{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IRWRMPDKDNOFSSVEEB4JA5BMJ2","short_pith_number":"pith:IRWRMPDK","schema_version":"1.0","canonical_sha256":"446d163c6a1b5c594aa4207890742c4e85e6e3348ac6f51df6a3011339b5ed98","source":{"kind":"arxiv","id":"2306.00650","version":2},"attestation_state":"computed","paper":{"title":"Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Yang, Mario D\\\"obler, Robert A. Marsden","submitted_at":"2023-06-01T13:16:10Z","abstract_excerpt":"Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. Clearly, a method proposed for online TTA has to perform well for all kinds of environmental conditions. By introducing the variable factors domain non-stationarity and temporal correlation, we first unfold all practically relevant settings and define the entity as universal TTA. We want to highlight that this is the first work that covers such a broad spectrum, wh"},"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":"2306.00650","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T13:16:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"315b06496258e2525150b50526ad6816b9965aed619b51737d0343ef8ac332e3","abstract_canon_sha256":"8f7b152d80b3b8155b884f3016f5234b4130a7879f8ebb9d35c79f3d257e5b77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:09.407448Z","signature_b64":"aRMjYOw7ndMeqMOQHZN1kHZVjeChH6QGEP3ehSmxGV582eLnsMtg3QznOZ7YIFM1FbDeuVbJaNQdXPStygARDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"446d163c6a1b5c594aa4207890742c4e85e6e3348ac6f51df6a3011339b5ed98","last_reissued_at":"2026-07-05T07:05:09.406841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:09.406841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Test-time Adaptation through Weight Ensembling, Diversity Weighting, and Prior Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bin Yang, Mario D\\\"obler, Robert A. Marsden","submitted_at":"2023-06-01T13:16:10Z","abstract_excerpt":"Since distribution shifts are likely to occur during test-time and can drastically decrease the model's performance, online test-time adaptation (TTA) continues to update the model after deployment, leveraging the current test data. Clearly, a method proposed for online TTA has to perform well for all kinds of environmental conditions. By introducing the variable factors domain non-stationarity and temporal correlation, we first unfold all practically relevant settings and define the entity as universal TTA. We want to highlight that this is the first work that covers such a broad spectrum, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00650","kind":"arxiv","version":2},"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/2306.00650/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":"2306.00650","created_at":"2026-07-05T07:05:09.406916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00650v2","created_at":"2026-07-05T07:05:09.406916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00650","created_at":"2026-07-05T07:05:09.406916+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRWRMPDKDNOF","created_at":"2026-07-05T07:05:09.406916+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRWRMPDKDNOFSSVE","created_at":"2026-07-05T07:05:09.406916+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRWRMPDK","created_at":"2026-07-05T07:05:09.406916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17307","citing_title":"Learning to Adapt Frozen CLIP for Few-Shot Test-Time Domain Adaptation","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2","json":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2.json","graph_json":"https://pith.science/api/pith-number/IRWRMPDKDNOFSSVEEB4JA5BMJ2/graph.json","events_json":"https://pith.science/api/pith-number/IRWRMPDKDNOFSSVEEB4JA5BMJ2/events.json","paper":"https://pith.science/paper/IRWRMPDK"},"agent_actions":{"view_html":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2","download_json":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2.json","view_paper":"https://pith.science/paper/IRWRMPDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00650&json=true","fetch_graph":"https://pith.science/api/pith-number/IRWRMPDKDNOFSSVEEB4JA5BMJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/IRWRMPDKDNOFSSVEEB4JA5BMJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2/action/storage_attestation","attest_author":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2/action/author_attestation","sign_citation":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2/action/citation_signature","submit_replication":"https://pith.science/pith/IRWRMPDKDNOFSSVEEB4JA5BMJ2/action/replication_record"}},"created_at":"2026-07-05T07:05:09.406916+00:00","updated_at":"2026-07-05T07:05:09.406916+00:00"}