{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TLG4ZJGR3EPAHWVWJBF3ZUV6TX","short_pith_number":"pith:TLG4ZJGR","schema_version":"1.0","canonical_sha256":"9acdcca4d1d91e03dab6484bbcd2be9dfc5d7bbff0e41d3d08910799a33a0a87","source":{"kind":"arxiv","id":"2302.03648","version":2},"attestation_state":"computed","paper":{"title":"Class-Incremental Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da-Wei Zhou, De-Chuan Zhan, Han-Jia Ye, Qi-Wei Wang, Zhi-Hong Qi, Ziwei Liu","submitted_at":"2023-02-07T17:59:05Z","abstract_excerpt":"Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs -- the model tends to catastrophically forget the characterist"},"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":"2302.03648","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-02-07T17:59:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"75f4cd5a3892b49581a259aecc065c92bcefa78ec351bfe6ca18f218612b0233","abstract_canon_sha256":"7d3a66117224ddf7b8e0d56af4df1779c095937399f70ec46f74e04557bbce1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:49.255334Z","signature_b64":"cdgR59ulsO8nag9xLtol1CC+VInpXuaRfXyoBrTmqN9tG4P7lX9GJfQ4FmCvMeiQVc1+BsJut4KiCNfwSkb8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9acdcca4d1d91e03dab6484bbcd2be9dfc5d7bbff0e41d3d08910799a33a0a87","last_reissued_at":"2026-07-05T08:43:49.254872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:49.254872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Incremental Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Da-Wei Zhou, De-Chuan Zhan, Han-Jia Ye, Qi-Wei Wang, Zhi-Hong Qi, Ziwei Liu","submitted_at":"2023-02-07T17:59:05Z","abstract_excerpt":"Deep models, e.g., CNNs and Vision Transformers, have achieved impressive achievements in many vision tasks in the closed world. However, novel classes emerge from time to time in our ever-changing world, requiring a learning system to acquire new knowledge continually. Class-Incremental Learning (CIL) enables the learner to incorporate the knowledge of new classes incrementally and build a universal classifier among all seen classes. Correspondingly, when directly training the model with new class instances, a fatal problem occurs -- the model tends to catastrophically forget the characterist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03648","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/2302.03648/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":"2302.03648","created_at":"2026-07-05T08:43:49.254935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03648v2","created_at":"2026-07-05T08:43:49.254935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03648","created_at":"2026-07-05T08:43:49.254935+00:00"},{"alias_kind":"pith_short_12","alias_value":"TLG4ZJGR3EPA","created_at":"2026-07-05T08:43:49.254935+00:00"},{"alias_kind":"pith_short_16","alias_value":"TLG4ZJGR3EPAHWVW","created_at":"2026-07-05T08:43:49.254935+00:00"},{"alias_kind":"pith_short_8","alias_value":"TLG4ZJGR","created_at":"2026-07-05T08:43:49.254935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.02813","citing_title":"Sparse Orthogonal Parameters Tuning for Continual Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17575","citing_title":"UniAlign: A Model-Agnostic Framework for Robust Network Traffic Classification under Distribution Shifts","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11064","citing_title":"A Faster Path to Continual Learning","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX","json":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX.json","graph_json":"https://pith.science/api/pith-number/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/graph.json","events_json":"https://pith.science/api/pith-number/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/events.json","paper":"https://pith.science/paper/TLG4ZJGR"},"agent_actions":{"view_html":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX","download_json":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX.json","view_paper":"https://pith.science/paper/TLG4ZJGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03648&json=true","fetch_graph":"https://pith.science/api/pith-number/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/graph.json","fetch_events":"https://pith.science/api/pith-number/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/action/storage_attestation","attest_author":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/action/author_attestation","sign_citation":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/action/citation_signature","submit_replication":"https://pith.science/pith/TLG4ZJGR3EPAHWVWJBF3ZUV6TX/action/replication_record"}},"created_at":"2026-07-05T08:43:49.254935+00:00","updated_at":"2026-07-05T08:43:49.254935+00:00"}