{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WADKGNMOG3UVKTJSOZ52HTOBKK","short_pith_number":"pith:WADKGNMO","schema_version":"1.0","canonical_sha256":"b006a3358e36e9554d32767ba3cdc15296b707d4701f40230dedf211ecffc6fb","source":{"kind":"arxiv","id":"2303.05266","version":1},"attestation_state":"computed","paper":{"title":"From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Backes, Yang Zhang, Zeyang Sha, Ziqing Yang","submitted_at":"2023-03-09T13:59:49Z","abstract_excerpt":"Visual prompt learning, as a newly emerged technique, leverages the knowledge learned by a large-scale pre-trained model and adapts it to downstream tasks through the usage of prompts. While previous research has focused on designing effective prompts, in this work, we argue that compared to prompt design, a good mapping strategy matters more. In this sense, we propose SeMap, a more effective mapping using the semantic alignment between the pre-trained model's knowledge and the downstream task. Our experimental results show that SeMap can largely boost the performance of visual prompt learning"},"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":"2303.05266","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T13:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"045bf997c59856a49a5b8730cdb997d7372ce38665e277b7c1e8c16788e761ca","abstract_canon_sha256":"7ce93b32f14dc3107e9583986710f7ad53808fa066e7e76bbdf89e03d8666d82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:38.926572Z","signature_b64":"0ML8xsbb9VsC0t4ORlWERV+nrOOlQVSOHkeGq4LEvHG0JpqKzMq6VhyIVHzBWEhN3ntSmzt7i3TatBpOGkczCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b006a3358e36e9554d32767ba3cdc15296b707d4701f40230dedf211ecffc6fb","last_reissued_at":"2026-07-05T05:49:38.926231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:38.926231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Visual Prompt Learning to Zero-Shot Transfer: Mapping Is All You Need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Michael Backes, Yang Zhang, Zeyang Sha, Ziqing Yang","submitted_at":"2023-03-09T13:59:49Z","abstract_excerpt":"Visual prompt learning, as a newly emerged technique, leverages the knowledge learned by a large-scale pre-trained model and adapts it to downstream tasks through the usage of prompts. While previous research has focused on designing effective prompts, in this work, we argue that compared to prompt design, a good mapping strategy matters more. In this sense, we propose SeMap, a more effective mapping using the semantic alignment between the pre-trained model's knowledge and the downstream task. Our experimental results show that SeMap can largely boost the performance of visual prompt learning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05266","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/2303.05266/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":"2303.05266","created_at":"2026-07-05T05:49:38.926279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05266v1","created_at":"2026-07-05T05:49:38.926279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05266","created_at":"2026-07-05T05:49:38.926279+00:00"},{"alias_kind":"pith_short_12","alias_value":"WADKGNMOG3UV","created_at":"2026-07-05T05:49:38.926279+00:00"},{"alias_kind":"pith_short_16","alias_value":"WADKGNMOG3UVKTJS","created_at":"2026-07-05T05:49:38.926279+00:00"},{"alias_kind":"pith_short_8","alias_value":"WADKGNMO","created_at":"2026-07-05T05:49:38.926279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31246","citing_title":"BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06440","citing_title":"Visual prompting reimagined: The power of the Activation Prompts","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK","json":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK.json","graph_json":"https://pith.science/api/pith-number/WADKGNMOG3UVKTJSOZ52HTOBKK/graph.json","events_json":"https://pith.science/api/pith-number/WADKGNMOG3UVKTJSOZ52HTOBKK/events.json","paper":"https://pith.science/paper/WADKGNMO"},"agent_actions":{"view_html":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK","download_json":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK.json","view_paper":"https://pith.science/paper/WADKGNMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05266&json=true","fetch_graph":"https://pith.science/api/pith-number/WADKGNMOG3UVKTJSOZ52HTOBKK/graph.json","fetch_events":"https://pith.science/api/pith-number/WADKGNMOG3UVKTJSOZ52HTOBKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK/action/storage_attestation","attest_author":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK/action/author_attestation","sign_citation":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK/action/citation_signature","submit_replication":"https://pith.science/pith/WADKGNMOG3UVKTJSOZ52HTOBKK/action/replication_record"}},"created_at":"2026-07-05T05:49:38.926279+00:00","updated_at":"2026-07-05T05:49:38.926279+00:00"}