{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JTWEDAWH6KQ7S7OLZIOT6BL5ZU","short_pith_number":"pith:JTWEDAWH","schema_version":"1.0","canonical_sha256":"4cec4182c7f2a1f97dcbca1d3f057dcd0b7bcb42f2385ac0d50d9217e1ff2b2a","source":{"kind":"arxiv","id":"2302.05155","version":2},"attestation_state":"computed","paper":{"title":"TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byeonggeun Kim, Hyesu Lim, Jaegul Choo, Sungha Choi","submitted_at":"2023-02-10T10:25:29Z","abstract_excerpt":"This paper proposes a novel batch normalization strategy for test-time adaptation. Recent test-time adaptation methods heavily rely on the modified batch normalization, i.e., transductive batch normalization (TBN), which calculates the mean and the variance from the current test batch rather than using the running mean and variance obtained from the source data, i.e., conventional batch normalization (CBN). Adopting TBN that employs test batch statistics mitigates the performance degradation caused by the domain shift. However, re-estimating normalization statistics using test data depends on "},"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":"2302.05155","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-02-10T10:25:29Z","cross_cats_sorted":[],"title_canon_sha256":"8b24d873322bb1c4640d7d32057e2fe5721f240f2344d6740668d2aeded6424f","abstract_canon_sha256":"be559acc391337b3c0d721b29c2ff36a8c180b9bb0c8196d234198ad7d22fe23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:19.971140Z","signature_b64":"+l0wnp4I+RjewIZCoJ5LC93xKFg4ThHD2me9ZCWNlx5iUqxI+qiH0IX7LrYABQ2DPclxYaOI5I4hg15UEokaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cec4182c7f2a1f97dcbca1d3f057dcd0b7bcb42f2385ac0d50d9217e1ff2b2a","last_reissued_at":"2026-07-05T05:43:19.970700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:19.970700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Byeonggeun Kim, Hyesu Lim, Jaegul Choo, Sungha Choi","submitted_at":"2023-02-10T10:25:29Z","abstract_excerpt":"This paper proposes a novel batch normalization strategy for test-time adaptation. Recent test-time adaptation methods heavily rely on the modified batch normalization, i.e., transductive batch normalization (TBN), which calculates the mean and the variance from the current test batch rather than using the running mean and variance obtained from the source data, i.e., conventional batch normalization (CBN). Adopting TBN that employs test batch statistics mitigates the performance degradation caused by the domain shift. However, re-estimating normalization statistics using test data depends on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.05155","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/2302.05155/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":"2302.05155","created_at":"2026-07-05T05:43:19.970757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.05155v2","created_at":"2026-07-05T05:43:19.970757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.05155","created_at":"2026-07-05T05:43:19.970757+00:00"},{"alias_kind":"pith_short_12","alias_value":"JTWEDAWH6KQ7","created_at":"2026-07-05T05:43:19.970757+00:00"},{"alias_kind":"pith_short_16","alias_value":"JTWEDAWH6KQ7S7OL","created_at":"2026-07-05T05:43:19.970757+00:00"},{"alias_kind":"pith_short_8","alias_value":"JTWEDAWH","created_at":"2026-07-05T05:43:19.970757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13546","citing_title":"Learning Inference Concurrency in DynamicGate MLP Structural and Mathematical Justification","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU","json":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU.json","graph_json":"https://pith.science/api/pith-number/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/graph.json","events_json":"https://pith.science/api/pith-number/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/events.json","paper":"https://pith.science/paper/JTWEDAWH"},"agent_actions":{"view_html":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU","download_json":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU.json","view_paper":"https://pith.science/paper/JTWEDAWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.05155&json=true","fetch_graph":"https://pith.science/api/pith-number/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/graph.json","fetch_events":"https://pith.science/api/pith-number/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/action/storage_attestation","attest_author":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/action/author_attestation","sign_citation":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/action/citation_signature","submit_replication":"https://pith.science/pith/JTWEDAWH6KQ7S7OLZIOT6BL5ZU/action/replication_record"}},"created_at":"2026-07-05T05:43:19.970757+00:00","updated_at":"2026-07-05T05:43:19.970757+00:00"}