{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LBAXKGCBVCWDVQ24I376XSNPPU","short_pith_number":"pith:LBAXKGCB","schema_version":"1.0","canonical_sha256":"5841751841a8ac3ac35c46ffebc9af7d30663b5b0fa923e5eef6bc4da76677f3","source":{"kind":"arxiv","id":"2406.08288","version":2},"attestation_state":"computed","paper":{"title":"Decoupling the Class Label and the Target Concept in Machine Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Jiangchao Yao, Jianing Zhu, Jianliang Xu, Masashi Sugiyama","submitted_at":"2024-06-12T14:53:30Z","abstract_excerpt":"Machine unlearning as an emerging research topic for data regulations, aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class, through gradient ascent on the forgetting data or fine-tuning with the remaining data. However, while these methods are useful, they are insufficient as the class label and the target concept are often considered to coincide. In this work, we decouple them by considering the label domain mismatch and investigate"},"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":"2406.08288","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T14:53:30Z","cross_cats_sorted":[],"title_canon_sha256":"7be2bc647bd517c1b815bcd271609bcaccc802fe304a384bd3cc755e14dbf9b9","abstract_canon_sha256":"b37b405da84c713991b31257ff1e52855a8011331050aab1e79506d2d9d3b5af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:42.769708Z","signature_b64":"/Tos6e12ac1OP0A7oLTk4Yo3OZRzds0Xt2phNL9unytUKZGliO5XXQOfsBWeZREjXVO+lAVRdxO6F5jaa6/OCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5841751841a8ac3ac35c46ffebc9af7d30663b5b0fa923e5eef6bc4da76677f3","last_reissued_at":"2026-07-05T08:32:42.769141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:42.769141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling the Class Label and the Target Concept in Machine Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Jiangchao Yao, Jianing Zhu, Jianliang Xu, Masashi Sugiyama","submitted_at":"2024-06-12T14:53:30Z","abstract_excerpt":"Machine unlearning as an emerging research topic for data regulations, aims to adjust a trained model to approximate a retrained one that excludes a portion of training data. Previous studies showed that class-wise unlearning is successful in forgetting the knowledge of a target class, through gradient ascent on the forgetting data or fine-tuning with the remaining data. However, while these methods are useful, they are insufficient as the class label and the target concept are often considered to coincide. In this work, we decouple them by considering the label domain mismatch and investigate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08288","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/2406.08288/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":"2406.08288","created_at":"2026-07-05T08:32:42.769204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08288v2","created_at":"2026-07-05T08:32:42.769204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08288","created_at":"2026-07-05T08:32:42.769204+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBAXKGCBVCWD","created_at":"2026-07-05T08:32:42.769204+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBAXKGCBVCWDVQ24","created_at":"2026-07-05T08:32:42.769204+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBAXKGCB","created_at":"2026-07-05T08:32:42.769204+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01658","citing_title":"CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15166","citing_title":"Class Unlearning via Depth-Aware Removal of Forget-Specific Directions","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04030","citing_title":"Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15166","citing_title":"Class Unlearning via Depth-Aware Removal of Forget-Specific Directions","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU","json":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU.json","graph_json":"https://pith.science/api/pith-number/LBAXKGCBVCWDVQ24I376XSNPPU/graph.json","events_json":"https://pith.science/api/pith-number/LBAXKGCBVCWDVQ24I376XSNPPU/events.json","paper":"https://pith.science/paper/LBAXKGCB"},"agent_actions":{"view_html":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU","download_json":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU.json","view_paper":"https://pith.science/paper/LBAXKGCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08288&json=true","fetch_graph":"https://pith.science/api/pith-number/LBAXKGCBVCWDVQ24I376XSNPPU/graph.json","fetch_events":"https://pith.science/api/pith-number/LBAXKGCBVCWDVQ24I376XSNPPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU/action/storage_attestation","attest_author":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU/action/author_attestation","sign_citation":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU/action/citation_signature","submit_replication":"https://pith.science/pith/LBAXKGCBVCWDVQ24I376XSNPPU/action/replication_record"}},"created_at":"2026-07-05T08:32:42.769204+00:00","updated_at":"2026-07-05T08:32:42.769204+00:00"}