{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H3TSLSKMBPZQPJLBHNAWFM2J4V","short_pith_number":"pith:H3TSLSKM","schema_version":"1.0","canonical_sha256":"3ee725c94c0bf307a5613b4162b349e5735b530856514fca0887f06a895c9e72","source":{"kind":"arxiv","id":"2502.19946","version":1},"attestation_state":"computed","paper":{"title":"Space Rotation with Basis Transformation for Training-free Test-Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kot, Chenhao Ding, Qiang Wang, SongLin Dong, Xiang Song, Xinyuan Gao, Yihong Gong, Yuhang He","submitted_at":"2025-02-27T10:15:34Z","abstract_excerpt":"With the development of visual-language models (VLM) in downstream task applications, test-time adaptation methods based on VLM have attracted increasing attention for their ability to address changes distribution in test-time. Although prior approaches have achieved some progress, they typically either demand substantial computational resources or are constrained by the limitations of the original feature space, rendering them less effective for test-time adaptation tasks. To address these challenges, we propose a training-free feature space rotation with basis transformation for test-time ad"},"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":"2502.19946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T10:15:34Z","cross_cats_sorted":[],"title_canon_sha256":"4d21f569f7dd5f04759a392404d1032e00ae86501baa58c239e4b63cdb0e92e6","abstract_canon_sha256":"7a234fdd218b57f3dd411dd5843633a833fd7a7f146c54d0d177576d913890ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:55.720121Z","signature_b64":"Z0NlZ52AdpV9Si9n7MlFEToCDJGVKpHyIC+PBWd5RhFKWXZqtujbat7Smx38HL6ykGipgVnVL/eLnP+yHFTgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee725c94c0bf307a5613b4162b349e5735b530856514fca0887f06a895c9e72","last_reissued_at":"2026-07-05T10:20:55.719630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:55.719630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Space Rotation with Basis Transformation for Training-free Test-Time Adaptation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Kot, Chenhao Ding, Qiang Wang, SongLin Dong, Xiang Song, Xinyuan Gao, Yihong Gong, Yuhang He","submitted_at":"2025-02-27T10:15:34Z","abstract_excerpt":"With the development of visual-language models (VLM) in downstream task applications, test-time adaptation methods based on VLM have attracted increasing attention for their ability to address changes distribution in test-time. Although prior approaches have achieved some progress, they typically either demand substantial computational resources or are constrained by the limitations of the original feature space, rendering them less effective for test-time adaptation tasks. To address these challenges, we propose a training-free feature space rotation with basis transformation for test-time ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19946","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/2502.19946/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":"2502.19946","created_at":"2026-07-05T10:20:55.719683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19946v1","created_at":"2026-07-05T10:20:55.719683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19946","created_at":"2026-07-05T10:20:55.719683+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3TSLSKMBPZQ","created_at":"2026-07-05T10:20:55.719683+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3TSLSKMBPZQPJLB","created_at":"2026-07-05T10:20:55.719683+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3TSLSKM","created_at":"2026-07-05T10:20:55.719683+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05547","citing_title":"Adapting Vision-Language Models Without Labels: A Comprehensive Survey","ref_index":219,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V","json":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V.json","graph_json":"https://pith.science/api/pith-number/H3TSLSKMBPZQPJLBHNAWFM2J4V/graph.json","events_json":"https://pith.science/api/pith-number/H3TSLSKMBPZQPJLBHNAWFM2J4V/events.json","paper":"https://pith.science/paper/H3TSLSKM"},"agent_actions":{"view_html":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V","download_json":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V.json","view_paper":"https://pith.science/paper/H3TSLSKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19946&json=true","fetch_graph":"https://pith.science/api/pith-number/H3TSLSKMBPZQPJLBHNAWFM2J4V/graph.json","fetch_events":"https://pith.science/api/pith-number/H3TSLSKMBPZQPJLBHNAWFM2J4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V/action/storage_attestation","attest_author":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V/action/author_attestation","sign_citation":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V/action/citation_signature","submit_replication":"https://pith.science/pith/H3TSLSKMBPZQPJLBHNAWFM2J4V/action/replication_record"}},"created_at":"2026-07-05T10:20:55.719683+00:00","updated_at":"2026-07-05T10:20:55.719683+00:00"}