{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UZOKQRZVYMA6DT5VUXQS2SWBUX","short_pith_number":"pith:UZOKQRZV","schema_version":"1.0","canonical_sha256":"a65ca84735c301e1cfb5a5e12d4ac1a5d54bcd5dab6cff35243a75d29ef5cd21","source":{"kind":"arxiv","id":"2607.19524","version":1},"attestation_state":"computed","paper":{"title":"SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Akarsh K Nair, Amna Burzic, Andy Burton, David Baldwin, David J. Brown, Emma O'Dowd, Jun He, Mufti Mahmud, Muhammad Arifur Rahman, Nicholas Shopland, Yuan Shen","submitted_at":"2026-07-21T19:12:48Z","abstract_excerpt":"Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted data sharing, client heterogeneity, class imbalance, and the lack of realistic tabular electronic health record (EHR) benchmarks. Synthetic data generation may alleviate data scarcity, yet its integration with federated optimisation has received limited systematic study. We propose SynPre-FL, a unified framework combining high-fidelity synthetic EHR generation with synthetic-pretrained FL for robust prediction under non-IID conditions. A latent au"},"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":"2607.19524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-21T19:12:48Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"8d447cf122049f3cf23e061655da966107e8b47a7d6056488af58ffdbd6c3be3","abstract_canon_sha256":"5bca5e5bf4f70f2193a0744b7ab33bf943fba3b60298751f65be820c7c801337"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:55.082024Z","signature_b64":"w3uY8iuw6ggZlbcx4PAcDK9qob6GlwAUPYSPeQq+OnmxlwnLuNqJp6NlabKyz/q8OO4Aa6vIx7nPsMHB21CzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a65ca84735c301e1cfb5a5e12d4ac1a5d54bcd5dab6cff35243a75d29ef5cd21","last_reissued_at":"2026-07-23T00:23:55.081123Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:55.081123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Akarsh K Nair, Amna Burzic, Andy Burton, David Baldwin, David J. Brown, Emma O'Dowd, Jun He, Mufti Mahmud, Muhammad Arifur Rahman, Nicholas Shopland, Yuan Shen","submitted_at":"2026-07-21T19:12:48Z","abstract_excerpt":"Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted data sharing, client heterogeneity, class imbalance, and the lack of realistic tabular electronic health record (EHR) benchmarks. Synthetic data generation may alleviate data scarcity, yet its integration with federated optimisation has received limited systematic study. We propose SynPre-FL, a unified framework combining high-fidelity synthetic EHR generation with synthetic-pretrained FL for robust prediction under non-IID conditions. A latent au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19524","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/2607.19524/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":"2607.19524","created_at":"2026-07-23T00:23:55.081589+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19524v1","created_at":"2026-07-23T00:23:55.081589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19524","created_at":"2026-07-23T00:23:55.081589+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZOKQRZVYMA6","created_at":"2026-07-23T00:23:55.081589+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZOKQRZVYMA6DT5V","created_at":"2026-07-23T00:23:55.081589+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZOKQRZV","created_at":"2026-07-23T00:23:55.081589+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/UZOKQRZVYMA6DT5VUXQS2SWBUX","json":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX.json","graph_json":"https://pith.science/api/pith-number/UZOKQRZVYMA6DT5VUXQS2SWBUX/graph.json","events_json":"https://pith.science/api/pith-number/UZOKQRZVYMA6DT5VUXQS2SWBUX/events.json","paper":"https://pith.science/paper/UZOKQRZV"},"agent_actions":{"view_html":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX","download_json":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX.json","view_paper":"https://pith.science/paper/UZOKQRZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19524&json=true","fetch_graph":"https://pith.science/api/pith-number/UZOKQRZVYMA6DT5VUXQS2SWBUX/graph.json","fetch_events":"https://pith.science/api/pith-number/UZOKQRZVYMA6DT5VUXQS2SWBUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX/action/storage_attestation","attest_author":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX/action/author_attestation","sign_citation":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX/action/citation_signature","submit_replication":"https://pith.science/pith/UZOKQRZVYMA6DT5VUXQS2SWBUX/action/replication_record"}},"created_at":"2026-07-23T00:23:55.081589+00:00","updated_at":"2026-07-23T00:23:55.081589+00:00"}