{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CRTVOND6QN3ZDXVP3KZTHVIDFF","short_pith_number":"pith:CRTVOND6","schema_version":"1.0","canonical_sha256":"146757347e837791deafdab333d503294c14b31bd59bff115ca72c68af68c426","source":{"kind":"arxiv","id":"2505.20020","version":1},"attestation_state":"computed","paper":{"title":"Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Adam Belloum, Bernard de Bono, Lang Li, Lei Wang, Natallia Kokash, Paola Grosso, Sara Quinney, Thomas H. Gillespie","submitted_at":"2025-05-26T14:09:17Z","abstract_excerpt":"The rise of electronic health records (EHRs) has unlocked new opportunities for medical research, but privacy regulations and data heterogeneity remain key barriers to large-scale machine learning. Federated learning (FL) enables collaborative modeling without sharing raw data, yet faces challenges in harmonizing diverse clinical datasets. This paper presents a two-step data alignment strategy integrating ontologies and large language models (LLMs) to support secure, privacy-preserving FL in healthcare, demonstrating its effectiveness in a real-world project involving semantic mapping of EHR d"},"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":"2505.20020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T14:09:17Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"2fa77ab403573741dbf36c774259f1ea62e6f313279d85ff84c760dcb46e8a52","abstract_canon_sha256":"1ad6d78bdaf1898aa42a8613956681eb1840b875f97d657880623960f6b3f6d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:51.345126Z","signature_b64":"lkKMJ+Oz95431mFTRbvqtkGHWc2hB2IRp34t1ZtO5eq1EKUo7/0rxZW3A4Huc4R/xB8uLjFOcM2UyJiG0jx9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"146757347e837791deafdab333d503294c14b31bd59bff115ca72c68af68c426","last_reissued_at":"2026-07-05T11:09:51.344635Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:51.344635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Adam Belloum, Bernard de Bono, Lang Li, Lei Wang, Natallia Kokash, Paola Grosso, Sara Quinney, Thomas H. Gillespie","submitted_at":"2025-05-26T14:09:17Z","abstract_excerpt":"The rise of electronic health records (EHRs) has unlocked new opportunities for medical research, but privacy regulations and data heterogeneity remain key barriers to large-scale machine learning. Federated learning (FL) enables collaborative modeling without sharing raw data, yet faces challenges in harmonizing diverse clinical datasets. This paper presents a two-step data alignment strategy integrating ontologies and large language models (LLMs) to support secure, privacy-preserving FL in healthcare, demonstrating its effectiveness in a real-world project involving semantic mapping of EHR d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20020","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/2505.20020/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":"2505.20020","created_at":"2026-07-05T11:09:51.344694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20020v1","created_at":"2026-07-05T11:09:51.344694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20020","created_at":"2026-07-05T11:09:51.344694+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRTVOND6QN3Z","created_at":"2026-07-05T11:09:51.344694+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRTVOND6QN3ZDXVP","created_at":"2026-07-05T11:09:51.344694+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRTVOND6","created_at":"2026-07-05T11:09:51.344694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.19360","citing_title":"Compliance Management for Federated Data Processing","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF","json":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF.json","graph_json":"https://pith.science/api/pith-number/CRTVOND6QN3ZDXVP3KZTHVIDFF/graph.json","events_json":"https://pith.science/api/pith-number/CRTVOND6QN3ZDXVP3KZTHVIDFF/events.json","paper":"https://pith.science/paper/CRTVOND6"},"agent_actions":{"view_html":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF","download_json":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF.json","view_paper":"https://pith.science/paper/CRTVOND6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20020&json=true","fetch_graph":"https://pith.science/api/pith-number/CRTVOND6QN3ZDXVP3KZTHVIDFF/graph.json","fetch_events":"https://pith.science/api/pith-number/CRTVOND6QN3ZDXVP3KZTHVIDFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/action/storage_attestation","attest_author":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/action/author_attestation","sign_citation":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/action/citation_signature","submit_replication":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/action/replication_record"}},"created_at":"2026-07-05T11:09:51.344694+00:00","updated_at":"2026-07-05T11:09:51.344694+00:00"}