{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A5KMZF5J2M5NV44KDRBHTBUCEU","short_pith_number":"pith:A5KMZF5J","schema_version":"1.0","canonical_sha256":"0754cc97a9d33adaf38a1c42798682250723ecbd5e769e3be957309107879492","source":{"kind":"arxiv","id":"2504.04981","version":2},"attestation_state":"computed","paper":{"title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Juwon Kang, Nayeong Kim, Seong Joon Oh, Sohyun Lee, Suha Kwak","submitted_at":"2025-04-07T12:09:18Z","abstract_excerpt":"This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge. Existing CTTA methods mostly focus on adaptation to the current test domain only, overlooking generalization to arbitrary test domains a model may face in the future. To tackle this limitation, we present a novel online test-time domain generalization framework for CTTA, dubbed TestDG. TestDG aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potenti"},"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":"2504.04981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T12:09:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39323b7850876b4f376dc35f05c6c17d665c6c3ed2b7f0bc9780362a0cd2c373","abstract_canon_sha256":"d5a032242f155f2c87cd3a0b6acdea26115fff3d8b193ef081dc93bc471372ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:57.917724Z","signature_b64":"kjDZZu0PjhGmx4kq1aFGnr8PAHeZ2ie17M3PmDDa5W5sApAYJ+Oil2d+3WWff6sU3IObwIMA3KMGxc9cTsQ3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0754cc97a9d33adaf38a1c42798682250723ecbd5e769e3be957309107879492","last_reissued_at":"2026-07-05T11:14:57.917236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:57.917236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TestDG: Test-time Domain Generalization for Continual Test-time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Juwon Kang, Nayeong Kim, Seong Joon Oh, Sohyun Lee, Suha Kwak","submitted_at":"2025-04-07T12:09:18Z","abstract_excerpt":"This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge. Existing CTTA methods mostly focus on adaptation to the current test domain only, overlooking generalization to arbitrary test domains a model may face in the future. To tackle this limitation, we present a novel online test-time domain generalization framework for CTTA, dubbed TestDG. TestDG aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04981","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/2504.04981/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":"2504.04981","created_at":"2026-07-05T11:14:57.917293+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04981v2","created_at":"2026-07-05T11:14:57.917293+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04981","created_at":"2026-07-05T11:14:57.917293+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5KMZF5J2M5N","created_at":"2026-07-05T11:14:57.917293+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5KMZF5J2M5NV44K","created_at":"2026-07-05T11:14:57.917293+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5KMZF5J","created_at":"2026-07-05T11:14:57.917293+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12006","citing_title":"Robust Promptable Video Object Segmentation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU","json":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU.json","graph_json":"https://pith.science/api/pith-number/A5KMZF5J2M5NV44KDRBHTBUCEU/graph.json","events_json":"https://pith.science/api/pith-number/A5KMZF5J2M5NV44KDRBHTBUCEU/events.json","paper":"https://pith.science/paper/A5KMZF5J"},"agent_actions":{"view_html":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU","download_json":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU.json","view_paper":"https://pith.science/paper/A5KMZF5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04981&json=true","fetch_graph":"https://pith.science/api/pith-number/A5KMZF5J2M5NV44KDRBHTBUCEU/graph.json","fetch_events":"https://pith.science/api/pith-number/A5KMZF5J2M5NV44KDRBHTBUCEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU/action/storage_attestation","attest_author":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU/action/author_attestation","sign_citation":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU/action/citation_signature","submit_replication":"https://pith.science/pith/A5KMZF5J2M5NV44KDRBHTBUCEU/action/replication_record"}},"created_at":"2026-07-05T11:14:57.917293+00:00","updated_at":"2026-07-05T11:14:57.917293+00:00"}