{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BGAYTHT6PUTHVN2CNX2PBBFEAU","short_pith_number":"pith:BGAYTHT6","schema_version":"1.0","canonical_sha256":"0981899e7e7d267ab7426df4f084a405118ae83f63f6301be505712a1dddbbcc","source":{"kind":"arxiv","id":"2303.00198","version":2},"attestation_state":"computed","paper":{"title":"Convolutional Visual Prompt for Robust Visual Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Junfeng Yang, Yun-Yun Tsai","submitted_at":"2023-03-01T03:06:29Z","abstract_excerpt":"Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting. While visual prompts offer a lightweight method of input-space adaptation for large-scale vision models, they rely on a high-dimensional additive vector and labeled data. This leads to overfitting when adapting models in a self-supervised test-time setting without labels. We introduce convolutional visual prompts (CVP) for label-free test-time adaptation for robust visual perception. The structured nature of CVP demands fewer trainable parameters, less than 1\\% compared to standard visual prompts, combati"},"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":"2303.00198","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-01T03:06:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d066addcf9059df3965861a943ded3f3f9bf82233613c00e64e463aec27010f9","abstract_canon_sha256":"ee6b1aa4a65272900bc16f29489b493641e1c2d1434519d6862cbecb7d02403c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:06.653762Z","signature_b64":"3G9z6HKQuj1c3xOVLuBZ0BikZZ6F5o75vzUaJkaliLmuK/4/aQSPunG/E3x67j3uRISfkdrcGhWiJ7PECkYEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0981899e7e7d267ab7426df4f084a405118ae83f63f6301be505712a1dddbbcc","last_reissued_at":"2026-07-05T07:05:06.653186Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:06.653186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convolutional Visual Prompt for Robust Visual Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengzhi Mao, Junfeng Yang, Yun-Yun Tsai","submitted_at":"2023-03-01T03:06:29Z","abstract_excerpt":"Vision models are often vulnerable to out-of-distribution (OOD) samples without adapting. While visual prompts offer a lightweight method of input-space adaptation for large-scale vision models, they rely on a high-dimensional additive vector and labeled data. This leads to overfitting when adapting models in a self-supervised test-time setting without labels. We introduce convolutional visual prompts (CVP) for label-free test-time adaptation for robust visual perception. The structured nature of CVP demands fewer trainable parameters, less than 1\\% compared to standard visual prompts, combati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00198","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/2303.00198/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":"2303.00198","created_at":"2026-07-05T07:05:06.653245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.00198v2","created_at":"2026-07-05T07:05:06.653245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00198","created_at":"2026-07-05T07:05:06.653245+00:00"},{"alias_kind":"pith_short_12","alias_value":"BGAYTHT6PUTH","created_at":"2026-07-05T07:05:06.653245+00:00"},{"alias_kind":"pith_short_16","alias_value":"BGAYTHT6PUTHVN2C","created_at":"2026-07-05T07:05:06.653245+00:00"},{"alias_kind":"pith_short_8","alias_value":"BGAYTHT6","created_at":"2026-07-05T07:05:06.653245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06440","citing_title":"Visual prompting reimagined: The power of the Activation Prompts","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU","json":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU.json","graph_json":"https://pith.science/api/pith-number/BGAYTHT6PUTHVN2CNX2PBBFEAU/graph.json","events_json":"https://pith.science/api/pith-number/BGAYTHT6PUTHVN2CNX2PBBFEAU/events.json","paper":"https://pith.science/paper/BGAYTHT6"},"agent_actions":{"view_html":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU","download_json":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU.json","view_paper":"https://pith.science/paper/BGAYTHT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.00198&json=true","fetch_graph":"https://pith.science/api/pith-number/BGAYTHT6PUTHVN2CNX2PBBFEAU/graph.json","fetch_events":"https://pith.science/api/pith-number/BGAYTHT6PUTHVN2CNX2PBBFEAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU/action/storage_attestation","attest_author":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU/action/author_attestation","sign_citation":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU/action/citation_signature","submit_replication":"https://pith.science/pith/BGAYTHT6PUTHVN2CNX2PBBFEAU/action/replication_record"}},"created_at":"2026-07-05T07:05:06.653245+00:00","updated_at":"2026-07-05T07:05:06.653245+00:00"}