{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:77FCFUTU3ZK3A6AU266PIZUWWY","short_pith_number":"pith:77FCFUTU","schema_version":"1.0","canonical_sha256":"ffca22d274de55b07814d7bcf46696b620d23dc988795c6dee19dfcfdd4fa6bf","source":{"kind":"arxiv","id":"2406.15363","version":2},"attestation_state":"computed","paper":{"title":"Exploring LLM Multi-Agents for ICD Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Yu, Rumeng Li, Xun Wang","submitted_at":"2024-04-01T15:17:39Z","abstract_excerpt":"To address the limitations of Large Language Models (LLMs) in the International Classification of Diseases (ICD) coding task, where they often produce inaccurate and incomplete prediction results due to the high-dimensional and skewed distribution of the ICD codes, and often lack interpretability and reliability as well. We introduce an innovative multi-agent approach for ICD coding which mimics the ICD coding assignment procedure in real-world settings, comprising five distinct agents: the patient, physician, coder, reviewer, and adjuster. Each agent utilizes an LLM-based model tailored to th"},"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":"2406.15363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-01T15:17:39Z","cross_cats_sorted":[],"title_canon_sha256":"ff535307e1339e2529f322e0c7f8ec00fd4025f832debabe45e51e69f521b75c","abstract_canon_sha256":"eb7d2b7c2a7cf30f3f89da44eace0f427a8b9a3b58a32e06c0c6ac25aa4fef35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:23.103901Z","signature_b64":"5GJk7D6ctNRmYd6SIClU6nJTpl/4d5JM8unKvam66ulhMdFwX6K9claS8quwVEpNrp8AaPqL5sw3F5o5KxRRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffca22d274de55b07814d7bcf46696b620d23dc988795c6dee19dfcfdd4fa6bf","last_reissued_at":"2026-07-05T08:55:23.103429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:23.103429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring LLM Multi-Agents for ICD Coding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Yu, Rumeng Li, Xun Wang","submitted_at":"2024-04-01T15:17:39Z","abstract_excerpt":"To address the limitations of Large Language Models (LLMs) in the International Classification of Diseases (ICD) coding task, where they often produce inaccurate and incomplete prediction results due to the high-dimensional and skewed distribution of the ICD codes, and often lack interpretability and reliability as well. We introduce an innovative multi-agent approach for ICD coding which mimics the ICD coding assignment procedure in real-world settings, comprising five distinct agents: the patient, physician, coder, reviewer, and adjuster. Each agent utilizes an LLM-based model tailored to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15363","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/2406.15363/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":"2406.15363","created_at":"2026-07-05T08:55:23.103484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15363v2","created_at":"2026-07-05T08:55:23.103484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15363","created_at":"2026-07-05T08:55:23.103484+00:00"},{"alias_kind":"pith_short_12","alias_value":"77FCFUTU3ZK3","created_at":"2026-07-05T08:55:23.103484+00:00"},{"alias_kind":"pith_short_16","alias_value":"77FCFUTU3ZK3A6AU","created_at":"2026-07-05T08:55:23.103484+00:00"},{"alias_kind":"pith_short_8","alias_value":"77FCFUTU","created_at":"2026-07-05T08:55:23.103484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18768","citing_title":"ClinQueryAgent: A Conversational Agent for Population Health Management","ref_index":210,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY","json":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY.json","graph_json":"https://pith.science/api/pith-number/77FCFUTU3ZK3A6AU266PIZUWWY/graph.json","events_json":"https://pith.science/api/pith-number/77FCFUTU3ZK3A6AU266PIZUWWY/events.json","paper":"https://pith.science/paper/77FCFUTU"},"agent_actions":{"view_html":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY","download_json":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY.json","view_paper":"https://pith.science/paper/77FCFUTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15363&json=true","fetch_graph":"https://pith.science/api/pith-number/77FCFUTU3ZK3A6AU266PIZUWWY/graph.json","fetch_events":"https://pith.science/api/pith-number/77FCFUTU3ZK3A6AU266PIZUWWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY/action/storage_attestation","attest_author":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY/action/author_attestation","sign_citation":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY/action/citation_signature","submit_replication":"https://pith.science/pith/77FCFUTU3ZK3A6AU266PIZUWWY/action/replication_record"}},"created_at":"2026-07-05T08:55:23.103484+00:00","updated_at":"2026-07-05T08:55:23.103484+00:00"}