{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4KO2RONRS35UJEOHSHALTHHVN3","short_pith_number":"pith:4KO2RONR","schema_version":"1.0","canonical_sha256":"e29da8b9b196fb4491c791c0b99cf56ef6635c63a6c8455dbde9ed4299954d6e","source":{"kind":"arxiv","id":"2406.13499","version":1},"attestation_state":"computed","paper":{"title":"GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SI","authors_text":"Canyixing Cui, Chao Wang, Lin Yuan, Shaojie Qiao, Tao Wu, Xingping Xian, Xinwen Cao, Yanbing Liu","submitted_at":"2024-06-19T12:41:15Z","abstract_excerpt":"Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks. However, these methods can only serve as a defense before poisoning, but cannot repair poisoned GNN. Therefore, there is an urgent need for a method to repair poisoned GNN. In this paper, we address this gap by introducing the novel concept of model repair for GNNs. We propose a repair framework, Repairing Robustness of Graph Neural N"},"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":"2406.13499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SI","submitted_at":"2024-06-19T12:41:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e04860929c495687ae76583c5c76fd3fad5dd789e6b643d4358d89b26b036f3d","abstract_canon_sha256":"f3a4862873caf9a55aa7b8428288f898625d60e81afb6dbae7846a7d0a3104ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:30.841913Z","signature_b64":"375lx036tv2Kw4s5dMd8JXj9aqJwGnHH1gKpklBcnVK6XMbkqONymXCSkE2XRmTIKrf77oV3VEw5dz8AgixaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29da8b9b196fb4491c791c0b99cf56ef6635c63a6c8455dbde9ed4299954d6e","last_reissued_at":"2026-07-05T08:34:30.841483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:30.841483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SI","authors_text":"Canyixing Cui, Chao Wang, Lin Yuan, Shaojie Qiao, Tao Wu, Xingping Xian, Xinwen Cao, Yanbing Liu","submitted_at":"2024-06-19T12:41:15Z","abstract_excerpt":"Graph Neural Networks (GNNs) have demonstrated significant application potential in various fields. However, GNNs are still vulnerable to adversarial attacks. Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks. However, these methods can only serve as a defense before poisoning, but cannot repair poisoned GNN. Therefore, there is an urgent need for a method to repair poisoned GNN. In this paper, we address this gap by introducing the novel concept of model repair for GNNs. We propose a repair framework, Repairing Robustness of Graph Neural N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13499","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/2406.13499/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":"2406.13499","created_at":"2026-07-05T08:34:30.841541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13499v1","created_at":"2026-07-05T08:34:30.841541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13499","created_at":"2026-07-05T08:34:30.841541+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KO2RONRS35U","created_at":"2026-07-05T08:34:30.841541+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KO2RONRS35UJEOH","created_at":"2026-07-05T08:34:30.841541+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KO2RONR","created_at":"2026-07-05T08:34:30.841541+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/4KO2RONRS35UJEOHSHALTHHVN3","json":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3.json","graph_json":"https://pith.science/api/pith-number/4KO2RONRS35UJEOHSHALTHHVN3/graph.json","events_json":"https://pith.science/api/pith-number/4KO2RONRS35UJEOHSHALTHHVN3/events.json","paper":"https://pith.science/paper/4KO2RONR"},"agent_actions":{"view_html":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3","download_json":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3.json","view_paper":"https://pith.science/paper/4KO2RONR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13499&json=true","fetch_graph":"https://pith.science/api/pith-number/4KO2RONRS35UJEOHSHALTHHVN3/graph.json","fetch_events":"https://pith.science/api/pith-number/4KO2RONRS35UJEOHSHALTHHVN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3/action/storage_attestation","attest_author":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3/action/author_attestation","sign_citation":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3/action/citation_signature","submit_replication":"https://pith.science/pith/4KO2RONRS35UJEOHSHALTHHVN3/action/replication_record"}},"created_at":"2026-07-05T08:34:30.841541+00:00","updated_at":"2026-07-05T08:34:30.841541+00:00"}