{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T5MRK4MMXA42IAJLSVPKUUAS5I","short_pith_number":"pith:T5MRK4MM","schema_version":"1.0","canonical_sha256":"9f5915718cb839a4012b955eaa5012ea34ca6aeb3fb21bdb9e00e6142c388d52","source":{"kind":"arxiv","id":"2403.10822","version":3},"attestation_state":"computed","paper":{"title":"Can Large Language Models abstract Medical Coded Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Simon A. Lee, Timothy Lindsey","submitted_at":"2024-03-16T06:18:15Z","abstract_excerpt":"Large Language Models (LLMs) have become a pivotal research area, potentially making beneficial contributions in fields like healthcare where they can streamline automated billing and decision support. However, the frequent use of specialized coded languages like ICD-10, which are regularly updated and deviate from natural language formats, presents potential challenges for LLMs in creating accurate and meaningful latent representations. This raises concerns among healthcare professionals about potential inaccuracies or ``hallucinations\" that could result in the direct impact of a patient. The"},"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":"2403.10822","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T06:18:15Z","cross_cats_sorted":[],"title_canon_sha256":"4a8874cac81658df20a5b00428b9e6ab74d03d52e162066df05e73324cc2031a","abstract_canon_sha256":"cb018412ddeed8461f5c89eaeb05741c088791bf818d6794b5ae5020ff408bab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:39.544053Z","signature_b64":"yhJz/1EgVZGULUw8XvWxJPCVwnTKe0KveE2cqYuJ/W5bxdkHsoHwbeAT6GKq7PKPL33oTPJXzlKpmh9DuOk1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f5915718cb839a4012b955eaa5012ea34ca6aeb3fb21bdb9e00e6142c388d52","last_reissued_at":"2026-07-05T08:28:39.543626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:39.543626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models abstract Medical Coded Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Simon A. Lee, Timothy Lindsey","submitted_at":"2024-03-16T06:18:15Z","abstract_excerpt":"Large Language Models (LLMs) have become a pivotal research area, potentially making beneficial contributions in fields like healthcare where they can streamline automated billing and decision support. However, the frequent use of specialized coded languages like ICD-10, which are regularly updated and deviate from natural language formats, presents potential challenges for LLMs in creating accurate and meaningful latent representations. This raises concerns among healthcare professionals about potential inaccuracies or ``hallucinations\" that could result in the direct impact of a patient. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10822","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/2403.10822/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":"2403.10822","created_at":"2026-07-05T08:28:39.543681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10822v3","created_at":"2026-07-05T08:28:39.543681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10822","created_at":"2026-07-05T08:28:39.543681+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5MRK4MMXA42","created_at":"2026-07-05T08:28:39.543681+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5MRK4MMXA42IAJL","created_at":"2026-07-05T08:28:39.543681+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5MRK4MM","created_at":"2026-07-05T08:28:39.543681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17765","citing_title":"AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08685","citing_title":"Event Fields: Learning Latent Event Structure for Waveform Foundation Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I","json":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I.json","graph_json":"https://pith.science/api/pith-number/T5MRK4MMXA42IAJLSVPKUUAS5I/graph.json","events_json":"https://pith.science/api/pith-number/T5MRK4MMXA42IAJLSVPKUUAS5I/events.json","paper":"https://pith.science/paper/T5MRK4MM"},"agent_actions":{"view_html":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I","download_json":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I.json","view_paper":"https://pith.science/paper/T5MRK4MM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10822&json=true","fetch_graph":"https://pith.science/api/pith-number/T5MRK4MMXA42IAJLSVPKUUAS5I/graph.json","fetch_events":"https://pith.science/api/pith-number/T5MRK4MMXA42IAJLSVPKUUAS5I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I/action/storage_attestation","attest_author":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I/action/author_attestation","sign_citation":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I/action/citation_signature","submit_replication":"https://pith.science/pith/T5MRK4MMXA42IAJLSVPKUUAS5I/action/replication_record"}},"created_at":"2026-07-05T08:28:39.543681+00:00","updated_at":"2026-07-05T08:28:39.543681+00:00"}