{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XTJORBCJLK537PFU4HCWNPYTST","short_pith_number":"pith:XTJORBCJ","schema_version":"1.0","canonical_sha256":"bcd2e884495abbbfbcb4e1c566bf1394c7024fa8d6e3184fdb6c3685bee342b2","source":{"kind":"arxiv","id":"2305.19270","version":2},"attestation_state":"computed","paper":{"title":"Learning without Forgetting for Vision-Language Models","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, Jingyi Ning, Yan Wang, Yuanhan Zhang, Ziwei Liu","submitted_at":"2023-05-30T17:59:32Z","abstract_excerpt":"Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual information to grasp core features, recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations with the aid of textual information. However, when continually trained with new classes, VLMs often suffer from catastrophic forgetting of former knowledge. Applying VLMs to CIL poses two major challenges: 1) "},"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":"2305.19270","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-30T17:59:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"244e04797b83ed351ec9f8a7498447083e5ad63ea7bb913d06d2c277ca8bfb08","abstract_canon_sha256":"da2ae2a6d290189a262db4af7125ade3713a345018d10523b0f9254abe32860c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:55.757563Z","signature_b64":"wZNTpEA9jkzYxZE0oOi3Pmsc+dek28RC5rH59rFdBal6uqRaUcEV6lMI8x51IttQdlAXwiJSc0nBqFOlNMknCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcd2e884495abbbfbcb4e1c566bf1394c7024fa8d6e3184fdb6c3685bee342b2","last_reissued_at":"2026-07-05T10:12:55.757124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:55.757124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning without Forgetting for Vision-Language Models","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, Jingyi Ning, Yan Wang, Yuanhan Zhang, Ziwei Liu","submitted_at":"2023-05-30T17:59:32Z","abstract_excerpt":"Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual information to grasp core features, recent advances in Vision-Language Models (VLM) have shown promising capabilities in learning generalizable representations with the aid of textual information. However, when continually trained with new classes, VLMs often suffer from catastrophic forgetting of former knowledge. Applying VLMs to CIL poses two major challenges: 1) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19270","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/2305.19270/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":"2305.19270","created_at":"2026-07-05T10:12:55.757185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19270v2","created_at":"2026-07-05T10:12:55.757185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19270","created_at":"2026-07-05T10:12:55.757185+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTJORBCJLK53","created_at":"2026-07-05T10:12:55.757185+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTJORBCJLK537PFU","created_at":"2026-07-05T10:12:55.757185+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTJORBCJ","created_at":"2026-07-05T10:12:55.757185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11064","citing_title":"A Faster Path to Continual Learning","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST","json":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST.json","graph_json":"https://pith.science/api/pith-number/XTJORBCJLK537PFU4HCWNPYTST/graph.json","events_json":"https://pith.science/api/pith-number/XTJORBCJLK537PFU4HCWNPYTST/events.json","paper":"https://pith.science/paper/XTJORBCJ"},"agent_actions":{"view_html":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST","download_json":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST.json","view_paper":"https://pith.science/paper/XTJORBCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19270&json=true","fetch_graph":"https://pith.science/api/pith-number/XTJORBCJLK537PFU4HCWNPYTST/graph.json","fetch_events":"https://pith.science/api/pith-number/XTJORBCJLK537PFU4HCWNPYTST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST/action/storage_attestation","attest_author":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST/action/author_attestation","sign_citation":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST/action/citation_signature","submit_replication":"https://pith.science/pith/XTJORBCJLK537PFU4HCWNPYTST/action/replication_record"}},"created_at":"2026-07-05T10:12:55.757185+00:00","updated_at":"2026-07-05T10:12:55.757185+00:00"}