{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6WJUJFNBMA5PUZRVKTVHOPGRPZ","short_pith_number":"pith:6WJUJFNB","schema_version":"1.0","canonical_sha256":"f5934495a1603afa663554ea773cd17e483963c86fca6a2525769a914f8d3ced","source":{"kind":"arxiv","id":"2307.13770","version":1},"attestation_state":"computed","paper":{"title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Han, Dongfang Liu, Qifan Wang, Siyuan Qi, Wenguan Wang, Yiming Cui, Zhiwen Cao","submitted_at":"2023-07-25T19:03:21Z","abstract_excerpt":"As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the number of tunable parameters during fine-tuning. Although these methods show promising results, there is still a significant performance gap compared to full fine-tuning. To address this challenge, we propose an Effective and Efficient Visual Prompt Tuning (E^2VPT) approach for large-scale transformer-based model adaptation. Specifically, we introduce a set of le"},"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":"2307.13770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-25T19:03:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4dd3cc14875a9ebc1f985bc94f7270980b2ad5c32f21c8dd29715e6444212b61","abstract_canon_sha256":"473490645a6b5ee1686149c1ec2ef7cfb9fca91925d90b0828e5f6726e0f7542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:52.397908Z","signature_b64":"Z7oH5EevDSbY/va7OOkRmWfy/FYSCFqX5zaOpvP206izbxbn4B49E3MdMvZpd5ocTVA1eR2Wy/SoWTFCKMboCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5934495a1603afa663554ea773cd17e483963c86fca6a2525769a914f8d3ced","last_reissued_at":"2026-07-05T06:34:52.397419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:52.397419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Han, Dongfang Liu, Qifan Wang, Siyuan Qi, Wenguan Wang, Yiming Cui, Zhiwen Cao","submitted_at":"2023-07-25T19:03:21Z","abstract_excerpt":"As the size of transformer-based models continues to grow, fine-tuning these large-scale pretrained vision models for new tasks has become increasingly parameter-intensive. Parameter-efficient learning has been developed to reduce the number of tunable parameters during fine-tuning. Although these methods show promising results, there is still a significant performance gap compared to full fine-tuning. To address this challenge, we propose an Effective and Efficient Visual Prompt Tuning (E^2VPT) approach for large-scale transformer-based model adaptation. Specifically, we introduce a set of le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13770","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/2307.13770/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":"2307.13770","created_at":"2026-07-05T06:34:52.397479+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13770v1","created_at":"2026-07-05T06:34:52.397479+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13770","created_at":"2026-07-05T06:34:52.397479+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WJUJFNBMA5P","created_at":"2026-07-05T06:34:52.397479+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WJUJFNBMA5PUZRV","created_at":"2026-07-05T06:34:52.397479+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WJUJFNB","created_at":"2026-07-05T06:34:52.397479+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22383","citing_title":"Structured Hyperedge Adaptation for Parameter-Efficient Fine-Tuning of Vision Transformers","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19944","citing_title":"Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19478","citing_title":"Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06440","citing_title":"Visual prompting reimagined: The power of the Activation Prompts","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16943","citing_title":"MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ","json":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ.json","graph_json":"https://pith.science/api/pith-number/6WJUJFNBMA5PUZRVKTVHOPGRPZ/graph.json","events_json":"https://pith.science/api/pith-number/6WJUJFNBMA5PUZRVKTVHOPGRPZ/events.json","paper":"https://pith.science/paper/6WJUJFNB"},"agent_actions":{"view_html":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ","download_json":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ.json","view_paper":"https://pith.science/paper/6WJUJFNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13770&json=true","fetch_graph":"https://pith.science/api/pith-number/6WJUJFNBMA5PUZRVKTVHOPGRPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6WJUJFNBMA5PUZRVKTVHOPGRPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ/action/storage_attestation","attest_author":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ/action/author_attestation","sign_citation":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ/action/citation_signature","submit_replication":"https://pith.science/pith/6WJUJFNBMA5PUZRVKTVHOPGRPZ/action/replication_record"}},"created_at":"2026-07-05T06:34:52.397479+00:00","updated_at":"2026-07-05T06:34:52.397479+00:00"}