{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7NEQS6TDH365PTZCZZQEYM4E37","short_pith_number":"pith:7NEQS6TD","schema_version":"1.0","canonical_sha256":"fb49097a633efdd7cf22ce604c3384dff2b1028be75fcf47891964f8959ac225","source":{"kind":"arxiv","id":"2606.24113","version":1},"attestation_state":"computed","paper":{"title":"FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feihong Nan, Ji Wang, Pan Wang, Quan Wen, Weidong Bao, Xiongtao Zhang, Zhengyi Zhong","submitted_at":"2026-06-23T03:59:22Z","abstract_excerpt":"Federated unlearning (FU) is critical for complying with legal mandates like the right to be forgotten in decentralized systems, yet current methods face a persistent dilemma between non-target knowledge loss and high request latency. To resolve these issues, we propose FedUP, a one-shot federated unlearning framework utilizing lightweight pluggable filters that act as a \"knowledge funnel\" to screen out target data while preserving original model performance. By freezing original model parameters and training filters at the server side using differentially private (DP)-protected class centroid"},"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":"2606.24113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-23T03:59:22Z","cross_cats_sorted":[],"title_canon_sha256":"2c411004a6c71306f844578f9cbe71695b042945a5e57dc104c9b7e5cec3d03d","abstract_canon_sha256":"43fbe23f8a760ad86424cbf6b7b009e9c5ad7546dd38e7a6e5e44852aba9c698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:41.409568Z","signature_b64":"6s0njzrW+J8K6GXYtKGqnEjDzXwsFGnR0wq5GM7M22CUndW4L+YCK9cyhqC0rZi2n8ukWYJWxZAafiRsxHcqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb49097a633efdd7cf22ce604c3384dff2b1028be75fcf47891964f8959ac225","last_reissued_at":"2026-06-24T01:14:41.409175Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:41.409175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Feihong Nan, Ji Wang, Pan Wang, Quan Wen, Weidong Bao, Xiongtao Zhang, Zhengyi Zhong","submitted_at":"2026-06-23T03:59:22Z","abstract_excerpt":"Federated unlearning (FU) is critical for complying with legal mandates like the right to be forgotten in decentralized systems, yet current methods face a persistent dilemma between non-target knowledge loss and high request latency. To resolve these issues, we propose FedUP, a one-shot federated unlearning framework utilizing lightweight pluggable filters that act as a \"knowledge funnel\" to screen out target data while preserving original model performance. By freezing original model parameters and training filters at the server side using differentially private (DP)-protected class centroid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24113","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/2606.24113/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":"2606.24113","created_at":"2026-06-24T01:14:41.409238+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24113v1","created_at":"2026-06-24T01:14:41.409238+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24113","created_at":"2026-06-24T01:14:41.409238+00:00"},{"alias_kind":"pith_short_12","alias_value":"7NEQS6TDH365","created_at":"2026-06-24T01:14:41.409238+00:00"},{"alias_kind":"pith_short_16","alias_value":"7NEQS6TDH365PTZC","created_at":"2026-06-24T01:14:41.409238+00:00"},{"alias_kind":"pith_short_8","alias_value":"7NEQS6TD","created_at":"2026-06-24T01:14:41.409238+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/7NEQS6TDH365PTZCZZQEYM4E37","json":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37.json","graph_json":"https://pith.science/api/pith-number/7NEQS6TDH365PTZCZZQEYM4E37/graph.json","events_json":"https://pith.science/api/pith-number/7NEQS6TDH365PTZCZZQEYM4E37/events.json","paper":"https://pith.science/paper/7NEQS6TD"},"agent_actions":{"view_html":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37","download_json":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37.json","view_paper":"https://pith.science/paper/7NEQS6TD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24113&json=true","fetch_graph":"https://pith.science/api/pith-number/7NEQS6TDH365PTZCZZQEYM4E37/graph.json","fetch_events":"https://pith.science/api/pith-number/7NEQS6TDH365PTZCZZQEYM4E37/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37/action/storage_attestation","attest_author":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37/action/author_attestation","sign_citation":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37/action/citation_signature","submit_replication":"https://pith.science/pith/7NEQS6TDH365PTZCZZQEYM4E37/action/replication_record"}},"created_at":"2026-06-24T01:14:41.409238+00:00","updated_at":"2026-06-24T01:14:41.409238+00:00"}