{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HAMUMHPXQ5ZRKUO3CCZ7QFETNM","short_pith_number":"pith:HAMUMHPX","schema_version":"1.0","canonical_sha256":"3819461df787731551db10b3f814936b17bfed1c22529a7318e2f73591e3a16d","source":{"kind":"arxiv","id":"2401.14619","version":1},"attestation_state":"computed","paper":{"title":"Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ka Chun Cheung, Nevin L. Zhang, Simon See, Xingzhi Zhou, Zhiliang Tian","submitted_at":"2024-01-26T03:24:55Z","abstract_excerpt":"Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference. However, the model performance can be significantly impaired by continuous distribution changes in the target domain and non-independent and identically distributed (non-i.i.d.) test samples often encountered in practical scenarios. While existing memory bank methodologies use memory to store samples and mitigate non-i.i.d. effects, they do not inherently prevent potential model degradation. To address this issue, we propose a resilient practical test"},"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":"2401.14619","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-26T03:24:55Z","cross_cats_sorted":[],"title_canon_sha256":"9ce6395ecb0cbe863608ffbbc79714b974a3192617ea75648f388b120b11c66c","abstract_canon_sha256":"aa0e4652a31f0b6b03dbe84029a5552bddd9ccd79d89d3ead1b12a949028492b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:59.142069Z","signature_b64":"FOd1fA/8fFI8Ywz9EFfoeyOpIbYceC6kTo6d8YFC3Xp38KhMGIM7+h+KibHgZdvQRW+ofdDVpR2sPKR28lH8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3819461df787731551db10b3f814936b17bfed1c22529a7318e2f73591e3a16d","last_reissued_at":"2026-07-05T07:37:59.141612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:59.141612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ka Chun Cheung, Nevin L. Zhang, Simon See, Xingzhi Zhou, Zhiliang Tian","submitted_at":"2024-01-26T03:24:55Z","abstract_excerpt":"Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference. However, the model performance can be significantly impaired by continuous distribution changes in the target domain and non-independent and identically distributed (non-i.i.d.) test samples often encountered in practical scenarios. While existing memory bank methodologies use memory to store samples and mitigate non-i.i.d. effects, they do not inherently prevent potential model degradation. To address this issue, we propose a resilient practical test"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14619","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/2401.14619/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":"2401.14619","created_at":"2026-07-05T07:37:59.141665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14619v1","created_at":"2026-07-05T07:37:59.141665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14619","created_at":"2026-07-05T07:37:59.141665+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAMUMHPXQ5ZR","created_at":"2026-07-05T07:37:59.141665+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAMUMHPXQ5ZRKUO3","created_at":"2026-07-05T07:37:59.141665+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAMUMHPX","created_at":"2026-07-05T07:37:59.141665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06782","citing_title":"Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM","json":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM.json","graph_json":"https://pith.science/api/pith-number/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/graph.json","events_json":"https://pith.science/api/pith-number/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/events.json","paper":"https://pith.science/paper/HAMUMHPX"},"agent_actions":{"view_html":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM","download_json":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM.json","view_paper":"https://pith.science/paper/HAMUMHPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14619&json=true","fetch_graph":"https://pith.science/api/pith-number/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/graph.json","fetch_events":"https://pith.science/api/pith-number/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/action/storage_attestation","attest_author":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/action/author_attestation","sign_citation":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/action/citation_signature","submit_replication":"https://pith.science/pith/HAMUMHPXQ5ZRKUO3CCZ7QFETNM/action/replication_record"}},"created_at":"2026-07-05T07:37:59.141665+00:00","updated_at":"2026-07-05T07:37:59.141665+00:00"}