{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K7IUSTJRO4KO3RMCPYX5HYFPNV","short_pith_number":"pith:K7IUSTJR","schema_version":"1.0","canonical_sha256":"57d1494d317714edc5827e2fd3e0af6d6c15a32eba24c5233bf64a4243c6eeeb","source":{"kind":"arxiv","id":"2412.13466","version":2},"attestation_state":"computed","paper":{"title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bing Xue, Qiang Zhang, Wenbin Pei, Xinrui Yu","submitted_at":"2024-12-18T03:25:11Z","abstract_excerpt":"In federated learning, federated unlearning is a technique that provides clients with a rollback mechanism that allows them to withdraw their data contribution without training from scratch. However, existing research has not considered scenarios with skewed label distributions. Unfortunately, the unlearning of a client with skewed data usually results in biased models and makes it difficult to deliver high-quality service, complicating the recovery process. This paper proposes a recovery method of federated unlearning with skewed label distributions. Specifically, we first adopt a strategy th"},"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":"2412.13466","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T03:25:11Z","cross_cats_sorted":[],"title_canon_sha256":"d49da501f0c9a312544ecf9be306893c1284dfc73156fab4b107b37b8d7c92ed","abstract_canon_sha256":"81b1f438b2ceefd0e7b20894a8ac311e1417d79822b1b618bd83651c97cfbade"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:19.930417Z","signature_b64":"NUpb9swzs4esNWg2wvphMwzD7R3e+KF+Dlxzg0iS1+4Hxwi8I2X/90g+U9JwOBVRPGj56r44HJq29GhlGJjRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57d1494d317714edc5827e2fd3e0af6d6c15a32eba24c5233bf64a4243c6eeeb","last_reissued_at":"2026-07-05T09:52:19.930013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:19.930013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Unlearning Model Recovery in Data with Skewed Label Distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bing Xue, Qiang Zhang, Wenbin Pei, Xinrui Yu","submitted_at":"2024-12-18T03:25:11Z","abstract_excerpt":"In federated learning, federated unlearning is a technique that provides clients with a rollback mechanism that allows them to withdraw their data contribution without training from scratch. However, existing research has not considered scenarios with skewed label distributions. Unfortunately, the unlearning of a client with skewed data usually results in biased models and makes it difficult to deliver high-quality service, complicating the recovery process. This paper proposes a recovery method of federated unlearning with skewed label distributions. Specifically, we first adopt a strategy th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13466","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/2412.13466/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":"2412.13466","created_at":"2026-07-05T09:52:19.930076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.13466v2","created_at":"2026-07-05T09:52:19.930076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13466","created_at":"2026-07-05T09:52:19.930076+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7IUSTJRO4KO","created_at":"2026-07-05T09:52:19.930076+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7IUSTJRO4KO3RMC","created_at":"2026-07-05T09:52:19.930076+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7IUSTJR","created_at":"2026-07-05T09:52:19.930076+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/K7IUSTJRO4KO3RMCPYX5HYFPNV","json":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV.json","graph_json":"https://pith.science/api/pith-number/K7IUSTJRO4KO3RMCPYX5HYFPNV/graph.json","events_json":"https://pith.science/api/pith-number/K7IUSTJRO4KO3RMCPYX5HYFPNV/events.json","paper":"https://pith.science/paper/K7IUSTJR"},"agent_actions":{"view_html":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV","download_json":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV.json","view_paper":"https://pith.science/paper/K7IUSTJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.13466&json=true","fetch_graph":"https://pith.science/api/pith-number/K7IUSTJRO4KO3RMCPYX5HYFPNV/graph.json","fetch_events":"https://pith.science/api/pith-number/K7IUSTJRO4KO3RMCPYX5HYFPNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV/action/storage_attestation","attest_author":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV/action/author_attestation","sign_citation":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV/action/citation_signature","submit_replication":"https://pith.science/pith/K7IUSTJRO4KO3RMCPYX5HYFPNV/action/replication_record"}},"created_at":"2026-07-05T09:52:19.930076+00:00","updated_at":"2026-07-05T09:52:19.930076+00:00"}