{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:222YHV4ODBFWG7BGK6LKVNFTPQ","short_pith_number":"pith:222YHV4O","schema_version":"1.0","canonical_sha256":"d6b583d78e184b637c265796aab4b37c0679e62cb5f491892c95598784a95060","source":{"kind":"arxiv","id":"2606.29832","version":1},"attestation_state":"computed","paper":{"title":"The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lingjie Duan, Qian Zhang, Yiting Hu","submitted_at":"2026-06-29T06:18:51Z","abstract_excerpt":"Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy. However, this presents a significant challenge in the context of continual learning (CL), where models update sequentially on dynamic datasets. A major limitation is that current certified unlearning algorithms fail to account for the complex, cumulative model evolution inherent to CL framework. In this work, we establish the first theoretical foundation bridging CL and machine unlearning. We formulate the CL's unlearning objective as the minimization of post-unlearning excess risk, wh"},"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":"2606.29832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-29T06:18:51Z","cross_cats_sorted":[],"title_canon_sha256":"36f371bc29a8031d45358b7c67b889cd4506ee0288d746f439bef4d62ac04afc","abstract_canon_sha256":"dd4f2e4fc1743ee9ac2bba3ee2181798edac9d6b4ba5cb495cd3a74f18470a08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:37.290764Z","signature_b64":"8jVLu7J/1fPEmVxN92MVV/QlKBVAYyxy6AkZH71jGEwknONju0brgv7G2DSib/tLYYI+ot7uvaOWX0KFSiATBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6b583d78e184b637c265796aab4b37c0679e62cb5f491892c95598784a95060","last_reissued_at":"2026-06-30T02:17:37.290168Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:37.290168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lingjie Duan, Qian Zhang, Yiting Hu","submitted_at":"2026-06-29T06:18:51Z","abstract_excerpt":"Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy. However, this presents a significant challenge in the context of continual learning (CL), where models update sequentially on dynamic datasets. A major limitation is that current certified unlearning algorithms fail to account for the complex, cumulative model evolution inherent to CL framework. In this work, we establish the first theoretical foundation bridging CL and machine unlearning. We formulate the CL's unlearning objective as the minimization of post-unlearning excess risk, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29832","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/2606.29832/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":"2606.29832","created_at":"2026-06-30T02:17:37.290246+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29832v1","created_at":"2026-06-30T02:17:37.290246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29832","created_at":"2026-06-30T02:17:37.290246+00:00"},{"alias_kind":"pith_short_12","alias_value":"222YHV4ODBFW","created_at":"2026-06-30T02:17:37.290246+00:00"},{"alias_kind":"pith_short_16","alias_value":"222YHV4ODBFWG7BG","created_at":"2026-06-30T02:17:37.290246+00:00"},{"alias_kind":"pith_short_8","alias_value":"222YHV4O","created_at":"2026-06-30T02:17:37.290246+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/222YHV4ODBFWG7BGK6LKVNFTPQ","json":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ.json","graph_json":"https://pith.science/api/pith-number/222YHV4ODBFWG7BGK6LKVNFTPQ/graph.json","events_json":"https://pith.science/api/pith-number/222YHV4ODBFWG7BGK6LKVNFTPQ/events.json","paper":"https://pith.science/paper/222YHV4O"},"agent_actions":{"view_html":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ","download_json":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ.json","view_paper":"https://pith.science/paper/222YHV4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29832&json=true","fetch_graph":"https://pith.science/api/pith-number/222YHV4ODBFWG7BGK6LKVNFTPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/222YHV4ODBFWG7BGK6LKVNFTPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ/action/storage_attestation","attest_author":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ/action/author_attestation","sign_citation":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ/action/citation_signature","submit_replication":"https://pith.science/pith/222YHV4ODBFWG7BGK6LKVNFTPQ/action/replication_record"}},"created_at":"2026-06-30T02:17:37.290246+00:00","updated_at":"2026-06-30T02:17:37.290246+00:00"}