{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3MEWUNRYB64TZ2H5LXPW3COS6J","short_pith_number":"pith:3MEWUNRY","schema_version":"1.0","canonical_sha256":"db096a36380fb93ce8fd5ddf6d89d2f27986f4501ad16107eb56369bcb3e0161","source":{"kind":"arxiv","id":"2505.04365","version":1},"attestation_state":"computed","paper":{"title":"CDE-Mapper: Using Retrieval-Augmented Language Models for Linking Clinical Data Elements to Controlled Vocabularies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Christof Peters, Hans-Peter Brunner-La Rocca, Komal Gilani, Marlo Verket, Michel Dumontier, Visara Urovi","submitted_at":"2025-05-07T12:32:05Z","abstract_excerpt":"The standardization of clinical data elements (CDEs) aims to ensure consistent and comprehensive patient information across various healthcare systems. Existing methods often falter when standardizing CDEs of varying representation and complex structure, impeding data integration and interoperability in clinical research. We introduce CDE-Mapper, an innovative framework that leverages Retrieval-Augmented Generation approach combined with Large Language Models to automate the linking of CDEs to controlled vocabularies. Our modular approach features query decomposition to manage varying levels o"},"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":"2505.04365","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-07T12:32:05Z","cross_cats_sorted":[],"title_canon_sha256":"5c90fd4693f6c54d56bddf3455d905b3329640fdcf323d638eb8948b82a99b31","abstract_canon_sha256":"1dd21a0ae04ca3f8e2e3b45eb0d1a68a3d939a046800f44156c655bf91ea1261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:40.710965Z","signature_b64":"zQ3RITzrVc6WY3RzQI58JsIhFYYbOkRMzR2gZS2ucG3rdljZ1+SMPMA/EMLTr6TiuIBAcARZEvePxheMtQHaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db096a36380fb93ce8fd5ddf6d89d2f27986f4501ad16107eb56369bcb3e0161","last_reissued_at":"2026-07-05T10:59:40.710505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:40.710505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CDE-Mapper: Using Retrieval-Augmented Language Models for Linking Clinical Data Elements to Controlled Vocabularies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Christof Peters, Hans-Peter Brunner-La Rocca, Komal Gilani, Marlo Verket, Michel Dumontier, Visara Urovi","submitted_at":"2025-05-07T12:32:05Z","abstract_excerpt":"The standardization of clinical data elements (CDEs) aims to ensure consistent and comprehensive patient information across various healthcare systems. Existing methods often falter when standardizing CDEs of varying representation and complex structure, impeding data integration and interoperability in clinical research. We introduce CDE-Mapper, an innovative framework that leverages Retrieval-Augmented Generation approach combined with Large Language Models to automate the linking of CDEs to controlled vocabularies. Our modular approach features query decomposition to manage varying levels o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04365","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/2505.04365/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":"2505.04365","created_at":"2026-07-05T10:59:40.710561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04365v1","created_at":"2026-07-05T10:59:40.710561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04365","created_at":"2026-07-05T10:59:40.710561+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MEWUNRYB64T","created_at":"2026-07-05T10:59:40.710561+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MEWUNRYB64TZ2H5","created_at":"2026-07-05T10:59:40.710561+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MEWUNRY","created_at":"2026-07-05T10:59:40.710561+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/3MEWUNRYB64TZ2H5LXPW3COS6J","json":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J.json","graph_json":"https://pith.science/api/pith-number/3MEWUNRYB64TZ2H5LXPW3COS6J/graph.json","events_json":"https://pith.science/api/pith-number/3MEWUNRYB64TZ2H5LXPW3COS6J/events.json","paper":"https://pith.science/paper/3MEWUNRY"},"agent_actions":{"view_html":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J","download_json":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J.json","view_paper":"https://pith.science/paper/3MEWUNRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04365&json=true","fetch_graph":"https://pith.science/api/pith-number/3MEWUNRYB64TZ2H5LXPW3COS6J/graph.json","fetch_events":"https://pith.science/api/pith-number/3MEWUNRYB64TZ2H5LXPW3COS6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J/action/storage_attestation","attest_author":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J/action/author_attestation","sign_citation":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J/action/citation_signature","submit_replication":"https://pith.science/pith/3MEWUNRYB64TZ2H5LXPW3COS6J/action/replication_record"}},"created_at":"2026-07-05T10:59:40.710561+00:00","updated_at":"2026-07-05T10:59:40.710561+00:00"}