{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NKR6PCSETZTKIG52OVCDWVD5KF","short_pith_number":"pith:NKR6PCSE","schema_version":"1.0","canonical_sha256":"6aa3e78a449e66a41bba75443b547d5152c028326a5b5c6676fff31bab824a8b","source":{"kind":"arxiv","id":"2402.08712","version":3},"attestation_state":"computed","paper":{"title":"BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daeun Lee, Jaehong Yoon, Sung Ju Hwang","submitted_at":"2024-02-13T18:37:53Z","abstract_excerpt":"Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that cont"},"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":"2402.08712","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-13T18:37:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"89c1124856cf78bc6ecb9ba68c4539fb88ffd453f853bb1485dd93abb4199d31","abstract_canon_sha256":"fbae201152bb5ec322c6549b38d7468223b472b21dc9f63e816962322f18ae58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:52.438007Z","signature_b64":"q88GgeKF5fb8XsGLoJbrtrVCS0r3Vw3xRrjKRbfj1VLq8gbv21Gk5PZiRyeEx395ofjVLL9TLhk2ac0KyeglBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aa3e78a449e66a41bba75443b547d5152c028326a5b5c6676fff31bab824a8b","last_reissued_at":"2026-07-05T08:25:52.437472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:52.437472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daeun Lee, Jaehong Yoon, Sung Ju Hwang","submitted_at":"2024-02-13T18:37:53Z","abstract_excerpt":"Continual Test Time Adaptation (CTTA) is required to adapt efficiently to continuous unseen domains while retaining previously learned knowledge. However, despite the progress of CTTA, it is still challenging to deploy the model with improved forgetting-adaptation trade-offs and efficiency. In addition, current CTTA scenarios assume only the disjoint situation, even though real-world domains are seamlessly changed. To address these challenges, this paper proposes BECoTTA, an input-dependent and efficient modular framework for CTTA. We propose Mixture-of Domain Low-rank Experts (MoDE) that cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08712","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/2402.08712/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":"2402.08712","created_at":"2026-07-05T08:25:52.437540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08712v3","created_at":"2026-07-05T08:25:52.437540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08712","created_at":"2026-07-05T08:25:52.437540+00:00"},{"alias_kind":"pith_short_12","alias_value":"NKR6PCSETZTK","created_at":"2026-07-05T08:25:52.437540+00:00"},{"alias_kind":"pith_short_16","alias_value":"NKR6PCSETZTKIG52","created_at":"2026-07-05T08:25:52.437540+00:00"},{"alias_kind":"pith_short_8","alias_value":"NKR6PCSE","created_at":"2026-07-05T08:25:52.437540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17743","citing_title":"MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07926","citing_title":"IMSE: Intrinsic Mixture of Spectral Experts Fine-tuning for Test-Time Adaptation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF","json":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF.json","graph_json":"https://pith.science/api/pith-number/NKR6PCSETZTKIG52OVCDWVD5KF/graph.json","events_json":"https://pith.science/api/pith-number/NKR6PCSETZTKIG52OVCDWVD5KF/events.json","paper":"https://pith.science/paper/NKR6PCSE"},"agent_actions":{"view_html":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF","download_json":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF.json","view_paper":"https://pith.science/paper/NKR6PCSE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08712&json=true","fetch_graph":"https://pith.science/api/pith-number/NKR6PCSETZTKIG52OVCDWVD5KF/graph.json","fetch_events":"https://pith.science/api/pith-number/NKR6PCSETZTKIG52OVCDWVD5KF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF/action/storage_attestation","attest_author":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF/action/author_attestation","sign_citation":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF/action/citation_signature","submit_replication":"https://pith.science/pith/NKR6PCSETZTKIG52OVCDWVD5KF/action/replication_record"}},"created_at":"2026-07-05T08:25:52.437540+00:00","updated_at":"2026-07-05T08:25:52.437540+00:00"}