{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DDYBGZIQOZENCRKSSUF3AGLO4P","short_pith_number":"pith:DDYBGZIQ","schema_version":"1.0","canonical_sha256":"18f01365107648d14552950bb0196ee3df535294b96162d4538683fd656145d0","source":{"kind":"arxiv","id":"2304.04934","version":13},"attestation_state":"computed","paper":{"title":"Model Sparsity Can Simplify Machine Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaowen Liu, Jiancheng Liu, Jinghan Jia, Parikshit Ram, Pranay Sharma, Sijia Liu, Yang Liu, Yuguang Yao","submitted_at":"2023-04-11T02:12:02Z","abstract_excerpt":"In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process to remove the influence of specific examples from a given model. Although exact unlearning can be achieved through complete model retraining using the remaining dataset, the associated computational costs have driven the development of efficient, approximate unlearning techniques. Moving beyond data-centric MU approaches, our study introduces a novel model-based perspective: model sparsification via weight pruning, which is capable of reducing the gap between exact unlearning and appro"},"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":"2304.04934","kind":"arxiv","version":13},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T02:12:02Z","cross_cats_sorted":[],"title_canon_sha256":"d78f6ae59044050588d886a06aed97978934dee371400e985830b05394fad612","abstract_canon_sha256":"65e5dd7981de78ae6451106e25d23660b6ce440de63db20b1f45354c340b292c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:08.431043Z","signature_b64":"EW4AaaVPsVB7UXWKxxbrD1TTgc0FWRSBjdz+F7OdLBFGTe4gLgjLNte2Lu4ibaPADkPGjcdX0upCUs7Bn9QbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18f01365107648d14552950bb0196ee3df535294b96162d4538683fd656145d0","last_reissued_at":"2026-07-05T07:38:08.430570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:08.430570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model Sparsity Can Simplify Machine Unlearning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaowen Liu, Jiancheng Liu, Jinghan Jia, Parikshit Ram, Pranay Sharma, Sijia Liu, Yang Liu, Yuguang Yao","submitted_at":"2023-04-11T02:12:02Z","abstract_excerpt":"In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process to remove the influence of specific examples from a given model. Although exact unlearning can be achieved through complete model retraining using the remaining dataset, the associated computational costs have driven the development of efficient, approximate unlearning techniques. Moving beyond data-centric MU approaches, our study introduces a novel model-based perspective: model sparsification via weight pruning, which is capable of reducing the gap between exact unlearning and appro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04934","kind":"arxiv","version":13},"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/2304.04934/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":"2304.04934","created_at":"2026-07-05T07:38:08.430625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04934v13","created_at":"2026-07-05T07:38:08.430625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04934","created_at":"2026-07-05T07:38:08.430625+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDYBGZIQOZEN","created_at":"2026-07-05T07:38:08.430625+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDYBGZIQOZENCRKS","created_at":"2026-07-05T07:38:08.430625+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDYBGZIQ","created_at":"2026-07-05T07:38:08.430625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00399","citing_title":"Multi-Objective Reference-Aligned Machine Unlearning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04800","citing_title":"Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P","json":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P.json","graph_json":"https://pith.science/api/pith-number/DDYBGZIQOZENCRKSSUF3AGLO4P/graph.json","events_json":"https://pith.science/api/pith-number/DDYBGZIQOZENCRKSSUF3AGLO4P/events.json","paper":"https://pith.science/paper/DDYBGZIQ"},"agent_actions":{"view_html":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P","download_json":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P.json","view_paper":"https://pith.science/paper/DDYBGZIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04934&json=true","fetch_graph":"https://pith.science/api/pith-number/DDYBGZIQOZENCRKSSUF3AGLO4P/graph.json","fetch_events":"https://pith.science/api/pith-number/DDYBGZIQOZENCRKSSUF3AGLO4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P/action/storage_attestation","attest_author":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P/action/author_attestation","sign_citation":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P/action/citation_signature","submit_replication":"https://pith.science/pith/DDYBGZIQOZENCRKSSUF3AGLO4P/action/replication_record"}},"created_at":"2026-07-05T07:38:08.430625+00:00","updated_at":"2026-07-05T07:38:08.430625+00:00"}