{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCFELLSVBZSCUT6X4GKOTZBBT4","short_pith_number":"pith:FCFELLSV","schema_version":"1.0","canonical_sha256":"288a45ae550e642a4fd7e194e9e4219f1d218d9187e5afe15ecaa447faecece5","source":{"kind":"arxiv","id":"2502.20709","version":1},"attestation_state":"computed","paper":{"title":"Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingxuan Zhou, Ji Wang, Lingjuan Lyu, Shuai Zhang, Weidong Bao, Wei Yang Bryan Lim, Zhengyi Zhong","submitted_at":"2025-02-28T04:35:26Z","abstract_excerpt":"Federated Learning is a promising paradigm for privacy-preserving collaborative model training. In practice, it is essential not only to continuously train the model to acquire new knowledge but also to guarantee old knowledge the right to be forgotten (i.e., federated unlearning), especially for privacy-sensitive information or harmful knowledge. However, current federated unlearning methods face several challenges, including indiscriminate unlearning of cross-client knowledge, irreversibility of unlearning, and significant unlearning costs. To this end, we propose a method named FUSED, which"},"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":"2502.20709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T04:35:26Z","cross_cats_sorted":[],"title_canon_sha256":"e916caaf13e00f41a21b07c8427847019d5431e01343712e0fb9dc80d1f83f3b","abstract_canon_sha256":"123dc5eea9802d9a386e7eece96c8725d889ca024bb63c589e363a621ae68fd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:38.334593Z","signature_b64":"S+gcJjkV5Kd6FBkCE7xDA8GfYlqGZW7jTiZWQCdzoIs5dOXr8rbt4CoJggbA4k5zgA6LdzT1eDhwOsS+clTtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"288a45ae550e642a4fd7e194e9e4219f1d218d9187e5afe15ecaa447faecece5","last_reissued_at":"2026-07-05T10:21:38.334081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:38.334081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlearning through Knowledge Overwriting: Reversible Federated Unlearning via Selective Sparse Adapter","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jingxuan Zhou, Ji Wang, Lingjuan Lyu, Shuai Zhang, Weidong Bao, Wei Yang Bryan Lim, Zhengyi Zhong","submitted_at":"2025-02-28T04:35:26Z","abstract_excerpt":"Federated Learning is a promising paradigm for privacy-preserving collaborative model training. In practice, it is essential not only to continuously train the model to acquire new knowledge but also to guarantee old knowledge the right to be forgotten (i.e., federated unlearning), especially for privacy-sensitive information or harmful knowledge. However, current federated unlearning methods face several challenges, including indiscriminate unlearning of cross-client knowledge, irreversibility of unlearning, and significant unlearning costs. To this end, we propose a method named FUSED, which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20709","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/2502.20709/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":"2502.20709","created_at":"2026-07-05T10:21:38.334141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20709v1","created_at":"2026-07-05T10:21:38.334141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20709","created_at":"2026-07-05T10:21:38.334141+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCFELLSVBZSC","created_at":"2026-07-05T10:21:38.334141+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCFELLSVBZSCUT6X","created_at":"2026-07-05T10:21:38.334141+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCFELLSV","created_at":"2026-07-05T10:21:38.334141+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/FCFELLSVBZSCUT6X4GKOTZBBT4","json":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4.json","graph_json":"https://pith.science/api/pith-number/FCFELLSVBZSCUT6X4GKOTZBBT4/graph.json","events_json":"https://pith.science/api/pith-number/FCFELLSVBZSCUT6X4GKOTZBBT4/events.json","paper":"https://pith.science/paper/FCFELLSV"},"agent_actions":{"view_html":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4","download_json":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4.json","view_paper":"https://pith.science/paper/FCFELLSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20709&json=true","fetch_graph":"https://pith.science/api/pith-number/FCFELLSVBZSCUT6X4GKOTZBBT4/graph.json","fetch_events":"https://pith.science/api/pith-number/FCFELLSVBZSCUT6X4GKOTZBBT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4/action/storage_attestation","attest_author":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4/action/author_attestation","sign_citation":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4/action/citation_signature","submit_replication":"https://pith.science/pith/FCFELLSVBZSCUT6X4GKOTZBBT4/action/replication_record"}},"created_at":"2026-07-05T10:21:38.334141+00:00","updated_at":"2026-07-05T10:21:38.334141+00:00"}