{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LKB2VW7FERBJXFJRV6O7REZ7PF","short_pith_number":"pith:LKB2VW7F","schema_version":"1.0","canonical_sha256":"5a83aadbe524429b9531af9df8933f794fd03d10de7fcc8167d1dc873acb2c93","source":{"kind":"arxiv","id":"2312.02052","version":2},"attestation_state":"computed","paper":{"title":"DUCK: Distance-based Unlearning via Centroid Kinematics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Nicolosi, Francesco Pelosin, Jacopo Bonato, Luigi Sabetta, Marco Cotogni","submitted_at":"2023-12-04T17:10:25Z","abstract_excerpt":"Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models. This technique primarily aims to eradicate any residual influence of a specific subset of data from the knowledge acquired by a neural model during its training. This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK), which employs metric learning to guide the removal of samples matching the nearest incorrect centroid in the embedding space. Evaluation of the algorithm's performance is conduct"},"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":"2312.02052","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-04T17:10:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2d7fd0feb6e12310cf1cf6f4e6fa89425131ab3a4e8327a347050970f8b6fb96","abstract_canon_sha256":"dffcc96ad8b23d468eda1e869a5bbaac314b0fbdcc1a392e4daf1fdfd28d7def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:42.605407Z","signature_b64":"5fnJ24ZEX5bl6karK1Iv3CuD5ExJpO9POhx+SqDAOYyjbSPnYL3OgrBhTtQLJUTaOQr9wORe5J6CNiPdh8QaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a83aadbe524429b9531af9df8933f794fd03d10de7fcc8167d1dc873acb2c93","last_reissued_at":"2026-07-05T08:15:42.604853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:42.604853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DUCK: Distance-based Unlearning via Centroid Kinematics","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alessandro Nicolosi, Francesco Pelosin, Jacopo Bonato, Luigi Sabetta, Marco Cotogni","submitted_at":"2023-12-04T17:10:25Z","abstract_excerpt":"Machine Unlearning is rising as a new field, driven by the pressing necessity of ensuring privacy in modern artificial intelligence models. This technique primarily aims to eradicate any residual influence of a specific subset of data from the knowledge acquired by a neural model during its training. This work introduces a novel unlearning algorithm, denoted as Distance-based Unlearning via Centroid Kinematics (DUCK), which employs metric learning to guide the removal of samples matching the nearest incorrect centroid in the embedding space. Evaluation of the algorithm's performance is conduct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02052","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/2312.02052/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":"2312.02052","created_at":"2026-07-05T08:15:42.604918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.02052v2","created_at":"2026-07-05T08:15:42.604918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02052","created_at":"2026-07-05T08:15:42.604918+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKB2VW7FERBJ","created_at":"2026-07-05T08:15:42.604918+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKB2VW7FERBJXFJR","created_at":"2026-07-05T08:15:42.604918+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKB2VW7F","created_at":"2026-07-05T08:15:42.604918+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25001","citing_title":"Erased, but Not Gone: Output Forgetting Is Not True Forgetting","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19339","citing_title":"POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04030","citing_title":"Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF","json":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF.json","graph_json":"https://pith.science/api/pith-number/LKB2VW7FERBJXFJRV6O7REZ7PF/graph.json","events_json":"https://pith.science/api/pith-number/LKB2VW7FERBJXFJRV6O7REZ7PF/events.json","paper":"https://pith.science/paper/LKB2VW7F"},"agent_actions":{"view_html":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF","download_json":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF.json","view_paper":"https://pith.science/paper/LKB2VW7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.02052&json=true","fetch_graph":"https://pith.science/api/pith-number/LKB2VW7FERBJXFJRV6O7REZ7PF/graph.json","fetch_events":"https://pith.science/api/pith-number/LKB2VW7FERBJXFJRV6O7REZ7PF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF/action/storage_attestation","attest_author":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF/action/author_attestation","sign_citation":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF/action/citation_signature","submit_replication":"https://pith.science/pith/LKB2VW7FERBJXFJRV6O7REZ7PF/action/replication_record"}},"created_at":"2026-07-05T08:15:42.604918+00:00","updated_at":"2026-07-05T08:15:42.604918+00:00"}