{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EBR4DY2QNNSOWUELQUSQR4TNK4","short_pith_number":"pith:EBR4DY2Q","schema_version":"1.0","canonical_sha256":"2063c1e3506b64eb508b852508f26d5727629711d5e916672e8fd6d1ae4ea001","source":{"kind":"arxiv","id":"2412.00789","version":4},"attestation_state":"computed","paper":{"title":"A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Akshit Sinha, Arvindh Arun, Debangan Mishra, Ponnurangam Kumaraguru, Shashwat Goel, Sumit Kumar, Varshita Kolipaka","submitted_at":"2024-12-01T12:23:25Z","abstract_excerpt":"Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distributed (i.i.d.) assumption, adversarial manipulations or incorrect data can propagate to other data points through message passing, which deteriorates the model's performance. To allow model developers to remove the adverse effects of manipulated entities from a trained GNN, we study the recently formulated problem of Corrective Unlearning. We find that current graph unlearning methods fail to unlearn the effect of ma"},"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":"2412.00789","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-01T12:23:25Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"6ceb9320d71736f42d5ee073f277e175dffa5eb1f1a9e627ac6890ac83a36b20","abstract_canon_sha256":"dd7d4c4a9b49ad67cb72b0bbdb53767019ffba9ffbb88c2f3e0a29a4879a3c71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:16.370052Z","signature_b64":"+0GWdPCTb+1XGQ9twrDaEz4X3U7QZjEKfet1nBOucFyv3WF16eWTv33a0JQVlyOr9b+x8kyesce4AXf7n6dJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2063c1e3506b64eb508b852508f26d5727629711d5e916672e8fd6d1ae4ea001","last_reissued_at":"2026-07-05T11:18:16.369543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:16.369543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Cognac Shot To Forget Bad Memories: Corrective Unlearning for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Akshit Sinha, Arvindh Arun, Debangan Mishra, Ponnurangam Kumaraguru, Shashwat Goel, Sumit Kumar, Varshita Kolipaka","submitted_at":"2024-12-01T12:23:25Z","abstract_excerpt":"Graph Neural Networks (GNNs) are increasingly being used for a variety of ML applications on graph data. Because graph data does not follow the independently and identically distributed (i.i.d.) assumption, adversarial manipulations or incorrect data can propagate to other data points through message passing, which deteriorates the model's performance. To allow model developers to remove the adverse effects of manipulated entities from a trained GNN, we study the recently formulated problem of Corrective Unlearning. We find that current graph unlearning methods fail to unlearn the effect of ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00789","kind":"arxiv","version":4},"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/2412.00789/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":"2412.00789","created_at":"2026-07-05T11:18:16.369602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00789v4","created_at":"2026-07-05T11:18:16.369602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00789","created_at":"2026-07-05T11:18:16.369602+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBR4DY2QNNSO","created_at":"2026-07-05T11:18:16.369602+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBR4DY2QNNSOWUEL","created_at":"2026-07-05T11:18:16.369602+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBR4DY2Q","created_at":"2026-07-05T11:18:16.369602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16548","citing_title":"Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4","json":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4.json","graph_json":"https://pith.science/api/pith-number/EBR4DY2QNNSOWUELQUSQR4TNK4/graph.json","events_json":"https://pith.science/api/pith-number/EBR4DY2QNNSOWUELQUSQR4TNK4/events.json","paper":"https://pith.science/paper/EBR4DY2Q"},"agent_actions":{"view_html":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4","download_json":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4.json","view_paper":"https://pith.science/paper/EBR4DY2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00789&json=true","fetch_graph":"https://pith.science/api/pith-number/EBR4DY2QNNSOWUELQUSQR4TNK4/graph.json","fetch_events":"https://pith.science/api/pith-number/EBR4DY2QNNSOWUELQUSQR4TNK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4/action/storage_attestation","attest_author":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4/action/author_attestation","sign_citation":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4/action/citation_signature","submit_replication":"https://pith.science/pith/EBR4DY2QNNSOWUELQUSQR4TNK4/action/replication_record"}},"created_at":"2026-07-05T11:18:16.369602+00:00","updated_at":"2026-07-05T11:18:16.369602+00:00"}