{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FZBVN7JBPADGNT65URBOQ44VLE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4c8f61648c8fc4ffe01b40f8a68ae90647463da7237fc342166071f7c902b8fd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T03:00:13Z","title_canon_sha256":"aa5ba4e93ae3d7f6dc98f6c03eb6250e07c2164286fd7dc6dae919221b430b8a"},"schema_version":"1.0","source":{"id":"2602.17949","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.17949","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.17949v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.17949","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"FZBVN7JBPADG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FZBVN7JBPADGNT65","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FZBVN7JB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:bdd7ee8a5fcdeab634e098b2b12aad7b64cb7a03799204c895b6f2bb1e3dadfd","target":"graph","created_at":"2026-05-17T23:39:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods."}],"snapshot_sha256":"81d263ae8780ad419cd6a62d337611d7dc02f39e783b0f8b5343d34e80db4d68"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Blanca Gallego, Jamie Novak, Mathew Miller, Sze-yuan Ooi, Victoria Blake","cross_cats":["cs.AI"],"headline":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T03:00:13Z","title":"CUICurate: A GraphRAG-based Framework for Automated Clinical Concept Curation for NLP applications"},"references":{"count":17,"internal_anchors":0,"resolved_work":17,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Medical Concept Normalization","work_id":"8065502f-2898-4a9d-8036-ce87f8160c7e","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"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","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Clinical Concept Value Sets and Interoperability in Health Data Analytics","work_id":"35fc48cc-3ea4-4937-b51a-2987d73c9fd8","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Quickumls: a fast, unsupervised approach for medical concept extraction","work_id":"724c5e38-0c54-4125-8d8e-aabee04d8206","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"MedCAT -- Medical Concept Annotation Tool","work_id":"303c64c2-5670-426c-806b-4061c378154d","year":2019}],"snapshot_sha256":"8f70c3d8424d905b529fd2a279e6de87e0dbea55bec5dca40a8fd9da7a32f9d8"},"source":{"id":"2602.17949","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T21:14:14.730908Z","id":"055cea91-ef59-4104-a3e8-3975723644b9","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CUICurate automates UMLS concept set curation with GraphRAG to yield larger and more complete sets than manual methods.","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.","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."}},"verdict_id":"055cea91-ef59-4104-a3e8-3975723644b9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ad059e3529c0d6f6695277784d643ace2d9841b65674cb220fd54d960554df27","target":"record","created_at":"2026-05-17T23:39:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4c8f61648c8fc4ffe01b40f8a68ae90647463da7237fc342166071f7c902b8fd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-20T03:00:13Z","title_canon_sha256":"aa5ba4e93ae3d7f6dc98f6c03eb6250e07c2164286fd7dc6dae919221b430b8a"},"schema_version":"1.0","source":{"id":"2602.17949","kind":"arxiv","version":2}},"canonical_sha256":"2e4356fd21780666cfdda442e873955914ef7c1438700699ae9523bbc878e414","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e4356fd21780666cfdda442e873955914ef7c1438700699ae9523bbc878e414","first_computed_at":"2026-05-17T23:39:16.057378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.057378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1UlmWMwd2IcRiXeZVvxq5q+UfT10mEU7vPKY8ckQHuY67GlDSGry94brUSY0r+s6eVggr7JV8KjZEHmqt1RRDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.058009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.17949","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad059e3529c0d6f6695277784d643ace2d9841b65674cb220fd54d960554df27","sha256:bdd7ee8a5fcdeab634e098b2b12aad7b64cb7a03799204c895b6f2bb1e3dadfd"],"state_sha256":"1ae5ebdf2c3ece5b837b7a7a95149001204acd37ec1b0c74d14b2f3d43262c19"}