{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3FYQBQXNLEXTSHDW2Z3EEOPRTU","short_pith_number":"pith:3FYQBQXN","schema_version":"1.0","canonical_sha256":"d97100c2ed592f391c76d6764239f19d12ad8dce4ea40e515ebf9a16e434e614","source":{"kind":"arxiv","id":"2408.13991","version":1},"attestation_state":"computed","paper":{"title":"Dual-CBA: Improving Online Continual Learning via Dual Continual Bias Adaptors from a Bi-level Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deyu Meng, Minghao Zhou, Quanziang Wang, Renzhen Wang, Xixi Jia, Yichen Wu","submitted_at":"2024-08-26T03:19:52Z","abstract_excerpt":"In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level framework that augments the classification network to adapt to catastrophic distribution shifts during training, enabling the network to achieve a stable consolidation of all seen tasks. However, the CBA module adjusts distribution shifts in a class-specific manner, exacerbating the stability gap issue and, to some extent, fails to meet the need for continual testin"},"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":"2408.13991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-26T03:19:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a576b6dcf4cb31e256355c012623e33174f736513b091f9acef7d5fdecab1053","abstract_canon_sha256":"6c5a14f9d4be2a29d33a930a3da66fce94625a28eb0e3b9f47f0493902a765e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:14.578302Z","signature_b64":"VQNjdYY03GqbcWm4gAQTXdTAgRGMMNmcUf+Wf6CFF+Az9dUgrH6APrDiNBkOhi3mn9LhPqgdCNZFU7uIzCDECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d97100c2ed592f391c76d6764239f19d12ad8dce4ea40e515ebf9a16e434e614","last_reissued_at":"2026-07-05T08:59:14.577806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:14.577806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual-CBA: Improving Online Continual Learning via Dual Continual Bias Adaptors from a Bi-level Optimization Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Deyu Meng, Minghao Zhou, Quanziang Wang, Renzhen Wang, Xixi Jia, Yichen Wu","submitted_at":"2024-08-26T03:19:52Z","abstract_excerpt":"In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA), a bi-level framework that augments the classification network to adapt to catastrophic distribution shifts during training, enabling the network to achieve a stable consolidation of all seen tasks. However, the CBA module adjusts distribution shifts in a class-specific manner, exacerbating the stability gap issue and, to some extent, fails to meet the need for continual testin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13991","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/2408.13991/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":"2408.13991","created_at":"2026-07-05T08:59:14.577866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.13991v1","created_at":"2026-07-05T08:59:14.577866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13991","created_at":"2026-07-05T08:59:14.577866+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FYQBQXNLEXT","created_at":"2026-07-05T08:59:14.577866+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FYQBQXNLEXTSHDW","created_at":"2026-07-05T08:59:14.577866+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FYQBQXN","created_at":"2026-07-05T08:59:14.577866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20135","citing_title":"Data-Distill-Net: A Data Distillation Approach Tailored for Reply-based Continual Learning","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU","json":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU.json","graph_json":"https://pith.science/api/pith-number/3FYQBQXNLEXTSHDW2Z3EEOPRTU/graph.json","events_json":"https://pith.science/api/pith-number/3FYQBQXNLEXTSHDW2Z3EEOPRTU/events.json","paper":"https://pith.science/paper/3FYQBQXN"},"agent_actions":{"view_html":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU","download_json":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU.json","view_paper":"https://pith.science/paper/3FYQBQXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.13991&json=true","fetch_graph":"https://pith.science/api/pith-number/3FYQBQXNLEXTSHDW2Z3EEOPRTU/graph.json","fetch_events":"https://pith.science/api/pith-number/3FYQBQXNLEXTSHDW2Z3EEOPRTU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU/action/storage_attestation","attest_author":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU/action/author_attestation","sign_citation":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU/action/citation_signature","submit_replication":"https://pith.science/pith/3FYQBQXNLEXTSHDW2Z3EEOPRTU/action/replication_record"}},"created_at":"2026-07-05T08:59:14.577866+00:00","updated_at":"2026-07-05T08:59:14.577866+00:00"}