{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SFJ7J2KPJV4XIVTKQ4BJOEELDA","short_pith_number":"pith:SFJ7J2KP","schema_version":"1.0","canonical_sha256":"9153f4e94f4d7974566a870297108b1808710a0033def651b3ac11e834fb10b4","source":{"kind":"arxiv","id":"2302.13406","version":1},"attestation_state":"computed","paper":{"title":"GNNDelete: A General Strategy for Unlearning in Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chirag Agarwal, George Dasoulas, Huan He, Jiali Cheng, Marinka Zitnik","submitted_at":"2023-02-26T21:04:53Z","abstract_excerpt":"Graph unlearning, which involves deleting graph elements such as nodes, node labels, and relationships from a trained graph neural network (GNN) model, is crucial for real-world applications where data elements may become irrelevant, inaccurate, or privacy-sensitive. However, existing methods for graph unlearning either deteriorate model weights shared across all nodes or fail to effectively delete edges due to their strong dependence on local graph neighborhoods. To address these limitations, we introduce GNNDelete, a novel model-agnostic layer-wise operator that optimizes two critical proper"},"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":"2302.13406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-26T21:04:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2af7220f9cc9390d69606ca2c70627a3d4689411eb3f4984c74c7339aa6b5986","abstract_canon_sha256":"485c59ff4f2c6f08ec880e7ecfd32b1fcfe400a2dd5ef0c1ca422ed0b677e3e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:46.589115Z","signature_b64":"gPNMrWFa5E1bO79yYAJ8Qpefp96/YLPizjpjRR7JEc70vUnsqWdE9DoIwmI0CWaVBPkZwo2KpnBTQEnI9v7BBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9153f4e94f4d7974566a870297108b1808710a0033def651b3ac11e834fb10b4","last_reissued_at":"2026-07-05T05:45:46.588630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:46.588630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GNNDelete: A General Strategy for Unlearning in Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chirag Agarwal, George Dasoulas, Huan He, Jiali Cheng, Marinka Zitnik","submitted_at":"2023-02-26T21:04:53Z","abstract_excerpt":"Graph unlearning, which involves deleting graph elements such as nodes, node labels, and relationships from a trained graph neural network (GNN) model, is crucial for real-world applications where data elements may become irrelevant, inaccurate, or privacy-sensitive. However, existing methods for graph unlearning either deteriorate model weights shared across all nodes or fail to effectively delete edges due to their strong dependence on local graph neighborhoods. To address these limitations, we introduce GNNDelete, a novel model-agnostic layer-wise operator that optimizes two critical proper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13406","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/2302.13406/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":"2302.13406","created_at":"2026-07-05T05:45:46.588691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13406v1","created_at":"2026-07-05T05:45:46.588691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13406","created_at":"2026-07-05T05:45:46.588691+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFJ7J2KPJV4X","created_at":"2026-07-05T05:45:46.588691+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFJ7J2KPJV4XIVTK","created_at":"2026-07-05T05:45:46.588691+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFJ7J2KP","created_at":"2026-07-05T05:45:46.588691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02183","citing_title":"TRU: Targeted Reverse Update for Efficient Multimodal Recommendation Unlearning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA","json":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA.json","graph_json":"https://pith.science/api/pith-number/SFJ7J2KPJV4XIVTKQ4BJOEELDA/graph.json","events_json":"https://pith.science/api/pith-number/SFJ7J2KPJV4XIVTKQ4BJOEELDA/events.json","paper":"https://pith.science/paper/SFJ7J2KP"},"agent_actions":{"view_html":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA","download_json":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA.json","view_paper":"https://pith.science/paper/SFJ7J2KP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13406&json=true","fetch_graph":"https://pith.science/api/pith-number/SFJ7J2KPJV4XIVTKQ4BJOEELDA/graph.json","fetch_events":"https://pith.science/api/pith-number/SFJ7J2KPJV4XIVTKQ4BJOEELDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA/action/storage_attestation","attest_author":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA/action/author_attestation","sign_citation":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA/action/citation_signature","submit_replication":"https://pith.science/pith/SFJ7J2KPJV4XIVTKQ4BJOEELDA/action/replication_record"}},"created_at":"2026-07-05T05:45:46.588691+00:00","updated_at":"2026-07-05T05:45:46.588691+00:00"}