{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:57YSPWZU4ZMHRNJZH3QN4TEUV3","short_pith_number":"pith:57YSPWZU","schema_version":"1.0","canonical_sha256":"eff127db34e65878b5393ee0de4c94aee091b969a5e87a231cfc4428a8d1a978","source":{"kind":"arxiv","id":"2509.25906","version":2},"attestation_state":"computed","paper":{"title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shijian Su, Shuai Wang, Xiuhua Wang, Yiwei Li, Zhuojun Tian","submitted_at":"2025-09-30T07:51:06Z","abstract_excerpt":"Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client's model is partitioned into a private submodel, retained locally, and a public submodel, shared for global aggregation. The calibrated Gaussian noise is injected only into the public subm"},"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":"2509.25906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T07:51:06Z","cross_cats_sorted":[],"title_canon_sha256":"6a606a87727fc862bf29111086fee946419dc07fc604e62b220021d6637ed884","abstract_canon_sha256":"4f5df5f069703540311f523883c3359aef67930b4f741633d572d29b744540cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:27.492064Z","signature_b64":"zHbQp0nk9S9GbzZS+5JLpFQ8q7KFDmclDeZRSTQh7pl8UxCLOOLzWXvqG5jxZvqUMwC/w/71KsI0DzVAP7SyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eff127db34e65878b5393ee0de4c94aee091b969a5e87a231cfc4428a8d1a978","last_reissued_at":"2026-06-01T02:03:27.491121Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:27.491121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shijian Su, Shuai Wang, Xiuhua Wang, Yiwei Li, Zhuojun Tian","submitted_at":"2025-09-30T07:51:06Z","abstract_excerpt":"Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-splitting privacy-amplified federated learning (MS-PAFL), a novel framework that combines structural model splitting with statistical privacy amplification. In this framework, each client's model is partitioned into a private submodel, retained locally, and a public submodel, shared for global aggregation. The calibrated Gaussian noise is injected only into the public subm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.25906","kind":"arxiv","version":2},"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/2509.25906/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":"2509.25906","created_at":"2026-06-01T02:03:27.491242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.25906v2","created_at":"2026-06-01T02:03:27.491242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.25906","created_at":"2026-06-01T02:03:27.491242+00:00"},{"alias_kind":"pith_short_12","alias_value":"57YSPWZU4ZMH","created_at":"2026-06-01T02:03:27.491242+00:00"},{"alias_kind":"pith_short_16","alias_value":"57YSPWZU4ZMHRNJZ","created_at":"2026-06-01T02:03:27.491242+00:00"},{"alias_kind":"pith_short_8","alias_value":"57YSPWZU","created_at":"2026-06-01T02:03:27.491242+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/57YSPWZU4ZMHRNJZH3QN4TEUV3","json":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3.json","graph_json":"https://pith.science/api/pith-number/57YSPWZU4ZMHRNJZH3QN4TEUV3/graph.json","events_json":"https://pith.science/api/pith-number/57YSPWZU4ZMHRNJZH3QN4TEUV3/events.json","paper":"https://pith.science/paper/57YSPWZU"},"agent_actions":{"view_html":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3","download_json":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3.json","view_paper":"https://pith.science/paper/57YSPWZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.25906&json=true","fetch_graph":"https://pith.science/api/pith-number/57YSPWZU4ZMHRNJZH3QN4TEUV3/graph.json","fetch_events":"https://pith.science/api/pith-number/57YSPWZU4ZMHRNJZH3QN4TEUV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3/action/storage_attestation","attest_author":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3/action/author_attestation","sign_citation":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3/action/citation_signature","submit_replication":"https://pith.science/pith/57YSPWZU4ZMHRNJZH3QN4TEUV3/action/replication_record"}},"created_at":"2026-06-01T02:03:27.491242+00:00","updated_at":"2026-06-01T02:03:27.491242+00:00"}