{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JLGONFRTNCOT7HRQ4MDREAOBEU","short_pith_number":"pith:JLGONFRT","schema_version":"1.0","canonical_sha256":"4acce69633689d3f9e30e3071201c12518799d81ea8bdc7da6f922d4cd7bf53a","source":{"kind":"arxiv","id":"2302.01068","version":5},"attestation_state":"computed","paper":{"title":"FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dingfan Chen, Hui-Po Wang, Mario Fritz, Raouf Kerkouche","submitted_at":"2023-02-02T12:56:46Z","abstract_excerpt":"Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be attributed to the inconsistency between the local and global objectives. To address this issue, we propose FedLAP-DP, a novel privacy-preserving approach for FL. Our formulation involves clients synthesizing a small set of samples that approximate local loss landscapes by simulating the gradients of real images within a local region. Acting as loss surrogate"},"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":"2302.01068","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T12:56:46Z","cross_cats_sorted":[],"title_canon_sha256":"023248f3d0f35a4be3156d13cbfda02c0c6db331ae2deda9ead6bef8398b6fc1","abstract_canon_sha256":"002e7814b9e5813619578cd557dc7be4c37ea7f3cdf45767c5f3d8b12c8f949c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:50.435229Z","signature_b64":"gBXXGT2SxLmfLy5Uq9X7F9fAoHQMJnOsjGE42rkXSRq0CGcT4+6jBoySUKTmEChZr6QrpK6A1ezFtkcWEoBNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4acce69633689d3f9e30e3071201c12518799d81ea8bdc7da6f922d4cd7bf53a","last_reissued_at":"2026-07-05T09:24:50.434713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:50.434713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedLAP-DP: Federated Learning by Sharing Differentially Private Loss Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dingfan Chen, Hui-Po Wang, Mario Fritz, Raouf Kerkouche","submitted_at":"2023-02-02T12:56:46Z","abstract_excerpt":"Conventional gradient-sharing approaches for federated learning (FL), such as FedAvg, rely on aggregation of local models and often face performance degradation under differential privacy (DP) mechanisms or data heterogeneity, which can be attributed to the inconsistency between the local and global objectives. To address this issue, we propose FedLAP-DP, a novel privacy-preserving approach for FL. Our formulation involves clients synthesizing a small set of samples that approximate local loss landscapes by simulating the gradients of real images within a local region. Acting as loss surrogate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01068","kind":"arxiv","version":5},"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/2302.01068/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":"2302.01068","created_at":"2026-07-05T09:24:50.434770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01068v5","created_at":"2026-07-05T09:24:50.434770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01068","created_at":"2026-07-05T09:24:50.434770+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLGONFRTNCOT","created_at":"2026-07-05T09:24:50.434770+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLGONFRTNCOT7HRQ","created_at":"2026-07-05T09:24:50.434770+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLGONFRT","created_at":"2026-07-05T09:24:50.434770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01204","citing_title":"FLRSP: Privacy-Preserving Federated Learning Using Randomly Selected Model Parameters","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU","json":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU.json","graph_json":"https://pith.science/api/pith-number/JLGONFRTNCOT7HRQ4MDREAOBEU/graph.json","events_json":"https://pith.science/api/pith-number/JLGONFRTNCOT7HRQ4MDREAOBEU/events.json","paper":"https://pith.science/paper/JLGONFRT"},"agent_actions":{"view_html":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU","download_json":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU.json","view_paper":"https://pith.science/paper/JLGONFRT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01068&json=true","fetch_graph":"https://pith.science/api/pith-number/JLGONFRTNCOT7HRQ4MDREAOBEU/graph.json","fetch_events":"https://pith.science/api/pith-number/JLGONFRTNCOT7HRQ4MDREAOBEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU/action/storage_attestation","attest_author":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU/action/author_attestation","sign_citation":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU/action/citation_signature","submit_replication":"https://pith.science/pith/JLGONFRTNCOT7HRQ4MDREAOBEU/action/replication_record"}},"created_at":"2026-07-05T09:24:50.434770+00:00","updated_at":"2026-07-05T09:24:50.434770+00:00"}