{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FZBVN7JBPADGNT65URBOQ44VLE","short_pith_number":"pith:FZBVN7JB","schema_version":"1.0","canonical_sha256":"2e4356fd21780666cfdda442e873955914ef7c1438700699ae9523bbc878e414","source":{"kind":"arxiv","id":"2602.17949","version":2},"attestation_state":"computed","paper":{"title":"CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Blanca Gallego, Jamie Novak, Mathew Miller, Sze-yuan Ooi, Victoria Blake","submitted_at":"2026-02-20T03:00:13Z","abstract_excerpt":"Background: Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs). For many downstream tasks, however, the clinically meaningful unit is not a single CUI but a concept set comprising related synonyms, subtypes, and associated concepts. Constructing these sets is labour-intensive, inconsistently performed, and poorly supported by existing tools. Methods We present CUICurate, a graph-based retrieval-augmented generation (GraphRAG) framework for automated UMLS concept set curation. A UMLS knowledge graph (KG) was"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.17949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T03:00:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa5ba4e93ae3d7f6dc98f6c03eb6250e07c2164286fd7dc6dae919221b430b8a","abstract_canon_sha256":"4c8f61648c8fc4ffe01b40f8a68ae90647463da7237fc342166071f7c902b8fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.058009Z","signature_b64":"1UlmWMwd2IcRiXeZVvxq5q+UfT10mEU7vPKY8ckQHuY67GlDSGry94brUSY0r+s6eVggr7JV8KjZEHmqt1RRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e4356fd21780666cfdda442e873955914ef7c1438700699ae9523bbc878e414","last_reissued_at":"2026-05-17T23:39:16.057378Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.057378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Blanca Gallego, Jamie Novak, Mathew Miller, Sze-yuan Ooi, Victoria Blake","submitted_at":"2026-02-20T03:00:13Z","abstract_excerpt":"Background: Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs). For many downstream tasks, however, the clinically meaningful unit is not a single CUI but a concept set comprising related synonyms, subtypes, and associated concepts. Constructing these sets is labour-intensive, inconsistently performed, and poorly supported by existing tools. Methods We present CUICurate, a graph-based retrieval-augmented generation (GraphRAG) framework for automated UMLS concept set curation. A UMLS knowledge graph (KG) was"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CUICurate produced substantially larger and more complete concept sets than the manual benchmarks. GPT-5 outperformed manual curation for all concepts and retained at least 95% of definitive gold-standard CUIs.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that LLM-based filtering (GPT-5 and Qwen3-32B) accurately distinguishes clinically meaningful relations from noise without systematic bias or hallucination, especially for concepts not observed in the 10,000 MIMIC-III notes used for validation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CUICurate uses GraphRAG on a UMLS knowledge graph plus LLMs to generate larger, higher-recall concept sets than manual curation for five clinical concepts.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"81d263ae8780ad419cd6a62d337611d7dc02f39e783b0f8b5343d34e80db4d68"},"source":{"id":"2602.17949","kind":"arxiv","version":2},"verdict":{"id":"055cea91-ef59-4104-a3e8-3975723644b9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:14:14.730908Z","strongest_claim":"CUICurate produced substantially larger and more complete concept sets than the manual benchmarks. GPT-5 outperformed manual curation for all concepts and retained at least 95% of definitive gold-standard CUIs.","one_line_summary":"CUICurate uses GraphRAG on a UMLS knowledge graph plus LLMs to generate larger, higher-recall concept sets than manual curation for five clinical concepts.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that LLM-based filtering (GPT-5 and Qwen3-32B) accurately distinguishes clinically meaningful relations from noise without systematic bias or hallucination, especially for concepts not observed in the 10,000 MIMIC-III notes used for validation.","pith_extraction_headline":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods."},"references":{"count":17,"sample":[{"doi":"","year":2024,"title":"Medical Concept Normalization","work_id":"8065502f-2898-4a9d-8036-ce87f8160c7e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"The Unified Medical Language System at 30 Years and How It Is Used and Published: Systematic Review and Content Analysis","work_id":"6d7b30ca-ef61-4ffd-b7ce-bc7a21ca8e26","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Clinical Concept Value Sets and Interoperability in Health Data Analytics","work_id":"35fc48cc-3ea4-4937-b51a-2987d73c9fd8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Quickumls: a fast, unsupervised approach for medical concept extraction","work_id":"724c5e38-0c54-4125-8d8e-aabee04d8206","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"MedCAT -- Medical Concept Annotation Tool","work_id":"303c64c2-5670-426c-806b-4061c378154d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":17,"snapshot_sha256":"8f70c3d8424d905b529fd2a279e6de87e0dbea55bec5dca40a8fd9da7a32f9d8","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":"2602.17949","created_at":"2026-05-17T23:39:16.057475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.17949v2","created_at":"2026-05-17T23:39:16.057475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17949","created_at":"2026-05-17T23:39:16.057475+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZBVN7JBPADG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZBVN7JBPADGNT65","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZBVN7JB","created_at":"2026-05-18T12:33:37.589309+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/FZBVN7JBPADGNT65URBOQ44VLE","json":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE.json","graph_json":"https://pith.science/api/pith-number/FZBVN7JBPADGNT65URBOQ44VLE/graph.json","events_json":"https://pith.science/api/pith-number/FZBVN7JBPADGNT65URBOQ44VLE/events.json","paper":"https://pith.science/paper/FZBVN7JB"},"agent_actions":{"view_html":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE","download_json":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE.json","view_paper":"https://pith.science/paper/FZBVN7JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.17949&json=true","fetch_graph":"https://pith.science/api/pith-number/FZBVN7JBPADGNT65URBOQ44VLE/graph.json","fetch_events":"https://pith.science/api/pith-number/FZBVN7JBPADGNT65URBOQ44VLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE/action/storage_attestation","attest_author":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE/action/author_attestation","sign_citation":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE/action/citation_signature","submit_replication":"https://pith.science/pith/FZBVN7JBPADGNT65URBOQ44VLE/action/replication_record"}},"created_at":"2026-05-17T23:39:16.057475+00:00","updated_at":"2026-05-17T23:39:16.057475+00:00"}