{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCAKGBSW5DIQJHYIA3BKWGZ5HW","short_pith_number":"pith:WCAKGBSW","schema_version":"1.0","canonical_sha256":"b080a30656e8d1049f0806c2ab1b3d3dab0b6a823b8610dcf573af86a1bd5c82","source":{"kind":"arxiv","id":"2407.14143","version":1},"attestation_state":"computed","paper":{"title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haori Lu, Linlan Huang, Xialei Liu, Xusheng Cao","submitted_at":"2024-07-19T09:20:33Z","abstract_excerpt":"Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they demonstrate good generalization ability that allows them to excel in class-incremental learning with completely frozen parameters. However, further adaptation to downstream tasks by simply fine-tuning the model leads to severe forgetting. Most existing works with pre-trained models assume that the forgetting of old classes is uniform when the model acquires new"},"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":"2407.14143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T09:20:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"800847d299b197883c554d115a5fb8856f5651b1734c4d6d2f2e4b19a3500bd5","abstract_canon_sha256":"8a35fec673b857d7807e3b471745f62118cb79d4246fac9e8a32ec6f84c2f882"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:59.051561Z","signature_b64":"Muv4MgKQHV375Ea/8MjeB/ulfCk/ic4qo+lbdwK76Vgd+PL7d8ZjCIxjeU+6f+ehdVNCyasK1/IC2d6PE1+dDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b080a30656e8d1049f0806c2ab1b3d3dab0b6a823b8610dcf573af86a1bd5c82","last_reissued_at":"2026-07-05T08:45:59.051120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:59.051120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Haori Lu, Linlan Huang, Xialei Liu, Xusheng Cao","submitted_at":"2024-07-19T09:20:33Z","abstract_excerpt":"Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they demonstrate good generalization ability that allows them to excel in class-incremental learning with completely frozen parameters. However, further adaptation to downstream tasks by simply fine-tuning the model leads to severe forgetting. Most existing works with pre-trained models assume that the forgetting of old classes is uniform when the model acquires new"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14143","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/2407.14143/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":"2407.14143","created_at":"2026-07-05T08:45:59.051178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14143v1","created_at":"2026-07-05T08:45:59.051178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14143","created_at":"2026-07-05T08:45:59.051178+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCAKGBSW5DIQ","created_at":"2026-07-05T08:45:59.051178+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCAKGBSW5DIQJHYI","created_at":"2026-07-05T08:45:59.051178+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCAKGBSW","created_at":"2026-07-05T08:45:59.051178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09471","citing_title":"CKAA: Cross-subspace Knowledge Alignment and Aggregation for Robust Continual Learning","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW","json":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW.json","graph_json":"https://pith.science/api/pith-number/WCAKGBSW5DIQJHYIA3BKWGZ5HW/graph.json","events_json":"https://pith.science/api/pith-number/WCAKGBSW5DIQJHYIA3BKWGZ5HW/events.json","paper":"https://pith.science/paper/WCAKGBSW"},"agent_actions":{"view_html":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW","download_json":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW.json","view_paper":"https://pith.science/paper/WCAKGBSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14143&json=true","fetch_graph":"https://pith.science/api/pith-number/WCAKGBSW5DIQJHYIA3BKWGZ5HW/graph.json","fetch_events":"https://pith.science/api/pith-number/WCAKGBSW5DIQJHYIA3BKWGZ5HW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW/action/storage_attestation","attest_author":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW/action/author_attestation","sign_citation":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW/action/citation_signature","submit_replication":"https://pith.science/pith/WCAKGBSW5DIQJHYIA3BKWGZ5HW/action/replication_record"}},"created_at":"2026-07-05T08:45:59.051178+00:00","updated_at":"2026-07-05T08:45:59.051178+00:00"}