{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CRTVOND6QN3ZDXVP3KZTHVIDFF","short_pith_number":"pith:CRTVOND6","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"},"canonical_sha256":"146757347e837791deafdab333d503294c14b31bd59bff115ca72c68af68c426","source":{"kind":"arxiv","id":"2505.20020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20020","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20020v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20020","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"CRTVOND6QN3Z","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"CRTVOND6QN3ZDXVP","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"CRTVOND6","created_at":"2026-07-05T11:09:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CRTVOND6QN3ZDXVP3KZTHVIDFF","target":"record","payload":{"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"},"canonical_sha256":"146757347e837791deafdab333d503294c14b31bd59bff115ca72c68af68c426","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"},"source_kind":"arxiv","source_id":"2505.20020","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PfGcBgR3k1y+coh/6bQbpnF5vKCd4whurtoCW0OktrMWUffX2StpGMBUjsR9IDopSX7UCpNXMPaEiRni2sIyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:35:18.350518Z"},"content_sha256":"7aefe107679f1219568153431be7c99220358820326e006756e93d19386a4b02","schema_version":"1.0","event_id":"sha256:7aefe107679f1219568153431be7c99220358820326e006756e93d19386a4b02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CRTVOND6QN3ZDXVP3KZTHVIDFF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:09:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/dFxEE7YBeH30Iv6JgwYRqsf+IzDtNYu6WKsqMlhvHbvVv/CyoMF49Q7bLY5eIaYjQMzdmSVSjoP2zU942zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:35:18.351137Z"},"content_sha256":"7f22efa29fbfccbdb2192b103d39e910b222321929c6fe9008ae439013a10962","schema_version":"1.0","event_id":"sha256:7f22efa29fbfccbdb2192b103d39e910b222321929c6fe9008ae439013a10962"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/bundle.json","state_url":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T02:35:18Z","links":{"resolver":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF","bundle":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/bundle.json","state":"https://pith.science/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRTVOND6QN3ZDXVP3KZTHVIDFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CRTVOND6QN3ZDXVP3KZTHVIDFF","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":"1ad6d78bdaf1898aa42a8613956681eb1840b875f97d657880623960f6b3f6d2","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T14:09:17Z","title_canon_sha256":"2fa77ab403573741dbf36c774259f1ea62e6f313279d85ff84c760dcb46e8a52"},"schema_version":"1.0","source":{"id":"2505.20020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20020","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20020v1","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20020","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"CRTVOND6QN3Z","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"CRTVOND6QN3ZDXVP","created_at":"2026-07-05T11:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"CRTVOND6","created_at":"2026-07-05T11:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:7f22efa29fbfccbdb2192b103d39e910b222321929c6fe9008ae439013a10962","target":"graph","created_at":"2026-07-05T11:09:51Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.20020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adam Belloum, Bernard de Bono, Lang Li, Lei Wang, Natallia Kokash, Paola Grosso, Sara Quinney, Thomas H. Gillespie","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T14:09:17Z","title":"Ontology- and LLM-based Data Harmonization for Federated Learning in Healthcare"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20020","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7aefe107679f1219568153431be7c99220358820326e006756e93d19386a4b02","target":"record","created_at":"2026-07-05T11:09:51Z","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":"1ad6d78bdaf1898aa42a8613956681eb1840b875f97d657880623960f6b3f6d2","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T14:09:17Z","title_canon_sha256":"2fa77ab403573741dbf36c774259f1ea62e6f313279d85ff84c760dcb46e8a52"},"schema_version":"1.0","source":{"id":"2505.20020","kind":"arxiv","version":1}},"canonical_sha256":"146757347e837791deafdab333d503294c14b31bd59bff115ca72c68af68c426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"146757347e837791deafdab333d503294c14b31bd59bff115ca72c68af68c426","first_computed_at":"2026-07-05T11:09:51.344635Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:51.344635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lkKMJ+Oz95431mFTRbvqtkGHWc2hB2IRp34t1ZtO5eq1EKUo7/0rxZW3A4Huc4R/xB8uLjFOcM2UyJiG0jx9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:51.345126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aefe107679f1219568153431be7c99220358820326e006756e93d19386a4b02","sha256:7f22efa29fbfccbdb2192b103d39e910b222321929c6fe9008ae439013a10962"],"state_sha256":"e26ee2942947e1096d505dde1e573f537c034995e2fc9f99b774c0d9c48925f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VC69jFhkru1JwIEsqnV3SX+CWYE+UgXSrsml8nJQ1i/fowlA0/9pgIlBCiJDd/VEOpq84rYGbag/5YGfC+NPBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:35:18.355251Z","bundle_sha256":"e690905de60830b943b0e12641a112d7f98c2102dc7ee604d01b93d583650d3b"}}