{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JGDEWRPOEZ4A3TJLWX3XHPWXDR","short_pith_number":"pith:JGDEWRPO","schema_version":"1.0","canonical_sha256":"49864b45ee26780dcd2bb5f773bed71c62723225c952a1c494204b3eb454e1c9","source":{"kind":"arxiv","id":"2505.16257","version":1},"attestation_state":"computed","paper":{"title":"Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masanari Kimura","submitted_at":"2025-05-22T05:47:19Z","abstract_excerpt":"This study develops a higher-order asymptotic framework for test-time adaptation (TTA) of Batch Normalization (BN) statistics under distribution shift by integrating classical Edgeworth expansion and saddlepoint approximation techniques with a novel one-step M-estimation perspective. By analyzing the statistical discrepancy between training and test distributions, we derive an Edgeworth expansion for the normalized difference in BN means and obtain an optimal weighting parameter that minimizes the mean-squared error of the adapted statistic. Reinterpreting BN TTA as a one-step M-estimator allo"},"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":"2505.16257","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-05-22T05:47:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6a43c8a132d30adcb31d017f9e693f5714f05c1813c5d66e95df5badf14f9ff1","abstract_canon_sha256":"2d06b8e9e949e275e2e02e940d23b5e8aa0e65ff4fb3c0223e60a84633f26de7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:32.285115Z","signature_b64":"LXNTDCU+Ww+/rXf5f18z33i8wUpsXOL9kyfMynDIuNELklIpdz85Tjca9MooEr6Xq+PQYI0FBZsLsTG5TfarDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49864b45ee26780dcd2bb5f773bed71c62723225c952a1c494204b3eb454e1c9","last_reissued_at":"2026-07-05T11:07:32.284704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:32.284704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Masanari Kimura","submitted_at":"2025-05-22T05:47:19Z","abstract_excerpt":"This study develops a higher-order asymptotic framework for test-time adaptation (TTA) of Batch Normalization (BN) statistics under distribution shift by integrating classical Edgeworth expansion and saddlepoint approximation techniques with a novel one-step M-estimation perspective. By analyzing the statistical discrepancy between training and test distributions, we derive an Edgeworth expansion for the normalized difference in BN means and obtain an optimal weighting parameter that minimizes the mean-squared error of the adapted statistic. Reinterpreting BN TTA as a one-step M-estimator allo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16257","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/2505.16257/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":"2505.16257","created_at":"2026-07-05T11:07:32.284770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16257v1","created_at":"2026-07-05T11:07:32.284770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16257","created_at":"2026-07-05T11:07:32.284770+00:00"},{"alias_kind":"pith_short_12","alias_value":"JGDEWRPOEZ4A","created_at":"2026-07-05T11:07:32.284770+00:00"},{"alias_kind":"pith_short_16","alias_value":"JGDEWRPOEZ4A3TJL","created_at":"2026-07-05T11:07:32.284770+00:00"},{"alias_kind":"pith_short_8","alias_value":"JGDEWRPO","created_at":"2026-07-05T11:07:32.284770+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/JGDEWRPOEZ4A3TJLWX3XHPWXDR","json":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR.json","graph_json":"https://pith.science/api/pith-number/JGDEWRPOEZ4A3TJLWX3XHPWXDR/graph.json","events_json":"https://pith.science/api/pith-number/JGDEWRPOEZ4A3TJLWX3XHPWXDR/events.json","paper":"https://pith.science/paper/JGDEWRPO"},"agent_actions":{"view_html":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR","download_json":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR.json","view_paper":"https://pith.science/paper/JGDEWRPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16257&json=true","fetch_graph":"https://pith.science/api/pith-number/JGDEWRPOEZ4A3TJLWX3XHPWXDR/graph.json","fetch_events":"https://pith.science/api/pith-number/JGDEWRPOEZ4A3TJLWX3XHPWXDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR/action/storage_attestation","attest_author":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR/action/author_attestation","sign_citation":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR/action/citation_signature","submit_replication":"https://pith.science/pith/JGDEWRPOEZ4A3TJLWX3XHPWXDR/action/replication_record"}},"created_at":"2026-07-05T11:07:32.284770+00:00","updated_at":"2026-07-05T11:07:32.284770+00:00"}