{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KX3R2GOWJXFJRCV3FINYBRWJPC","short_pith_number":"pith:KX3R2GOW","schema_version":"1.0","canonical_sha256":"55f71d19d64dca988abb2a1b80c6c978968ee1d8fae0118f226d2acabe6e15f3","source":{"kind":"arxiv","id":"2306.04344","version":3},"attestation_state":"computed","paper":{"title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaming Liu, Ming Lu, Peidong Jia, Renrui Zhang, Senqiao Yang, Shanghang Zhang, Wei Xue, Yandong Guo","submitted_at":"2023-06-07T11:18:53Z","abstract_excerpt":"Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and "},"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":"2306.04344","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:18:53Z","cross_cats_sorted":[],"title_canon_sha256":"90b7e12f48c01e4b1fa272483e8e3c268cae67dea1cceb1b736e757723df91e3","abstract_canon_sha256":"84fddf885bf13c2d4d8007815e11bce5ba5c4e661ba37fa2c6989dca6187eb52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:14.484396Z","signature_b64":"XIvK/zQm2rIHNRMfuvHGGC9dz1C+b2ZWDBT6ixDeiTajFsT6+qmFaIsVpg3r29Z6A33T2b+e2pEld+b/0SzKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f71d19d64dca988abb2a1b80c6c978968ee1d8fae0118f226d2acabe6e15f3","last_reissued_at":"2026-07-05T08:01:14.483921Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:14.483921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaming Liu, Ming Lu, Peidong Jia, Renrui Zhang, Senqiao Yang, Shanghang Zhang, Wei Xue, Yandong Guo","submitted_at":"2023-06-07T11:18:53Z","abstract_excerpt":"Since real-world machine systems are running in non-stationary environments, Continual Test-Time Adaptation (CTTA) task is proposed to adapt the pre-trained model to continually changing target domains. Recently, existing methods mainly focus on model-based adaptation, which aims to leverage a self-training manner to extract the target domain knowledge. However, pseudo labels can be noisy and the updated model parameters are unreliable under dynamic data distributions, leading to error accumulation and catastrophic forgetting in the continual adaptation process. To tackle these challenges and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04344","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/2306.04344/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":"2306.04344","created_at":"2026-07-05T08:01:14.483970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04344v3","created_at":"2026-07-05T08:01:14.483970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04344","created_at":"2026-07-05T08:01:14.483970+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX3R2GOWJXFJ","created_at":"2026-07-05T08:01:14.483970+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX3R2GOWJXFJRCV3","created_at":"2026-07-05T08:01:14.483970+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX3R2GOW","created_at":"2026-07-05T08:01:14.483970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02671","citing_title":"Test-Time Distillation for Continual Model Adaptation","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC","json":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC.json","graph_json":"https://pith.science/api/pith-number/KX3R2GOWJXFJRCV3FINYBRWJPC/graph.json","events_json":"https://pith.science/api/pith-number/KX3R2GOWJXFJRCV3FINYBRWJPC/events.json","paper":"https://pith.science/paper/KX3R2GOW"},"agent_actions":{"view_html":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC","download_json":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC.json","view_paper":"https://pith.science/paper/KX3R2GOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04344&json=true","fetch_graph":"https://pith.science/api/pith-number/KX3R2GOWJXFJRCV3FINYBRWJPC/graph.json","fetch_events":"https://pith.science/api/pith-number/KX3R2GOWJXFJRCV3FINYBRWJPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC/action/storage_attestation","attest_author":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC/action/author_attestation","sign_citation":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC/action/citation_signature","submit_replication":"https://pith.science/pith/KX3R2GOWJXFJRCV3FINYBRWJPC/action/replication_record"}},"created_at":"2026-07-05T08:01:14.483970+00:00","updated_at":"2026-07-05T08:01:14.483970+00:00"}