{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ZA27ZAYE5PVOBXTSSSWGK22ZS4","short_pith_number":"pith:ZA27ZAYE","schema_version":"1.0","canonical_sha256":"c835fc8304ebeae0de7294ac656b599720e225c618a8c57bb8d18fc24291491a","source":{"kind":"arxiv","id":"2210.07225","version":1},"attestation_state":"computed","paper":{"title":"Unified Vision and Language Prompt Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Chen Huang, Kaiyang Zhou, Wei Li, Yuhang Zang","submitted_at":"2022-10-13T17:50:24Z","abstract_excerpt":"Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP. We present a systematic study on two representative prompt tuning methods, namely text prompt tuning and visual prompt tuning. A major finding is that none of the unimodal prompt tuning methods performs consistently well: text prompt tuning fails on data with high intra-class visual variances while visual prompt tuning cannot handle low inter-clas"},"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":"2210.07225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-13T17:50:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"89b06c8372c13544cfc1f5f9e05597925b2142d575c887ec161da4d45fded9f5","abstract_canon_sha256":"b0e487253c0a4579574db77558d56ffe55133df785b95c825248d9726b7144c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:25.902418Z","signature_b64":"kVbJ3p5nXrJsaYswW9LKPaNmLyr+q5WSYQZYzVqvd6e+cI58LEpVTlbnaX/HPZLUkC18uLtE9nboh9aMyPzXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c835fc8304ebeae0de7294ac656b599720e225c618a8c57bb8d18fc24291491a","last_reissued_at":"2026-07-05T05:06:25.901911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:25.901911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Vision and Language Prompt Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Chen Huang, Kaiyang Zhou, Wei Li, Yuhang Zang","submitted_at":"2022-10-13T17:50:24Z","abstract_excerpt":"Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP. We present a systematic study on two representative prompt tuning methods, namely text prompt tuning and visual prompt tuning. A major finding is that none of the unimodal prompt tuning methods performs consistently well: text prompt tuning fails on data with high intra-class visual variances while visual prompt tuning cannot handle low inter-clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07225","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/2210.07225/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":"2210.07225","created_at":"2026-07-05T05:06:25.901971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07225v1","created_at":"2026-07-05T05:06:25.901971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07225","created_at":"2026-07-05T05:06:25.901971+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZA27ZAYE5PVO","created_at":"2026-07-05T05:06:25.901971+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZA27ZAYE5PVOBXTS","created_at":"2026-07-05T05:06:25.901971+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZA27ZAYE","created_at":"2026-07-05T05:06:25.901971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31246","citing_title":"BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2407.17491","citing_title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08156","citing_title":"LAGO: Language-Guided Adaptive Object-Region Focus for Zero-Shot Visual-Text Alignment","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05910","citing_title":"Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4","json":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4.json","graph_json":"https://pith.science/api/pith-number/ZA27ZAYE5PVOBXTSSSWGK22ZS4/graph.json","events_json":"https://pith.science/api/pith-number/ZA27ZAYE5PVOBXTSSSWGK22ZS4/events.json","paper":"https://pith.science/paper/ZA27ZAYE"},"agent_actions":{"view_html":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4","download_json":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4.json","view_paper":"https://pith.science/paper/ZA27ZAYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07225&json=true","fetch_graph":"https://pith.science/api/pith-number/ZA27ZAYE5PVOBXTSSSWGK22ZS4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZA27ZAYE5PVOBXTSSSWGK22ZS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4/action/storage_attestation","attest_author":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4/action/author_attestation","sign_citation":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4/action/citation_signature","submit_replication":"https://pith.science/pith/ZA27ZAYE5PVOBXTSSSWGK22ZS4/action/replication_record"}},"created_at":"2026-07-05T05:06:25.901971+00:00","updated_at":"2026-07-05T05:06:25.901971+00:00"}