{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EE3I6YWWGQL2BIA4DI3B2RSZEA","short_pith_number":"pith:EE3I6YWW","schema_version":"1.0","canonical_sha256":"21368f62d63417a0a01c1a361d4659203d724d2e48abae38379f6b6ca1d3581b","source":{"kind":"arxiv","id":"2210.16023","version":1},"attestation_state":"computed","paper":{"title":"LegoNet: A Fast and Exact Unlearning Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Sun, Jiafeng Guo, Ruqing Zhang, Sihao Yu, Xueqi Cheng","submitted_at":"2022-10-28T09:53:05Z","abstract_excerpt":"Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model. Re-training the model on the retained data after deletion is an effective but not efficient way due to the huge number of model parameters and re-training samples. To speed up, a natural way is to reduce such parameters and samples. However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance. In this paper, we present a novel network, namely \\textit{LegoNet},"},"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":"2210.16023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-28T09:53:05Z","cross_cats_sorted":[],"title_canon_sha256":"21716f25fc0c9f9a8cfe4cc859f46720ed5557338f89e1b99c32002b9580670a","abstract_canon_sha256":"6d3f7ee29b204636d8a40ef4a78fb2346f474152b46b999680577131cd8773e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:29.749211Z","signature_b64":"Ji302rjAXR6F8grESxVtRf1QUhMacG0JEAA5jCflzpFuN7HgNFD4kTBUcc3aff1zhGjvcIQYsCuvn6PNBT8KAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21368f62d63417a0a01c1a361d4659203d724d2e48abae38379f6b6ca1d3581b","last_reissued_at":"2026-07-05T05:11:29.748779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:29.748779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LegoNet: A Fast and Exact Unlearning Architecture","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Sun, Jiafeng Guo, Ruqing Zhang, Sihao Yu, Xueqi Cheng","submitted_at":"2022-10-28T09:53:05Z","abstract_excerpt":"Machine unlearning aims to erase the impact of specific training samples upon deleted requests from a trained model. Re-training the model on the retained data after deletion is an effective but not efficient way due to the huge number of model parameters and re-training samples. To speed up, a natural way is to reduce such parameters and samples. However, such a strategy typically leads to a loss in model performance, which poses the challenge that increasing the unlearning efficiency while maintaining acceptable performance. In this paper, we present a novel network, namely \\textit{LegoNet},"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16023","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/2210.16023/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":"2210.16023","created_at":"2026-07-05T05:11:29.748829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16023v1","created_at":"2026-07-05T05:11:29.748829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16023","created_at":"2026-07-05T05:11:29.748829+00:00"},{"alias_kind":"pith_short_12","alias_value":"EE3I6YWWGQL2","created_at":"2026-07-05T05:11:29.748829+00:00"},{"alias_kind":"pith_short_16","alias_value":"EE3I6YWWGQL2BIA4","created_at":"2026-07-05T05:11:29.748829+00:00"},{"alias_kind":"pith_short_8","alias_value":"EE3I6YWW","created_at":"2026-07-05T05:11:29.748829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17783","citing_title":"Generative Data Augmentation for Object Point Cloud Segmentation","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA","json":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA.json","graph_json":"https://pith.science/api/pith-number/EE3I6YWWGQL2BIA4DI3B2RSZEA/graph.json","events_json":"https://pith.science/api/pith-number/EE3I6YWWGQL2BIA4DI3B2RSZEA/events.json","paper":"https://pith.science/paper/EE3I6YWW"},"agent_actions":{"view_html":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA","download_json":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA.json","view_paper":"https://pith.science/paper/EE3I6YWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16023&json=true","fetch_graph":"https://pith.science/api/pith-number/EE3I6YWWGQL2BIA4DI3B2RSZEA/graph.json","fetch_events":"https://pith.science/api/pith-number/EE3I6YWWGQL2BIA4DI3B2RSZEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA/action/storage_attestation","attest_author":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA/action/author_attestation","sign_citation":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA/action/citation_signature","submit_replication":"https://pith.science/pith/EE3I6YWWGQL2BIA4DI3B2RSZEA/action/replication_record"}},"created_at":"2026-07-05T05:11:29.748829+00:00","updated_at":"2026-07-05T05:11:29.748829+00:00"}