{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OMWCYM6FTHUTEK4WEW6ZF2UYJ2","short_pith_number":"pith:OMWCYM6F","schema_version":"1.0","canonical_sha256":"732c2c33c599e9322b9625bd92ea984e9f0dbf45c8ce90764e8e27aaa2124d86","source":{"kind":"arxiv","id":"2607.08164","version":1},"attestation_state":"computed","paper":{"title":"Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihun Hamm, Jose Dolz, Marco Pedersoli, Sarthak Kumar Maharana, Shambhavi Mishra, Shuaicheng Niu, Taki Hasan Rafi, Yunbei Zhang, Yunhui Guo","submitted_at":"2026-07-09T07:02:56Z","abstract_excerpt":"Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehen"},"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":"2607.08164","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T07:02:56Z","cross_cats_sorted":[],"title_canon_sha256":"8271ab52ad61dcad549bcdfc83656c4401e2610d1c37a2e475c206d9062c666e","abstract_canon_sha256":"98bce04f6196ad4c8b1c5bee7e9a9f981ef2e4fc398e5ef30c43ff39f466d7aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-10T01:19:28.466785Z","signature_b64":"EZ3MI++0MXI5ViqHYfB5VavP54Dfig2NMenY1WPASptUIYtOWCcxBefmE/t2xBJT+LccD4LUOF4OzxUIWvaACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"732c2c33c599e9322b9625bd92ea984e9f0dbf45c8ce90764e8e27aaa2124d86","last_reissued_at":"2026-07-10T01:19:28.466373Z","signature_status":"signed_v1","first_computed_at":"2026-07-10T01:19:28.466373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jihun Hamm, Jose Dolz, Marco Pedersoli, Sarthak Kumar Maharana, Shambhavi Mishra, Shuaicheng Niu, Taki Hasan Rafi, Yunbei Zhang, Yunhui Guo","submitted_at":"2026-07-09T07:02:56Z","abstract_excerpt":"Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08164","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/2607.08164/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":"2607.08164","created_at":"2026-07-10T01:19:28.466432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.08164v1","created_at":"2026-07-10T01:19:28.466432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08164","created_at":"2026-07-10T01:19:28.466432+00:00"},{"alias_kind":"pith_short_12","alias_value":"OMWCYM6FTHUT","created_at":"2026-07-10T01:19:28.466432+00:00"},{"alias_kind":"pith_short_16","alias_value":"OMWCYM6FTHUTEK4W","created_at":"2026-07-10T01:19:28.466432+00:00"},{"alias_kind":"pith_short_8","alias_value":"OMWCYM6F","created_at":"2026-07-10T01:19:28.466432+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/OMWCYM6FTHUTEK4WEW6ZF2UYJ2","json":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2.json","graph_json":"https://pith.science/api/pith-number/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/graph.json","events_json":"https://pith.science/api/pith-number/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/events.json","paper":"https://pith.science/paper/OMWCYM6F"},"agent_actions":{"view_html":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2","download_json":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2.json","view_paper":"https://pith.science/paper/OMWCYM6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.08164&json=true","fetch_graph":"https://pith.science/api/pith-number/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/action/storage_attestation","attest_author":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/action/author_attestation","sign_citation":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/action/citation_signature","submit_replication":"https://pith.science/pith/OMWCYM6FTHUTEK4WEW6ZF2UYJ2/action/replication_record"}},"created_at":"2026-07-10T01:19:28.466432+00:00","updated_at":"2026-07-10T01:19:28.466432+00:00"}