{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B2JYATX4KJWMCMXVD64BZFWFP5","short_pith_number":"pith:B2JYATX4","schema_version":"1.0","canonical_sha256":"0e93804efc526cc132f51fb81c96c57f609a60ce155f64d5570c06d1b36c3377","source":{"kind":"arxiv","id":"2401.13512","version":2},"attestation_state":"computed","paper":{"title":"Can GPT-3.5 Generate and Code Discharge Summaries?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Aryo Pradipta Gema, Beatrice Alex, Hang Dong, Luke Daines, Mat\\'u\\v{s} Falis, Michael Holder, Rose S Penfold, Siddharth Basetti","submitted_at":"2024-01-24T15:10:13Z","abstract_excerpt":"Objective: To investigate GPT-3.5 in generating and coding medical documents with ICD-10 codes for data augmentation on low-resources labels.\n  Materials and Methods: Employing GPT-3.5 we generated and coded 9,606 discharge summaries based on lists of ICD-10 code descriptions of patients with infrequent (generation) codes within the MIMIC-IV dataset. Combined with the baseline training set, this formed an augmented training set. Neural coding models were trained on baseline and augmented data and evaluated on a MIMIC-IV test set. We report micro- and macro-F1 scores on the full codeset, genera"},"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":"2401.13512","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T15:10:13Z","cross_cats_sorted":[],"title_canon_sha256":"37e0eb9ed6b682c244f83b4deb0cbc3826a942c6e4e0f942c81bc7adf002c082","abstract_canon_sha256":"5217e0be61b0b5970e25699ac8d24e30fbf2eaf00bfac582a32fc46eef5f8556"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:26.048950Z","signature_b64":"MJo8uaAOUoexaw81Hg/eVtX5KzYn/T4i+uBl8R4BW8WmGevkuihma86jyBmj0tfwS7JymQosLSYPEcTJbh8zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e93804efc526cc132f51fb81c96c57f609a60ce155f64d5570c06d1b36c3377","last_reissued_at":"2026-07-05T09:07:26.048553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:26.048553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can GPT-3.5 Generate and Code Discharge Summaries?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Birch, Aryo Pradipta Gema, Beatrice Alex, Hang Dong, Luke Daines, Mat\\'u\\v{s} Falis, Michael Holder, Rose S Penfold, Siddharth Basetti","submitted_at":"2024-01-24T15:10:13Z","abstract_excerpt":"Objective: To investigate GPT-3.5 in generating and coding medical documents with ICD-10 codes for data augmentation on low-resources labels.\n  Materials and Methods: Employing GPT-3.5 we generated and coded 9,606 discharge summaries based on lists of ICD-10 code descriptions of patients with infrequent (generation) codes within the MIMIC-IV dataset. Combined with the baseline training set, this formed an augmented training set. Neural coding models were trained on baseline and augmented data and evaluated on a MIMIC-IV test set. We report micro- and macro-F1 scores on the full codeset, genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13512","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/2401.13512/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":"2401.13512","created_at":"2026-07-05T09:07:26.048608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13512v2","created_at":"2026-07-05T09:07:26.048608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13512","created_at":"2026-07-05T09:07:26.048608+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2JYATX4KJWM","created_at":"2026-07-05T09:07:26.048608+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2JYATX4KJWMCMXV","created_at":"2026-07-05T09:07:26.048608+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2JYATX4","created_at":"2026-07-05T09:07:26.048608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5","json":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5.json","graph_json":"https://pith.science/api/pith-number/B2JYATX4KJWMCMXVD64BZFWFP5/graph.json","events_json":"https://pith.science/api/pith-number/B2JYATX4KJWMCMXVD64BZFWFP5/events.json","paper":"https://pith.science/paper/B2JYATX4"},"agent_actions":{"view_html":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5","download_json":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5.json","view_paper":"https://pith.science/paper/B2JYATX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13512&json=true","fetch_graph":"https://pith.science/api/pith-number/B2JYATX4KJWMCMXVD64BZFWFP5/graph.json","fetch_events":"https://pith.science/api/pith-number/B2JYATX4KJWMCMXVD64BZFWFP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5/action/storage_attestation","attest_author":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5/action/author_attestation","sign_citation":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5/action/citation_signature","submit_replication":"https://pith.science/pith/B2JYATX4KJWMCMXVD64BZFWFP5/action/replication_record"}},"created_at":"2026-07-05T09:07:26.048608+00:00","updated_at":"2026-07-05T09:07:26.048608+00:00"}