{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IPULJSUGW7C3R5NOPDN2ERU2ZV","short_pith_number":"pith:IPULJSUG","schema_version":"1.0","canonical_sha256":"43e8b4ca86b7c5b8f5ae78dba2469acd7f5dc4c1622a563b9b038c82d5000884","source":{"kind":"arxiv","id":"2206.09140","version":2},"attestation_state":"computed","paper":{"title":"Certified Graph Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Pan, Eli Chien, Olgica Milenkovic","submitted_at":"2022-06-18T07:41:10Z","abstract_excerpt":"Graph-structured data is ubiquitous in practice and often processed using graph neural networks (GNNs). With the adoption of recent laws ensuring the ``right to be forgotten'', the problem of graph data removal has become of significant importance. To address the problem, we introduce the first known framework for \\emph{certified graph unlearning} of GNNs. In contrast to standard machine unlearning, new analytical and heuristic unlearning challenges arise when dealing with complex graph data. First, three different types of unlearning requests need to be considered, including node feature, edg"},"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":"2206.09140","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-18T07:41:10Z","cross_cats_sorted":[],"title_canon_sha256":"9f16b0ad1e792713d27e5089f65f6216419e70de336a0c089a9b51f9db582b1c","abstract_canon_sha256":"fe3b16424caca55ad9ab102fcc760966d78cbb5fb90325988ade0c6a38b1d635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:40.418182Z","signature_b64":"1Xe+U1ba5YTIsrj93DvD8nHog6gtC9eZW/CB6EexL6QA9fLjxOW+yfDfI0RO08YgspFjUMsVXkRI7d+y4YdfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43e8b4ca86b7c5b8f5ae78dba2469acd7f5dc4c1622a563b9b038c82d5000884","last_reissued_at":"2026-07-05T05:11:40.417692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:40.417692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certified Graph Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Pan, Eli Chien, Olgica Milenkovic","submitted_at":"2022-06-18T07:41:10Z","abstract_excerpt":"Graph-structured data is ubiquitous in practice and often processed using graph neural networks (GNNs). With the adoption of recent laws ensuring the ``right to be forgotten'', the problem of graph data removal has become of significant importance. To address the problem, we introduce the first known framework for \\emph{certified graph unlearning} of GNNs. In contrast to standard machine unlearning, new analytical and heuristic unlearning challenges arise when dealing with complex graph data. First, three different types of unlearning requests need to be considered, including node feature, edg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09140","kind":"arxiv","version":2},"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/2206.09140/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":"2206.09140","created_at":"2026-07-05T05:11:40.417762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09140v2","created_at":"2026-07-05T05:11:40.417762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09140","created_at":"2026-07-05T05:11:40.417762+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPULJSUGW7C3","created_at":"2026-07-05T05:11:40.417762+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPULJSUGW7C3R5NO","created_at":"2026-07-05T05:11:40.417762+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPULJSUG","created_at":"2026-07-05T05:11:40.417762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.07406","citing_title":"Machine Unlearning: A Comprehensive Survey","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":221,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17396","citing_title":"Representation-Guided Parameter-Efficient LLM Unlearning","ref_index":144,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV","json":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV.json","graph_json":"https://pith.science/api/pith-number/IPULJSUGW7C3R5NOPDN2ERU2ZV/graph.json","events_json":"https://pith.science/api/pith-number/IPULJSUGW7C3R5NOPDN2ERU2ZV/events.json","paper":"https://pith.science/paper/IPULJSUG"},"agent_actions":{"view_html":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV","download_json":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV.json","view_paper":"https://pith.science/paper/IPULJSUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09140&json=true","fetch_graph":"https://pith.science/api/pith-number/IPULJSUGW7C3R5NOPDN2ERU2ZV/graph.json","fetch_events":"https://pith.science/api/pith-number/IPULJSUGW7C3R5NOPDN2ERU2ZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV/action/storage_attestation","attest_author":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV/action/author_attestation","sign_citation":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV/action/citation_signature","submit_replication":"https://pith.science/pith/IPULJSUGW7C3R5NOPDN2ERU2ZV/action/replication_record"}},"created_at":"2026-07-05T05:11:40.417762+00:00","updated_at":"2026-07-05T05:11:40.417762+00:00"}