{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R7KBCVN4CN6B5LAWKDTXRVNWZ2","short_pith_number":"pith:R7KBCVN4","schema_version":"1.0","canonical_sha256":"8fd41155bc137c1eac1650e778d5b6ce8e4d641bec83530f60f3f54381b8c55d","source":{"kind":"arxiv","id":"2505.00533","version":2},"attestation_state":"computed","paper":{"title":"Test-time Correlation Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiabao Lu, Linjing You, Xiayuan Huang","submitted_at":"2025-05-01T13:59:13Z","abstract_excerpt":"Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test data) increasingly attractive. However, current TTA methods still face practical challenges: (1) a primary focus on instance-wise alignment, overlooking CORrelation ALignment (CORAL) due to missing source correlations; (2) complex backpropagation operations for model updating, resulting in overhead computation and (3) domain forgetting. To address these challe"},"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":"2505.00533","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T13:59:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21fe79d6879d1eea92e147e7067b6bcb6eb7cdfce3440e5b132b2a38d2fe8333","abstract_canon_sha256":"35d06b70085b249898c524bfa06e50e82f990051a6d57bafac7013d91e2c1fcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:21.429838Z","signature_b64":"SkxhHbBekQ28BqBw5Cfuiat6z8hRCxTKIWSkl3P15Q9k1BYgG2wB2LSyUUKz2zez1lPSqIM+RRdR/Hnwb+7XAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fd41155bc137c1eac1650e778d5b6ce8e4d641bec83530f60f3f54381b8c55d","last_reissued_at":"2026-07-05T11:18:21.429354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:21.429354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test-time Correlation Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiabao Lu, Linjing You, Xiayuan Huang","submitted_at":"2025-05-01T13:59:13Z","abstract_excerpt":"Deep neural networks often degrade under distribution shifts. Although domain adaptation offers a solution, privacy constraints often prevent access to source data, making Test-Time Adaptation (TTA, which adapts using only unlabeled test data) increasingly attractive. However, current TTA methods still face practical challenges: (1) a primary focus on instance-wise alignment, overlooking CORrelation ALignment (CORAL) due to missing source correlations; (2) complex backpropagation operations for model updating, resulting in overhead computation and (3) domain forgetting. To address these challe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00533","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/2505.00533/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":"2505.00533","created_at":"2026-07-05T11:18:21.429415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00533v2","created_at":"2026-07-05T11:18:21.429415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00533","created_at":"2026-07-05T11:18:21.429415+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7KBCVN4CN6B","created_at":"2026-07-05T11:18:21.429415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7KBCVN4CN6B5LAW","created_at":"2026-07-05T11:18:21.429415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7KBCVN4","created_at":"2026-07-05T11:18:21.429415+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/R7KBCVN4CN6B5LAWKDTXRVNWZ2","json":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2.json","graph_json":"https://pith.science/api/pith-number/R7KBCVN4CN6B5LAWKDTXRVNWZ2/graph.json","events_json":"https://pith.science/api/pith-number/R7KBCVN4CN6B5LAWKDTXRVNWZ2/events.json","paper":"https://pith.science/paper/R7KBCVN4"},"agent_actions":{"view_html":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2","download_json":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2.json","view_paper":"https://pith.science/paper/R7KBCVN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00533&json=true","fetch_graph":"https://pith.science/api/pith-number/R7KBCVN4CN6B5LAWKDTXRVNWZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/R7KBCVN4CN6B5LAWKDTXRVNWZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2/action/storage_attestation","attest_author":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2/action/author_attestation","sign_citation":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2/action/citation_signature","submit_replication":"https://pith.science/pith/R7KBCVN4CN6B5LAWKDTXRVNWZ2/action/replication_record"}},"created_at":"2026-07-05T11:18:21.429415+00:00","updated_at":"2026-07-05T11:18:21.429415+00:00"}