{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6R6464WU5R6PVPDUBOB5UE6GJC","short_pith_number":"pith:6R6464WU","schema_version":"1.0","canonical_sha256":"f47dcf72d4ec7cfabc740b83da13c648a1f33e7a2ed5f6ebcdca8ab8c246c35e","source":{"kind":"arxiv","id":"2405.18663","version":1},"attestation_state":"computed","paper":{"title":"Lifelong Learning and Selective Forgetting via Contrastive Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lianlei Shan, Wei Li, Wenzhang Zhou, Xingyu Ding","submitted_at":"2024-05-28T23:57:48Z","abstract_excerpt":"Lifelong learning aims to train a model with good performance for new tasks while retaining the capacity of previous tasks. However, some practical scenarios require the system to forget undesirable knowledge due to privacy issues, which is called selective forgetting. The joint task of the two is dubbed Learning with Selective Forgetting (LSF). In this paper, we propose a new framework based on contrastive strategy for LSF. Specifically, for the preserved classes (tasks), we make features extracted from different samples within a same class compacted. And for the deleted classes, we make the "},"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":"2405.18663","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T23:57:48Z","cross_cats_sorted":[],"title_canon_sha256":"73e04270b0580381c28bf535cc658e2fd767f3aaeeac7da70c59c5a7a080fc66","abstract_canon_sha256":"f459784f430342060ca198640aa930249c012e62933294af851f41a896f49acb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:28.663831Z","signature_b64":"i+4PGpvEbnkDKXjPHGFXNV9dF2kJOGHfUABgd0DabF3kWiMXX1pEaZXwdtr2ruq8Uqy70o4psVjzhkjdL6SaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f47dcf72d4ec7cfabc740b83da13c648a1f33e7a2ed5f6ebcdca8ab8c246c35e","last_reissued_at":"2026-07-05T08:24:28.663371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:28.663371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lifelong Learning and Selective Forgetting via Contrastive Strategy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lianlei Shan, Wei Li, Wenzhang Zhou, Xingyu Ding","submitted_at":"2024-05-28T23:57:48Z","abstract_excerpt":"Lifelong learning aims to train a model with good performance for new tasks while retaining the capacity of previous tasks. However, some practical scenarios require the system to forget undesirable knowledge due to privacy issues, which is called selective forgetting. The joint task of the two is dubbed Learning with Selective Forgetting (LSF). In this paper, we propose a new framework based on contrastive strategy for LSF. Specifically, for the preserved classes (tasks), we make features extracted from different samples within a same class compacted. And for the deleted classes, we make the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18663","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/2405.18663/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":"2405.18663","created_at":"2026-07-05T08:24:28.663437+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18663v1","created_at":"2026-07-05T08:24:28.663437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18663","created_at":"2026-07-05T08:24:28.663437+00:00"},{"alias_kind":"pith_short_12","alias_value":"6R6464WU5R6P","created_at":"2026-07-05T08:24:28.663437+00:00"},{"alias_kind":"pith_short_16","alias_value":"6R6464WU5R6PVPDU","created_at":"2026-07-05T08:24:28.663437+00:00"},{"alias_kind":"pith_short_8","alias_value":"6R6464WU","created_at":"2026-07-05T08:24:28.663437+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00363","citing_title":"GDGS: 3D Gaussian Splatting Via Geometry-Guided Initialization And Dynamic Density Control","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC","json":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC.json","graph_json":"https://pith.science/api/pith-number/6R6464WU5R6PVPDUBOB5UE6GJC/graph.json","events_json":"https://pith.science/api/pith-number/6R6464WU5R6PVPDUBOB5UE6GJC/events.json","paper":"https://pith.science/paper/6R6464WU"},"agent_actions":{"view_html":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC","download_json":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC.json","view_paper":"https://pith.science/paper/6R6464WU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18663&json=true","fetch_graph":"https://pith.science/api/pith-number/6R6464WU5R6PVPDUBOB5UE6GJC/graph.json","fetch_events":"https://pith.science/api/pith-number/6R6464WU5R6PVPDUBOB5UE6GJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC/action/storage_attestation","attest_author":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC/action/author_attestation","sign_citation":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC/action/citation_signature","submit_replication":"https://pith.science/pith/6R6464WU5R6PVPDUBOB5UE6GJC/action/replication_record"}},"created_at":"2026-07-05T08:24:28.663437+00:00","updated_at":"2026-07-05T08:24:28.663437+00:00"}