{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WD6XNV6OHGGUEX5QFPZDP2EBBE","short_pith_number":"pith:WD6XNV6O","schema_version":"1.0","canonical_sha256":"b0fd76d7ce398d425fb02bf237e881093784fae173ba86c8a975dd6123be889a","source":{"kind":"arxiv","id":"2302.12448","version":1},"attestation_state":"computed","paper":{"title":"Subspace based Federated Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Guanghao Li, Han Hu, Li Shen, Yan Sun, Yue Hu","submitted_at":"2023-02-24T04:29:44Z","abstract_excerpt":"Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data. Federated unlearning is an inverse FL process that aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten. Most existing federated unlearning algorithms require the server to store the history of the parameter updates, which is not applicable in scenarios where the server storage resource is constrained. In this paper, we propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, 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":"2302.12448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T04:29:44Z","cross_cats_sorted":["cs.CR","cs.DC","math.OC"],"title_canon_sha256":"4b71073f313b7b853112f4ef28b753d6a6801aa8289327819725b83a9b9219f3","abstract_canon_sha256":"5831180e708c02ba8a0a019c4279dab4923e964de89baa85c999415bc1e517ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:09.893150Z","signature_b64":"w2BTIxwCfxI9rsmrGKQvgTRXiuuS9rNSmDltYDILACKCJRMafxxMJ6I7rS+DIWkj9yAbm4uOebgk57KwUGoRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0fd76d7ce398d425fb02bf237e881093784fae173ba86c8a975dd6123be889a","last_reissued_at":"2026-07-05T05:45:09.892659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:09.892659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subspace based Federated Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Guanghao Li, Han Hu, Li Shen, Yan Sun, Yue Hu","submitted_at":"2023-02-24T04:29:44Z","abstract_excerpt":"Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data. Federated unlearning is an inverse FL process that aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten. Most existing federated unlearning algorithms require the server to store the history of the parameter updates, which is not applicable in scenarios where the server storage resource is constrained. In this paper, we propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12448","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/2302.12448/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":"2302.12448","created_at":"2026-07-05T05:45:09.892725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12448v1","created_at":"2026-07-05T05:45:09.892725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12448","created_at":"2026-07-05T05:45:09.892725+00:00"},{"alias_kind":"pith_short_12","alias_value":"WD6XNV6OHGGU","created_at":"2026-07-05T05:45:09.892725+00:00"},{"alias_kind":"pith_short_16","alias_value":"WD6XNV6OHGGUEX5Q","created_at":"2026-07-05T05:45:09.892725+00:00"},{"alias_kind":"pith_short_8","alias_value":"WD6XNV6O","created_at":"2026-07-05T05:45:09.892725+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/WD6XNV6OHGGUEX5QFPZDP2EBBE","json":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE.json","graph_json":"https://pith.science/api/pith-number/WD6XNV6OHGGUEX5QFPZDP2EBBE/graph.json","events_json":"https://pith.science/api/pith-number/WD6XNV6OHGGUEX5QFPZDP2EBBE/events.json","paper":"https://pith.science/paper/WD6XNV6O"},"agent_actions":{"view_html":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE","download_json":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE.json","view_paper":"https://pith.science/paper/WD6XNV6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12448&json=true","fetch_graph":"https://pith.science/api/pith-number/WD6XNV6OHGGUEX5QFPZDP2EBBE/graph.json","fetch_events":"https://pith.science/api/pith-number/WD6XNV6OHGGUEX5QFPZDP2EBBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE/action/storage_attestation","attest_author":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE/action/author_attestation","sign_citation":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE/action/citation_signature","submit_replication":"https://pith.science/pith/WD6XNV6OHGGUEX5QFPZDP2EBBE/action/replication_record"}},"created_at":"2026-07-05T05:45:09.892725+00:00","updated_at":"2026-07-05T05:45:09.892725+00:00"}