{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6KBPVVKKBH74TK426RIQ6RBCLR","short_pith_number":"pith:6KBPVVKK","schema_version":"1.0","canonical_sha256":"f282fad54a09ffc9ab9af4510f44225c62897e631c29f7d5dc6d9c374eba1ee4","source":{"kind":"arxiv","id":"2406.12516","version":1},"attestation_state":"computed","paper":{"title":"Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CR","authors_text":"Heng Xu, Lefeng Zhang, Philip S. Yu, Tianqing Zhu, Wanlei Zhou","submitted_at":"2024-06-18T11:43:20Z","abstract_excerpt":"Federated learning is a promising privacy-preserving paradigm for distributed machine learning. In this context, there is sometimes a need for a specialized process called machine unlearning, which is required when the effect of some specific training samples needs to be removed from a learning model due to privacy, security, usability, and/or legislative factors. However, problems arise when current centralized unlearning methods are applied to existing federated learning, in which the server aims to remove all information about a class from the global model. Centralized unlearning usually fo"},"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":"2406.12516","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-18T11:43:20Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"f3b2871310981434df25fe1146e44bf82aa01caf5d260555bf95c034bd98c9dc","abstract_canon_sha256":"c40f2c63b5e03ec7e0559b3492f9c2d3de2cef30eed66b3f67ac393b06f6995c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:47.716369Z","signature_b64":"TgkU2lVxbwkc9b7qajPXjugMYEGaYVeJn2kMWE/z110ANhSCDWldNq7uwA/IV2XdE1ZNxOIrx5vJTFbWYZAZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f282fad54a09ffc9ab9af4510f44225c62897e631c29f7d5dc6d9c374eba1ee4","last_reissued_at":"2026-07-05T08:33:47.715924Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:47.715924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.CR","authors_text":"Heng Xu, Lefeng Zhang, Philip S. Yu, Tianqing Zhu, Wanlei Zhou","submitted_at":"2024-06-18T11:43:20Z","abstract_excerpt":"Federated learning is a promising privacy-preserving paradigm for distributed machine learning. In this context, there is sometimes a need for a specialized process called machine unlearning, which is required when the effect of some specific training samples needs to be removed from a learning model due to privacy, security, usability, and/or legislative factors. However, problems arise when current centralized unlearning methods are applied to existing federated learning, in which the server aims to remove all information about a class from the global model. Centralized unlearning usually fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12516","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/2406.12516/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":"2406.12516","created_at":"2026-07-05T08:33:47.715981+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12516v1","created_at":"2026-07-05T08:33:47.715981+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12516","created_at":"2026-07-05T08:33:47.715981+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KBPVVKKBH74","created_at":"2026-07-05T08:33:47.715981+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KBPVVKKBH74TK42","created_at":"2026-07-05T08:33:47.715981+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KBPVVKK","created_at":"2026-07-05T08:33:47.715981+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/6KBPVVKKBH74TK426RIQ6RBCLR","json":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR.json","graph_json":"https://pith.science/api/pith-number/6KBPVVKKBH74TK426RIQ6RBCLR/graph.json","events_json":"https://pith.science/api/pith-number/6KBPVVKKBH74TK426RIQ6RBCLR/events.json","paper":"https://pith.science/paper/6KBPVVKK"},"agent_actions":{"view_html":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR","download_json":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR.json","view_paper":"https://pith.science/paper/6KBPVVKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12516&json=true","fetch_graph":"https://pith.science/api/pith-number/6KBPVVKKBH74TK426RIQ6RBCLR/graph.json","fetch_events":"https://pith.science/api/pith-number/6KBPVVKKBH74TK426RIQ6RBCLR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR/action/storage_attestation","attest_author":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR/action/author_attestation","sign_citation":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR/action/citation_signature","submit_replication":"https://pith.science/pith/6KBPVVKKBH74TK426RIQ6RBCLR/action/replication_record"}},"created_at":"2026-07-05T08:33:47.715981+00:00","updated_at":"2026-07-05T08:33:47.715981+00:00"}