{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XCYFIY2NZVT5SGAW54T5PDGM4J","short_pith_number":"pith:XCYFIY2N","schema_version":"1.0","canonical_sha256":"b8b054634dcd67d91816ef27d78ccce256214f950fdd7121c1f753f6051055be","source":{"kind":"arxiv","id":"2411.01327","version":2},"attestation_state":"computed","paper":{"title":"Visual Fourier Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Han, Chunshu Wu, Dongfang Liu, Lifu Huang, Qifan Wang, Runjia Zeng, Tong Geng, Ying Nian Wu","submitted_at":"2024-11-02T18:18:35Z","abstract_excerpt":"With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient finetuning (PEFT) method to this trend. Despite its successes, a notable research challenge persists within almost all PEFT approaches: significant performance degradation is observed when there is a substantial disparity between the datasets applied in pretraining and finetuning phases. To address this challenge, we draw inspiration from human visual cognition,"},"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":"2411.01327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-02T18:18:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d10a633d89b00c569d11affe6b0e531e78186533e8b899b2840f69ba53f8c8a2","abstract_canon_sha256":"77521097fc5c6633467a3e5328f70d5d01e2d5b982bd0c12bbde85a411678a5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:15.813470Z","signature_b64":"WUgPoDOXmEn8geZHB/5P7HyQj7AGr3k3d2xhyP4Yr6VRrziuHa/jfzBvJ/AnPEZ15wJ5U1Se+2Ais3ZaZkaMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b054634dcd67d91816ef27d78ccce256214f950fdd7121c1f753f6051055be","last_reissued_at":"2026-07-05T09:36:15.812948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:15.812948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Fourier Prompt Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cheng Han, Chunshu Wu, Dongfang Liu, Lifu Huang, Qifan Wang, Runjia Zeng, Tong Geng, Ying Nian Wu","submitted_at":"2024-11-02T18:18:35Z","abstract_excerpt":"With the scale of vision Transformer-based models continuing to grow, finetuning these large-scale pretrained models for new tasks has become increasingly parameter-intensive. Visual prompt tuning is introduced as a parameter-efficient finetuning (PEFT) method to this trend. Despite its successes, a notable research challenge persists within almost all PEFT approaches: significant performance degradation is observed when there is a substantial disparity between the datasets applied in pretraining and finetuning phases. To address this challenge, we draw inspiration from human visual cognition,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01327","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/2411.01327/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":"2411.01327","created_at":"2026-07-05T09:36:15.813009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01327v2","created_at":"2026-07-05T09:36:15.813009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01327","created_at":"2026-07-05T09:36:15.813009+00:00"},{"alias_kind":"pith_short_12","alias_value":"XCYFIY2NZVT5","created_at":"2026-07-05T09:36:15.813009+00:00"},{"alias_kind":"pith_short_16","alias_value":"XCYFIY2NZVT5SGAW","created_at":"2026-07-05T09:36:15.813009+00:00"},{"alias_kind":"pith_short_8","alias_value":"XCYFIY2N","created_at":"2026-07-05T09:36:15.813009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02406","citing_title":"Token Coordinated Prompt Attention is Needed for Visual Prompting","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J","json":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J.json","graph_json":"https://pith.science/api/pith-number/XCYFIY2NZVT5SGAW54T5PDGM4J/graph.json","events_json":"https://pith.science/api/pith-number/XCYFIY2NZVT5SGAW54T5PDGM4J/events.json","paper":"https://pith.science/paper/XCYFIY2N"},"agent_actions":{"view_html":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J","download_json":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J.json","view_paper":"https://pith.science/paper/XCYFIY2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01327&json=true","fetch_graph":"https://pith.science/api/pith-number/XCYFIY2NZVT5SGAW54T5PDGM4J/graph.json","fetch_events":"https://pith.science/api/pith-number/XCYFIY2NZVT5SGAW54T5PDGM4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J/action/storage_attestation","attest_author":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J/action/author_attestation","sign_citation":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J/action/citation_signature","submit_replication":"https://pith.science/pith/XCYFIY2NZVT5SGAW54T5PDGM4J/action/replication_record"}},"created_at":"2026-07-05T09:36:15.813009+00:00","updated_at":"2026-07-05T09:36:15.813009+00:00"}