{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LGPTCAUU5GJMU3NY77RH5ESMG3","short_pith_number":"pith:LGPTCAUU","schema_version":"1.0","canonical_sha256":"599f310294e992ca6db8ffe27e924c36d2776119e2a66a1d66dc61b65d700c8a","source":{"kind":"arxiv","id":"2506.02453","version":2},"attestation_state":"computed","paper":{"title":"PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Ge, Chengzhi Cao, Kunyu Wang, Wei Zhai, Xueyang Fu, Yuanfei Bao, Zheng-Jun Zha","submitted_at":"2025-06-03T05:18:15Z","abstract_excerpt":"Continual Test-Time Adaptation (CTTA) aims to online adapt a pre-trained model to changing environments during inference. Most existing methods focus on exploiting target data, while overlooking another crucial source of information, the pre-trained weights, which encode underutilized domain-invariant priors. This paper takes the geometric attributes of pre-trained weights as a starting point, systematically analyzing three key components: magnitude, absolute angle, and pairwise angular structure. We find that the pairwise angular structure remains stable across diverse corrupted domains and e"},"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":"2506.02453","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-03T05:18:15Z","cross_cats_sorted":[],"title_canon_sha256":"b1400012ac1696537ea28f68874090b62067caa055b828967a57a984577b4a1e","abstract_canon_sha256":"7fc7fffb36245964639eddc1a7aa1b31a9714978dfeeeb454eb6604e3c1456d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:07.378892Z","signature_b64":"cMzHJ/0U/14T3uIaZkCABSUB/6fsX9M7e5P5mtzq1ehUjoeefVPLQ0e4xz9SuUdG82N9fr/zgJnKYIYwCfesAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599f310294e992ca6db8ffe27e924c36d2776119e2a66a1d66dc61b65d700c8a","last_reissued_at":"2026-07-05T11:31:07.378378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:07.378378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengjie Ge, Chengzhi Cao, Kunyu Wang, Wei Zhai, Xueyang Fu, Yuanfei Bao, Zheng-Jun Zha","submitted_at":"2025-06-03T05:18:15Z","abstract_excerpt":"Continual Test-Time Adaptation (CTTA) aims to online adapt a pre-trained model to changing environments during inference. Most existing methods focus on exploiting target data, while overlooking another crucial source of information, the pre-trained weights, which encode underutilized domain-invariant priors. This paper takes the geometric attributes of pre-trained weights as a starting point, systematically analyzing three key components: magnitude, absolute angle, and pairwise angular structure. We find that the pairwise angular structure remains stable across diverse corrupted domains and e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02453","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/2506.02453/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":"2506.02453","created_at":"2026-07-05T11:31:07.378435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02453v2","created_at":"2026-07-05T11:31:07.378435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02453","created_at":"2026-07-05T11:31:07.378435+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGPTCAUU5GJM","created_at":"2026-07-05T11:31:07.378435+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGPTCAUU5GJMU3NY","created_at":"2026-07-05T11:31:07.378435+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGPTCAUU","created_at":"2026-07-05T11:31:07.378435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18608","citing_title":"Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3","json":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3.json","graph_json":"https://pith.science/api/pith-number/LGPTCAUU5GJMU3NY77RH5ESMG3/graph.json","events_json":"https://pith.science/api/pith-number/LGPTCAUU5GJMU3NY77RH5ESMG3/events.json","paper":"https://pith.science/paper/LGPTCAUU"},"agent_actions":{"view_html":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3","download_json":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3.json","view_paper":"https://pith.science/paper/LGPTCAUU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02453&json=true","fetch_graph":"https://pith.science/api/pith-number/LGPTCAUU5GJMU3NY77RH5ESMG3/graph.json","fetch_events":"https://pith.science/api/pith-number/LGPTCAUU5GJMU3NY77RH5ESMG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3/action/storage_attestation","attest_author":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3/action/author_attestation","sign_citation":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3/action/citation_signature","submit_replication":"https://pith.science/pith/LGPTCAUU5GJMU3NY77RH5ESMG3/action/replication_record"}},"created_at":"2026-07-05T11:31:07.378435+00:00","updated_at":"2026-07-05T11:31:07.378435+00:00"}