Utilizing LLaMA as the foundational model and optimizing it through Low-Rank Adaptation (LoRA) on 236,192 MIMIC-IV discharge summaries, our DRG-LLaMA-7B model exhibited a noteworthy macro-averaged F1 score of 0.327, a top-1 prediction accuracy of 52.0%, and a macro-averaged Area Under the Curve (AUC) of 0.986, with a maximum input token length"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12625","kind":"arxiv","version":2},"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/2309.12625/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":"2309.12625","created_at":"2026-07-05T06:55:25.091915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.12625v2","created_at":"2026-07-05T06:55:25.091915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12625","created_at":"2026-07-05T06:55:25.091915+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZPAYXZBVCDJ","created_at":"2026-07-05T06:55:25.091915+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZPAYXZBVCDJX4EZ","created_at":"2026-07-05T06:55:25.091915+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZPAYXZB","created_at":"2026-07-05T06:55:25.091915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17775","citing_title":"Systematic Evaluation of the Quality of Synthetic Clinical Notes Rephrased by LLMs at Million-Note Scale","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA","json":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA.json","graph_json":"https://pith.science/api/pith-number/YZPAYXZBVCDJX4EZK3AGG3OMSA/graph.json","events_json":"https://pith.science/api/pith-number/YZPAYXZBVCDJX4EZK3AGG3OMSA/events.json","paper":"https://pith.science/paper/YZPAYXZB"},"agent_actions":{"view_html":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA","download_json":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA.json","view_paper":"https://pith.science/paper/YZPAYXZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.12625&json=true","fetch_graph":"https://pith.science/api/pith-number/YZPAYXZBVCDJX4EZK3AGG3OMSA/graph.json","fetch_events":"https://pith.science/api/pith-number/YZPAYXZBVCDJX4EZK3AGG3OMSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA/action/storage_attestation","attest_author":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA/action/author_attestation","sign_citation":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA/action/citation_signature","submit_replication":"https://pith.science/pith/YZPAYXZBVCDJX4EZK3AGG3OMSA/action/replication_record"}},"created_at":"2026-07-05T06:55:25.091915+00:00","updated_at":"2026-07-05T06:55:25.091915+00:00"}