{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZWDEFXBKQRTPCOAKVJGIBVGTI","short_pith_number":"pith:SZWDEFXB","schema_version":"1.0","canonical_sha256":"966c3216e154233789c055526406a69a20a13959bd9a19d66d0bf463b7a1815b","source":{"kind":"arxiv","id":"2502.10288","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Mixup Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yixuan Tang, Yi Yang, Zhuoyi Peng","submitted_at":"2025-02-14T16:50:33Z","abstract_excerpt":"Machine unlearning is a critical area of research aimed at safeguarding data privacy by enabling the removal of sensitive information from machine learning models. One unique challenge in this field is catastrophic unlearning, where erasing specific data from a well-trained model unintentionally removes essential knowledge, causing the model to deviate significantly from a retrained one. To address this, we introduce a novel approach that regularizes the unlearning process by utilizing synthesized mixup samples, which simulate the data susceptible to catastrophic effects. At the core of our ap"},"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":"2502.10288","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-14T16:50:33Z","cross_cats_sorted":[],"title_canon_sha256":"ca7e68fc91481d8a6b99a3c88908cf6572cc41c467e1fb40dda6dfdf0c147402","abstract_canon_sha256":"ea6741b692bbe813433e35a8bb83bfe5324dcd8999cbc48aadb1afccd6fedca0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:31.165676Z","signature_b64":"0Cycr2EUrcSEbMo+SJl1QjszifCJB1svpBFsgM+W+jvbbfVyXmIqv257jmBPMQjYUv65OnF9CBl6dTj8dpJXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"966c3216e154233789c055526406a69a20a13959bd9a19d66d0bf463b7a1815b","last_reissued_at":"2026-07-05T10:14:31.165143Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:31.165143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Mixup Unlearning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yixuan Tang, Yi Yang, Zhuoyi Peng","submitted_at":"2025-02-14T16:50:33Z","abstract_excerpt":"Machine unlearning is a critical area of research aimed at safeguarding data privacy by enabling the removal of sensitive information from machine learning models. One unique challenge in this field is catastrophic unlearning, where erasing specific data from a well-trained model unintentionally removes essential knowledge, causing the model to deviate significantly from a retrained one. To address this, we introduce a novel approach that regularizes the unlearning process by utilizing synthesized mixup samples, which simulate the data susceptible to catastrophic effects. At the core of our ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10288","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/2502.10288/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":"2502.10288","created_at":"2026-07-05T10:14:31.165206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10288v1","created_at":"2026-07-05T10:14:31.165206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10288","created_at":"2026-07-05T10:14:31.165206+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZWDEFXBKQRT","created_at":"2026-07-05T10:14:31.165206+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZWDEFXBKQRTPCOA","created_at":"2026-07-05T10:14:31.165206+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZWDEFXB","created_at":"2026-07-05T10:14:31.165206+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/SZWDEFXBKQRTPCOAKVJGIBVGTI","json":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI.json","graph_json":"https://pith.science/api/pith-number/SZWDEFXBKQRTPCOAKVJGIBVGTI/graph.json","events_json":"https://pith.science/api/pith-number/SZWDEFXBKQRTPCOAKVJGIBVGTI/events.json","paper":"https://pith.science/paper/SZWDEFXB"},"agent_actions":{"view_html":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI","download_json":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI.json","view_paper":"https://pith.science/paper/SZWDEFXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10288&json=true","fetch_graph":"https://pith.science/api/pith-number/SZWDEFXBKQRTPCOAKVJGIBVGTI/graph.json","fetch_events":"https://pith.science/api/pith-number/SZWDEFXBKQRTPCOAKVJGIBVGTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI/action/storage_attestation","attest_author":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI/action/author_attestation","sign_citation":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI/action/citation_signature","submit_replication":"https://pith.science/pith/SZWDEFXBKQRTPCOAKVJGIBVGTI/action/replication_record"}},"created_at":"2026-07-05T10:14:31.165206+00:00","updated_at":"2026-07-05T10:14:31.165206+00:00"}