{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DLWPWNLJKMG6GQHTIIMA3CU3MW","short_pith_number":"pith:DLWPWNLJ","schema_version":"1.0","canonical_sha256":"1aecfb3569530de340f342180d8a9b65b901a2284dc54c2904bfec172c96e3b9","source":{"kind":"arxiv","id":"2407.12128","version":1},"attestation_state":"computed","paper":{"title":"Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Konstantinos Plataniotis, Li Gu, Yanan Wu, Yang Wang, Zhi Liu, Zhixiang Chi, Ziqiang Wang","submitted_at":"2024-07-16T19:33:23Z","abstract_excerpt":"Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch using self-training loss. While these methods yield commendable results in ideal test data streams, where batches are independently and identically sampled from the target distribution, they falter under more practical test data streams that are not independent and identically distributed (non-i.i.d.). The data batches in a non-i.i.d. stream display prominent "},"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":"2407.12128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-16T19:33:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6ac6515a04e7fa228f8c5986705e0c3fcc3742d2c077e550ba9b3cafcf74bca0","abstract_canon_sha256":"0681e7e858c89fe39fabf6e71fb7a75d1bda68042354b2ff42265c44a4a7e7ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:00.344000Z","signature_b64":"a1/J7apRFshmv4P7HlFCBXGfcdH8wUIh4Q5Kw28vTeFJC0JK075XN3UobUb57qPHAQy6fpKFTAvpZ58Gm2/iAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aecfb3569530de340f342180d8a9b65b901a2284dc54c2904bfec172c96e3b9","last_reissued_at":"2026-07-05T08:45:00.343604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:00.343604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Konstantinos Plataniotis, Li Gu, Yanan Wu, Yang Wang, Zhi Liu, Zhixiang Chi, Ziqiang Wang","submitted_at":"2024-07-16T19:33:23Z","abstract_excerpt":"Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source. Current methods predominantly optimize the model for each incoming test data batch using self-training loss. While these methods yield commendable results in ideal test data streams, where batches are independently and identically sampled from the target distribution, they falter under more practical test data streams that are not independent and identically distributed (non-i.i.d.). The data batches in a non-i.i.d. stream display prominent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12128","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/2407.12128/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":"2407.12128","created_at":"2026-07-05T08:45:00.343663+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12128v1","created_at":"2026-07-05T08:45:00.343663+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12128","created_at":"2026-07-05T08:45:00.343663+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLWPWNLJKMG6","created_at":"2026-07-05T08:45:00.343663+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLWPWNLJKMG6GQHT","created_at":"2026-07-05T08:45:00.343663+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLWPWNLJ","created_at":"2026-07-05T08:45:00.343663+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/DLWPWNLJKMG6GQHTIIMA3CU3MW","json":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW.json","graph_json":"https://pith.science/api/pith-number/DLWPWNLJKMG6GQHTIIMA3CU3MW/graph.json","events_json":"https://pith.science/api/pith-number/DLWPWNLJKMG6GQHTIIMA3CU3MW/events.json","paper":"https://pith.science/paper/DLWPWNLJ"},"agent_actions":{"view_html":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW","download_json":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW.json","view_paper":"https://pith.science/paper/DLWPWNLJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12128&json=true","fetch_graph":"https://pith.science/api/pith-number/DLWPWNLJKMG6GQHTIIMA3CU3MW/graph.json","fetch_events":"https://pith.science/api/pith-number/DLWPWNLJKMG6GQHTIIMA3CU3MW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW/action/storage_attestation","attest_author":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW/action/author_attestation","sign_citation":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW/action/citation_signature","submit_replication":"https://pith.science/pith/DLWPWNLJKMG6GQHTIIMA3CU3MW/action/replication_record"}},"created_at":"2026-07-05T08:45:00.343663+00:00","updated_at":"2026-07-05T08:45:00.343663+00:00"}