{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCRA3U7KM2BZ7ZZNZTGGRXQPH7","short_pith_number":"pith:FCRA3U7K","schema_version":"1.0","canonical_sha256":"28a20dd3ea66839fe72dcccc68de0f3fc3a69f95f76d63a6b765007db2b21264","source":{"kind":"arxiv","id":"2507.09786","version":3},"attestation_state":"computed","paper":{"title":"Leveraging Distribution Matching to Make Approximate Machine Unlearning Faster","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junaid Iqbal Khan","submitted_at":"2025-07-13T20:57:31Z","abstract_excerpt":"Approximate machine unlearning (AMU) enables models to `forget' specific training data through specialized fine-tuning on a retained (and forget) subset of training set. However, processing this large retained subset still dominates computational runtime, while reductions of unlearning epochs also remain a challenge. In this paper, we propose two complementary methods to accelerate arbitrary classification-oriented AMU method. First, \\textbf{Blend}, a novel distribution-matching dataset condensation (DC), merges visually similar images with shared blend-weights to significantly reduce the reta"},"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":"2507.09786","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-13T20:57:31Z","cross_cats_sorted":[],"title_canon_sha256":"ba0f4dc0c3dcf839ee12bcdca86d63bf06d63ef238874afcfb4640cc35699e92","abstract_canon_sha256":"73553141011c1939a6b7c1cce59610651f05980e57f763ce9932312638ff6ba9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:27.192516Z","signature_b64":"NFQuFjF8U66YnstdrQ0xmyQynF7/atkuXFZBoCRxrixovL9SXtTPaPiXR3YK+BjgUsat3iNb11OcOaxPSHQOAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28a20dd3ea66839fe72dcccc68de0f3fc3a69f95f76d63a6b765007db2b21264","last_reissued_at":"2026-07-05T11:48:27.192033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:27.192033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Distribution Matching to Make Approximate Machine Unlearning Faster","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junaid Iqbal Khan","submitted_at":"2025-07-13T20:57:31Z","abstract_excerpt":"Approximate machine unlearning (AMU) enables models to `forget' specific training data through specialized fine-tuning on a retained (and forget) subset of training set. However, processing this large retained subset still dominates computational runtime, while reductions of unlearning epochs also remain a challenge. In this paper, we propose two complementary methods to accelerate arbitrary classification-oriented AMU method. First, \\textbf{Blend}, a novel distribution-matching dataset condensation (DC), merges visually similar images with shared blend-weights to significantly reduce the reta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09786","kind":"arxiv","version":3},"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/2507.09786/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":"2507.09786","created_at":"2026-07-05T11:48:27.192089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.09786v3","created_at":"2026-07-05T11:48:27.192089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09786","created_at":"2026-07-05T11:48:27.192089+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCRA3U7KM2BZ","created_at":"2026-07-05T11:48:27.192089+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCRA3U7KM2BZ7ZZN","created_at":"2026-07-05T11:48:27.192089+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCRA3U7K","created_at":"2026-07-05T11:48:27.192089+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/FCRA3U7KM2BZ7ZZNZTGGRXQPH7","json":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7.json","graph_json":"https://pith.science/api/pith-number/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/graph.json","events_json":"https://pith.science/api/pith-number/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/events.json","paper":"https://pith.science/paper/FCRA3U7K"},"agent_actions":{"view_html":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7","download_json":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7.json","view_paper":"https://pith.science/paper/FCRA3U7K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.09786&json=true","fetch_graph":"https://pith.science/api/pith-number/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/graph.json","fetch_events":"https://pith.science/api/pith-number/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/action/storage_attestation","attest_author":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/action/author_attestation","sign_citation":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/action/citation_signature","submit_replication":"https://pith.science/pith/FCRA3U7KM2BZ7ZZNZTGGRXQPH7/action/replication_record"}},"created_at":"2026-07-05T11:48:27.192089+00:00","updated_at":"2026-07-05T11:48:27.192089+00:00"}