{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VSRFB7SUS4Z7M34G62NOIFCTDA","short_pith_number":"pith:VSRFB7SU","schema_version":"1.0","canonical_sha256":"aca250fe549733f66f86f69ae41453182186497ee471b9ea39850e1e3b2f42f5","source":{"kind":"arxiv","id":"2606.07646","version":1},"attestation_state":"computed","paper":{"title":"DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Xiaoran Xu, Xiaoshan Yang, Yifan Xu, Yupeng Wu","submitted_at":"2026-06-02T03:24:03Z","abstract_excerpt":"Test-time adaptation (TTA) aims to align a model to shifting test domains using only unlabeled streaming data. Most existing methods implicitly infer a single global domain distribution, ignoring the multidimensional and sample-specific nature of real-world domain shifts, leading to fragile adaptation. We propose DOME, an effective domain encoder that explicitly models each sample's domain in a zero-shot manner. DOME leverages vision-language pretraining to extract dense, continuous representations, parameterizes domains as distributional variables, and introduces a momentum-updated sparse dom"},"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":"2606.07646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T03:24:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5c787aac458da826612e8906289115c1941c578aa6dd81718cef17fc894cd83","abstract_canon_sha256":"7b6ac2c0755c833bc62ad2b3476629badef48aa1542cab7af279186ba65ef49d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:45.729475Z","signature_b64":"baJLTaMWO/ddgMT1wO4Xp+zvLKccOebYSd1Trg5FIkwvg5UXI7cTo5mEFYFeZcHLknDcPQLEvh5QrQl6cch8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aca250fe549733f66f86f69ae41453182186497ee471b9ea39850e1e3b2f42f5","last_reissued_at":"2026-06-09T00:04:45.729114Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:45.729114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Xiaoran Xu, Xiaoshan Yang, Yifan Xu, Yupeng Wu","submitted_at":"2026-06-02T03:24:03Z","abstract_excerpt":"Test-time adaptation (TTA) aims to align a model to shifting test domains using only unlabeled streaming data. Most existing methods implicitly infer a single global domain distribution, ignoring the multidimensional and sample-specific nature of real-world domain shifts, leading to fragile adaptation. We propose DOME, an effective domain encoder that explicitly models each sample's domain in a zero-shot manner. DOME leverages vision-language pretraining to extract dense, continuous representations, parameterizes domains as distributional variables, and introduces a momentum-updated sparse dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07646","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/2606.07646/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":"2606.07646","created_at":"2026-06-09T00:04:45.729178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07646v1","created_at":"2026-06-09T00:04:45.729178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07646","created_at":"2026-06-09T00:04:45.729178+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSRFB7SUS4Z7","created_at":"2026-06-09T00:04:45.729178+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSRFB7SUS4Z7M34G","created_at":"2026-06-09T00:04:45.729178+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSRFB7SU","created_at":"2026-06-09T00:04:45.729178+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/VSRFB7SUS4Z7M34G62NOIFCTDA","json":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA.json","graph_json":"https://pith.science/api/pith-number/VSRFB7SUS4Z7M34G62NOIFCTDA/graph.json","events_json":"https://pith.science/api/pith-number/VSRFB7SUS4Z7M34G62NOIFCTDA/events.json","paper":"https://pith.science/paper/VSRFB7SU"},"agent_actions":{"view_html":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA","download_json":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA.json","view_paper":"https://pith.science/paper/VSRFB7SU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07646&json=true","fetch_graph":"https://pith.science/api/pith-number/VSRFB7SUS4Z7M34G62NOIFCTDA/graph.json","fetch_events":"https://pith.science/api/pith-number/VSRFB7SUS4Z7M34G62NOIFCTDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA/action/storage_attestation","attest_author":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA/action/author_attestation","sign_citation":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA/action/citation_signature","submit_replication":"https://pith.science/pith/VSRFB7SUS4Z7M34G62NOIFCTDA/action/replication_record"}},"created_at":"2026-06-09T00:04:45.729178+00:00","updated_at":"2026-06-09T00:04:45.729178+00:00"}