{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FDXJ5VJ4CTO4GSOHD7I6ULXFUE","short_pith_number":"pith:FDXJ5VJ4","schema_version":"1.0","canonical_sha256":"28ee9ed53c14ddc349c71fd1ea2ee5a13a11b4c1db017e888eced9d590d6f9e8","source":{"kind":"arxiv","id":"2401.16386","version":2},"attestation_state":"computed","paper":{"title":"Continual Learning with Pre-Trained Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Da-Wei Zhou, De-Chuan Zhan, Hai-Long Sun, Han-Jia Ye, Jingyi Ning","submitted_at":"2024-01-29T18:27:52Z","abstract_excerpt":"Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former knowledge when learning new ones. Typical CL methods build the model from scratch to grow with incoming data. However, the advent of the pre-trained model (PTM) era has sparked immense research interest, particularly in leveraging PTMs' robust representational capabilities. This paper presents a comprehensive survey of the latest advancements in PTM-"},"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":"2401.16386","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-29T18:27:52Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"900d146919bf3b665f55cc988947032a2e0b9e19696c8b8e38e5cc0eccb6b282","abstract_canon_sha256":"829bb629172c729bd04077952c2f142261054ee6ac613d6dc9442ad2bfa2829b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:00.979861Z","signature_b64":"dnr4HZS5+TZHucsdnzKWxIENuUONEfV1UWQQQy7eHQLXlrSiV1iDlL4ABG+VshdgHG6aNCKWfFiYKHv5g9QAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ee9ed53c14ddc349c71fd1ea2ee5a13a11b4c1db017e888eced9d590d6f9e8","last_reissued_at":"2026-07-05T08:11:00.979299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:00.979299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning with Pre-Trained Models: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Da-Wei Zhou, De-Chuan Zhan, Hai-Long Sun, Han-Jia Ye, Jingyi Ning","submitted_at":"2024-01-29T18:27:52Z","abstract_excerpt":"Nowadays, real-world applications often face streaming data, which requires the learning system to absorb new knowledge as data evolves. Continual Learning (CL) aims to achieve this goal and meanwhile overcome the catastrophic forgetting of former knowledge when learning new ones. Typical CL methods build the model from scratch to grow with incoming data. However, the advent of the pre-trained model (PTM) era has sparked immense research interest, particularly in leveraging PTMs' robust representational capabilities. This paper presents a comprehensive survey of the latest advancements in PTM-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16386","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/2401.16386/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":"2401.16386","created_at":"2026-07-05T08:11:00.979367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16386v2","created_at":"2026-07-05T08:11:00.979367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16386","created_at":"2026-07-05T08:11:00.979367+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDXJ5VJ4CTO4","created_at":"2026-07-05T08:11:00.979367+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDXJ5VJ4CTO4GSOH","created_at":"2026-07-05T08:11:00.979367+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDXJ5VJ4","created_at":"2026-07-05T08:11:00.979367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19635","citing_title":"Token Factory: Efficiently Integrating Diverse Signals into Large Recommendation Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10969","citing_title":"A Functional Data Framework For Analyzing Shapes and Textures in Images","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25708","citing_title":"CMAP: Cross-Modal Adaptive Prompting for Multi-Domain Task-Incremental Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2411.02813","citing_title":"Sparse Orthogonal Parameters Tuning for Continual Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19301","citing_title":"iGSP:Implicit Gradient Subspace Projection for Efficient Continual Learning of Vision-Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21577","citing_title":"Collaborative Parameter Learning: Mitigating Forgetting via Parameter-Level Gradient Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11904","citing_title":"Beyond Point-wise Neural Collapse: A Topology-Aware Hierarchical Classifier for Class-Incremental Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05776","citing_title":"HEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11064","citing_title":"A Faster Path to Continual Learning","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE","json":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE.json","graph_json":"https://pith.science/api/pith-number/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/graph.json","events_json":"https://pith.science/api/pith-number/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/events.json","paper":"https://pith.science/paper/FDXJ5VJ4"},"agent_actions":{"view_html":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE","download_json":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE.json","view_paper":"https://pith.science/paper/FDXJ5VJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16386&json=true","fetch_graph":"https://pith.science/api/pith-number/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/graph.json","fetch_events":"https://pith.science/api/pith-number/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/action/storage_attestation","attest_author":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/action/author_attestation","sign_citation":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/action/citation_signature","submit_replication":"https://pith.science/pith/FDXJ5VJ4CTO4GSOHD7I6ULXFUE/action/replication_record"}},"created_at":"2026-07-05T08:11:00.979367+00:00","updated_at":"2026-07-05T08:11:00.979367+00:00"}