{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GLXLY5VXSB24RDPBX5YT6C5NJS","short_pith_number":"pith:GLXLY5VX","schema_version":"1.0","canonical_sha256":"32eebc76b79075c88de1bf713f0bad4c804331d7c51c9e552148365cb6d0a40d","source":{"kind":"arxiv","id":"2507.03001","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akram Mustafa, Mostafa Rahimi Azghadi, Usman Naseem","submitted_at":"2025-07-02T00:53:54Z","abstract_excerpt":"This study evaluates how well large language models (LLMs) can classify ICD-10 codes from hospital discharge summaries, a critical but error-prone task in healthcare. Using 1,500 summaries from the MIMIC-IV dataset and focusing on the 10 most frequent ICD-10 codes, the study tested 11 LLMs, including models with and without structured reasoning capabilities. Medical terms were extracted using a clinical NLP tool (cTAKES), and models were prompted in a consistent, coder-like format. None of the models achieved an F1 score above 57%, with performance dropping as code specificity increased. Reaso"},"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":"2507.03001","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-02T00:53:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"58279e2ebf1c11d7fc6c59884d9189d3de06ec169f68aae45c64e37cf9f8710f","abstract_canon_sha256":"3ab2f12b23af586ca098c9794052959a9d1c49645a36dcfe20fa4de2d069816b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:50.493608Z","signature_b64":"2Hvoy72L+aNxPhU0pyVCFOx1tTNkWU3nMayrHdMTVQ3BEOq5bSfM1hWpfozOMxG74sCSEZ9j6lR6yCbFtIcNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32eebc76b79075c88de1bf713f0bad4c804331d7c51c9e552148365cb6d0a40d","last_reissued_at":"2026-07-05T11:31:50.493209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:50.493209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Akram Mustafa, Mostafa Rahimi Azghadi, Usman Naseem","submitted_at":"2025-07-02T00:53:54Z","abstract_excerpt":"This study evaluates how well large language models (LLMs) can classify ICD-10 codes from hospital discharge summaries, a critical but error-prone task in healthcare. Using 1,500 summaries from the MIMIC-IV dataset and focusing on the 10 most frequent ICD-10 codes, the study tested 11 LLMs, including models with and without structured reasoning capabilities. Medical terms were extracted using a clinical NLP tool (cTAKES), and models were prompted in a consistent, coder-like format. None of the models achieved an F1 score above 57%, with performance dropping as code specificity increased. Reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03001","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/2507.03001/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":"2507.03001","created_at":"2026-07-05T11:31:50.493266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03001v1","created_at":"2026-07-05T11:31:50.493266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03001","created_at":"2026-07-05T11:31:50.493266+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLXLY5VXSB24","created_at":"2026-07-05T11:31:50.493266+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLXLY5VXSB24RDPB","created_at":"2026-07-05T11:31:50.493266+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLXLY5VX","created_at":"2026-07-05T11:31:50.493266+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/GLXLY5VXSB24RDPBX5YT6C5NJS","json":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS.json","graph_json":"https://pith.science/api/pith-number/GLXLY5VXSB24RDPBX5YT6C5NJS/graph.json","events_json":"https://pith.science/api/pith-number/GLXLY5VXSB24RDPBX5YT6C5NJS/events.json","paper":"https://pith.science/paper/GLXLY5VX"},"agent_actions":{"view_html":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS","download_json":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS.json","view_paper":"https://pith.science/paper/GLXLY5VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03001&json=true","fetch_graph":"https://pith.science/api/pith-number/GLXLY5VXSB24RDPBX5YT6C5NJS/graph.json","fetch_events":"https://pith.science/api/pith-number/GLXLY5VXSB24RDPBX5YT6C5NJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS/action/storage_attestation","attest_author":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS/action/author_attestation","sign_citation":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS/action/citation_signature","submit_replication":"https://pith.science/pith/GLXLY5VXSB24RDPBX5YT6C5NJS/action/replication_record"}},"created_at":"2026-07-05T11:31:50.493266+00:00","updated_at":"2026-07-05T11:31:50.493266+00:00"}