{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZCC2UMY5EVIIK22ERQFSDM5NQS","short_pith_number":"pith:ZCC2UMY5","schema_version":"1.0","canonical_sha256":"c885aa331d2550856b448c0b21b3ad84b74f68bba1974c2515aa8db6d16f494c","source":{"kind":"arxiv","id":"2606.25758","version":1},"attestation_state":"computed","paper":{"title":"Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Liang Xu, Wenjie Zhu, Wenjun Zeng, Xin Jin, Yabin Zhang","submitted_at":"2026-06-24T12:32:01Z","abstract_excerpt":"While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to out-of-distribution (OOD) outliers prevalent in real-world applications. This discrepancy motivates Noisy TTA (NTTA), an online task to filter noisy OOD samples on the fly while maximizing in-distribution (ID) classification accuracy. Existing zero-shot NTTA approaches typically rely on test-time discriminative training, leading to overconfident misclassifications and significantly degraded inference efficiency. To address these limitations, we propose a novel fr"},"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":"2606.25758","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T12:32:01Z","cross_cats_sorted":[],"title_canon_sha256":"59c7993b09556c063ca2f723c0afa3067ff3c3e61a770072f632562e0399bdd7","abstract_canon_sha256":"4b704d46b1817bc7b1d629236ef191a28805b80633949d4cb8f014a308bf1bfa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:14.469604Z","signature_b64":"XNwjmggk5HpRt/fC074P24Ikm06t8mxisBO7cB/IpybJfiPk+dknx23nSe9YlQbR8newKQchcdrIPZx1OlksBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c885aa331d2550856b448c0b21b3ad84b74f68bba1974c2515aa8db6d16f494c","last_reissued_at":"2026-06-25T01:18:14.469263Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:14.469263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Liang Xu, Wenjie Zhu, Wenjun Zeng, Xin Jin, Yabin Zhang","submitted_at":"2026-06-24T12:32:01Z","abstract_excerpt":"While test-time adaptation (TTA) empowers vision-language models to adapt without costly retraining, it remains highly vulnerable to out-of-distribution (OOD) outliers prevalent in real-world applications. This discrepancy motivates Noisy TTA (NTTA), an online task to filter noisy OOD samples on the fly while maximizing in-distribution (ID) classification accuracy. Existing zero-shot NTTA approaches typically rely on test-time discriminative training, leading to overconfident misclassifications and significantly degraded inference efficiency. To address these limitations, we propose a novel fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25758","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/2606.25758/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":"2606.25758","created_at":"2026-06-25T01:18:14.469324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25758v1","created_at":"2026-06-25T01:18:14.469324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25758","created_at":"2026-06-25T01:18:14.469324+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZCC2UMY5EVII","created_at":"2026-06-25T01:18:14.469324+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZCC2UMY5EVIIK22E","created_at":"2026-06-25T01:18:14.469324+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZCC2UMY5","created_at":"2026-06-25T01:18:14.469324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS","json":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS.json","graph_json":"https://pith.science/api/pith-number/ZCC2UMY5EVIIK22ERQFSDM5NQS/graph.json","events_json":"https://pith.science/api/pith-number/ZCC2UMY5EVIIK22ERQFSDM5NQS/events.json","paper":"https://pith.science/paper/ZCC2UMY5"},"agent_actions":{"view_html":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS","download_json":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS.json","view_paper":"https://pith.science/paper/ZCC2UMY5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25758&json=true","fetch_graph":"https://pith.science/api/pith-number/ZCC2UMY5EVIIK22ERQFSDM5NQS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZCC2UMY5EVIIK22ERQFSDM5NQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS/action/storage_attestation","attest_author":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS/action/author_attestation","sign_citation":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS/action/citation_signature","submit_replication":"https://pith.science/pith/ZCC2UMY5EVIIK22ERQFSDM5NQS/action/replication_record"}},"created_at":"2026-06-25T01:18:14.469324+00:00","updated_at":"2026-06-25T01:18:14.469324+00:00"}