{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JYNILHKMG7I5QFQLKZPOHHRUNJ","short_pith_number":"pith:JYNILHKM","schema_version":"1.0","canonical_sha256":"4e1a859d4c37d1d8160b565ee39e346a4083afd9e11d58488600b67631b397fb","source":{"kind":"arxiv","id":"2207.05521","version":3},"attestation_state":"computed","paper":{"title":"Federated Unlearning: How to Efficiently Erase a Client in FL?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Ambrish Rawat, Anisa Halimi, Nathalie Baracaldo, Swanand Kadhe","submitted_at":"2022-07-12T13:24:23Z","abstract_excerpt":"With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data. However, existing unlearning methods in the machine learning context can not be directly applied in the context of distributed settings like federated learning due to the differences in learning protocol and the presence of multiple actors. In this paper, we tackle the problem of federated unlearning for the case of erasing a client by removing the influence of their entire local data from the trained global model. To erase a c"},"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":"2207.05521","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-12T13:24:23Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"31e266c9b07fdf6ba86efca335c3b691536a4d5ffc7d9ffbd727f6242db5a0fd","abstract_canon_sha256":"3b8d0297ec3453535c4a48f7fb4042c8ecd0bcf9553756061364241f62ab722e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:17.790618Z","signature_b64":"bJlsvoS/Jtm2UE30Ru5I2nBbjFBL+BMFRkzc7I316fy6501Hpr37Kcy3sz9KAIp86NO7n+/LlRr3n4FZdJCCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e1a859d4c37d1d8160b565ee39e346a4083afd9e11d58488600b67631b397fb","last_reissued_at":"2026-07-05T07:03:17.790075Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:17.790075Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Unlearning: How to Efficiently Erase a Client in FL?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Ambrish Rawat, Anisa Halimi, Nathalie Baracaldo, Swanand Kadhe","submitted_at":"2022-07-12T13:24:23Z","abstract_excerpt":"With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data. However, existing unlearning methods in the machine learning context can not be directly applied in the context of distributed settings like federated learning due to the differences in learning protocol and the presence of multiple actors. In this paper, we tackle the problem of federated unlearning for the case of erasing a client by removing the influence of their entire local data from the trained global model. To erase a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05521","kind":"arxiv","version":3},"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/2207.05521/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":"2207.05521","created_at":"2026-07-05T07:03:17.790139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05521v3","created_at":"2026-07-05T07:03:17.790139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05521","created_at":"2026-07-05T07:03:17.790139+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYNILHKMG7I5","created_at":"2026-07-05T07:03:17.790139+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYNILHKMG7I5QFQL","created_at":"2026-07-05T07:03:17.790139+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYNILHKM","created_at":"2026-07-05T07:03:17.790139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26715","citing_title":"Image Feature Fusion-based Federated Client Unlearning (FCU)","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2408.07587","citing_title":"FedQUIT: On-Device Federated Unlearning via a Quasi-Competent Virtual Teacher","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22589","citing_title":"SCALE: Sensitivity-Aware Federated Unlearning with Information Freshness Optimization for Mobile Edge Computing","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20341","citing_title":"Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04030","citing_title":"Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26809","citing_title":"Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04713","citing_title":"Not Every Subject Should Stay: Machine Unlearning for Noisy Engagement Recognition","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00733","citing_title":"EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ","json":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ.json","graph_json":"https://pith.science/api/pith-number/JYNILHKMG7I5QFQLKZPOHHRUNJ/graph.json","events_json":"https://pith.science/api/pith-number/JYNILHKMG7I5QFQLKZPOHHRUNJ/events.json","paper":"https://pith.science/paper/JYNILHKM"},"agent_actions":{"view_html":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ","download_json":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ.json","view_paper":"https://pith.science/paper/JYNILHKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05521&json=true","fetch_graph":"https://pith.science/api/pith-number/JYNILHKMG7I5QFQLKZPOHHRUNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JYNILHKMG7I5QFQLKZPOHHRUNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ/action/storage_attestation","attest_author":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ/action/author_attestation","sign_citation":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ/action/citation_signature","submit_replication":"https://pith.science/pith/JYNILHKMG7I5QFQLKZPOHHRUNJ/action/replication_record"}},"created_at":"2026-07-05T07:03:17.790139+00:00","updated_at":"2026-07-05T07:03:17.790139+00:00"}