{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EWLUCEFHAT5MZCUC5TG45UGE7B","short_pith_number":"pith:EWLUCEFH","schema_version":"1.0","canonical_sha256":"25974110a704facc8a82eccdced0c4f863d690fbf6d70908d574a86a7829bee9","source":{"kind":"arxiv","id":"2403.18886","version":3},"attestation_state":"computed","paper":{"title":"Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Gong, Haodong Lu, Huiyi Wang, Lina Yao","submitted_at":"2024-03-27T17:59:21Z","abstract_excerpt":"Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable representation in pre-trained models (PTMs), PTM-based CL methods perform effective continual adaptation on downstream tasks by adding learnable adapters or prompts upon the frozen PTMs. However, many existing PTM-based CL methods use restricted adaptation on a fixed set of these modules to avoid forgetting, suffering from limited CL ability. Periodically addi"},"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":"2403.18886","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-27T17:59:21Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5ddae6ec92a4a784137eeb67dfa95e805931fb8e0aaebdf0f935e77896d661c6","abstract_canon_sha256":"07ac1e969e563c631da9ec8438f0f72e6c4134630c562cf21b2a05cbc7e7e223"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:40:00.480742Z","signature_b64":"raxXPE5lK5lYgrk/q0jU/9KQDU47S2ghu3bLvk2SesxKzk/KX0FLexlss9FLlhvbDKxDDMdEwXRPYP/FrSuFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25974110a704facc8a82eccdced0c4f863d690fbf6d70908d574a86a7829bee9","last_reissued_at":"2026-07-05T10:40:00.480241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:40:00.480241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Expansion of Pre-trained Models with Mixture of Adapters for Continual Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Dong Gong, Haodong Lu, Huiyi Wang, Lina Yao","submitted_at":"2024-03-27T17:59:21Z","abstract_excerpt":"Continual learning (CL) aims to continually accumulate knowledge from a non-stationary data stream without catastrophic forgetting of learned knowledge, requiring a balance between stability and adaptability. Relying on the generalizable representation in pre-trained models (PTMs), PTM-based CL methods perform effective continual adaptation on downstream tasks by adding learnable adapters or prompts upon the frozen PTMs. However, many existing PTM-based CL methods use restricted adaptation on a fixed set of these modules to avoid forgetting, suffering from limited CL ability. Periodically addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18886","kind":"arxiv","version":3},"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/2403.18886/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":"2403.18886","created_at":"2026-07-05T10:40:00.480297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18886v3","created_at":"2026-07-05T10:40:00.480297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18886","created_at":"2026-07-05T10:40:00.480297+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWLUCEFHAT5M","created_at":"2026-07-05T10:40:00.480297+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWLUCEFHAT5MZCUC","created_at":"2026-07-05T10:40:00.480297+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWLUCEFH","created_at":"2026-07-05T10:40:00.480297+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21035","citing_title":"Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18187","citing_title":"BRAIN: Bias-Mitigation Continual Learning Approach to Vision-Brain Understanding","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01831","citing_title":"Routing-Based Continual Learning for Multimodal Large Language Models","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2601.03938","citing_title":"FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B","json":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B.json","graph_json":"https://pith.science/api/pith-number/EWLUCEFHAT5MZCUC5TG45UGE7B/graph.json","events_json":"https://pith.science/api/pith-number/EWLUCEFHAT5MZCUC5TG45UGE7B/events.json","paper":"https://pith.science/paper/EWLUCEFH"},"agent_actions":{"view_html":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B","download_json":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B.json","view_paper":"https://pith.science/paper/EWLUCEFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18886&json=true","fetch_graph":"https://pith.science/api/pith-number/EWLUCEFHAT5MZCUC5TG45UGE7B/graph.json","fetch_events":"https://pith.science/api/pith-number/EWLUCEFHAT5MZCUC5TG45UGE7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B/action/storage_attestation","attest_author":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B/action/author_attestation","sign_citation":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B/action/citation_signature","submit_replication":"https://pith.science/pith/EWLUCEFHAT5MZCUC5TG45UGE7B/action/replication_record"}},"created_at":"2026-07-05T10:40:00.480297+00:00","updated_at":"2026-07-05T10:40:00.480297+00:00"}