{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NOBOVIT5I7DNNR3I6VQYXOSFEO","short_pith_number":"pith:NOBOVIT5","schema_version":"1.0","canonical_sha256":"6b82eaa27d47c6d6c768f5618bba452399e768a537912a4aa63dcb4835bde794","source":{"kind":"arxiv","id":"2302.12400","version":1},"attestation_state":"computed","paper":{"title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiaxiang Wu, Mingkui Tan, Peilin Zhao, Shuaicheng Niu, Yaofo Chen, Yifan Zhang, Zhiquan Wen","submitted_at":"2023-02-24T02:03:41Z","abstract_excerpt":"Test-time adaptation (TTA) has shown to be effective at tackling distribution shifts between training and testing data by adapting a given model on test samples. However, the online model updating of TTA may be unstable and this is often a key obstacle preventing existing TTA methods from being deployed in the real world. Specifically, TTA may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, and 3) online imbalanced label distribution shifts, which are quite common in practice. In this paper, we investigate the unstable"},"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":"2302.12400","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-24T02:03:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fb5d896e7a73578bfe343a6ff73fdb2d488d69f0280854ff6b2919b7b6c475d0","abstract_canon_sha256":"e552949457b9c1b0aa3aefe2396b18c5fe18f4d0da2e5adeee0ed889ec6833ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:09.332776Z","signature_b64":"6TZoasJXEfxJrwl23wGxGF04ottynXHHtBzq0WXc9j7xLCcBhATYbjpkZgz2cPlWtSJBHlVFGgYbbc9OJUQiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b82eaa27d47c6d6c768f5618bba452399e768a537912a4aa63dcb4835bde794","last_reissued_at":"2026-07-05T05:45:09.332288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:09.332288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Stable Test-Time Adaptation in Dynamic Wild World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jiaxiang Wu, Mingkui Tan, Peilin Zhao, Shuaicheng Niu, Yaofo Chen, Yifan Zhang, Zhiquan Wen","submitted_at":"2023-02-24T02:03:41Z","abstract_excerpt":"Test-time adaptation (TTA) has shown to be effective at tackling distribution shifts between training and testing data by adapting a given model on test samples. However, the online model updating of TTA may be unstable and this is often a key obstacle preventing existing TTA methods from being deployed in the real world. Specifically, TTA may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, and 3) online imbalanced label distribution shifts, which are quite common in practice. In this paper, we investigate the unstable"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12400","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/2302.12400/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":"2302.12400","created_at":"2026-07-05T05:45:09.332358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12400v1","created_at":"2026-07-05T05:45:09.332358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12400","created_at":"2026-07-05T05:45:09.332358+00:00"},{"alias_kind":"pith_short_12","alias_value":"NOBOVIT5I7DN","created_at":"2026-07-05T05:45:09.332358+00:00"},{"alias_kind":"pith_short_16","alias_value":"NOBOVIT5I7DNNR3I","created_at":"2026-07-05T05:45:09.332358+00:00"},{"alias_kind":"pith_short_8","alias_value":"NOBOVIT5","created_at":"2026-07-05T05:45:09.332358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25758","citing_title":"Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22424","citing_title":"FlowDec: Temporal Conditional Flow Decorruptor for Robust Continuous Vision-Language Navigation","ref_index":33,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12939","citing_title":"MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07646","citing_title":"DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32026","citing_title":"AdaJEPA: An Adaptive Latent World Model","ref_index":22,"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":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24014","citing_title":"SkySeg: Collaborative Onboard Semantic Segmentation with Heterogeneous UAVs in the Wild","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23411","citing_title":"Sample-wise Targeted Adversarial Attacks on Test-time Adaptation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2505.00986","citing_title":"EmbodiTTA: Resource-Efficient Test-Time Adaptation for Embodied Visual Systems","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19890","citing_title":"GoTTA be Diverse: Rethinking Memory Policies for Test-Time Adaptation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19607","citing_title":"Contrastive Residual Energy Test-time Adaptation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02671","citing_title":"Test-Time Distillation for Continual Model Adaptation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10421","citing_title":"Neural Collapse in Test-Time Adaptation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01765","citing_title":"Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation","ref_index":32,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23636","citing_title":"Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08598","citing_title":"Pretrain-then-Adapt: Uncertainty-Aware Test-Time Adaptation for Text-based Person Search","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13546","citing_title":"Learning Inference Concurrency in DynamicGate MLP Structural and Mathematical Justification","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24602","citing_title":"Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO","json":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO.json","graph_json":"https://pith.science/api/pith-number/NOBOVIT5I7DNNR3I6VQYXOSFEO/graph.json","events_json":"https://pith.science/api/pith-number/NOBOVIT5I7DNNR3I6VQYXOSFEO/events.json","paper":"https://pith.science/paper/NOBOVIT5"},"agent_actions":{"view_html":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO","download_json":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO.json","view_paper":"https://pith.science/paper/NOBOVIT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12400&json=true","fetch_graph":"https://pith.science/api/pith-number/NOBOVIT5I7DNNR3I6VQYXOSFEO/graph.json","fetch_events":"https://pith.science/api/pith-number/NOBOVIT5I7DNNR3I6VQYXOSFEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO/action/storage_attestation","attest_author":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO/action/author_attestation","sign_citation":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO/action/citation_signature","submit_replication":"https://pith.science/pith/NOBOVIT5I7DNNR3I6VQYXOSFEO/action/replication_record"}},"created_at":"2026-07-05T05:45:09.332358+00:00","updated_at":"2026-07-05T05:45:09.332358+00:00"}