{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EIR6YJB5TYAFDFSPGPIXA7KQR2","short_pith_number":"pith:EIR6YJB5","schema_version":"1.0","canonical_sha256":"2223ec243d9e0051964f33d1707d508e91c0691728ea0c66ca25773eab845f38","source":{"kind":"arxiv","id":"2303.08138","version":1},"attestation_state":"computed","paper":{"title":"Diversity-Aware Meta Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Feifei Wang, Gang Hua, Nenghai Yu, Qidong Huang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2023-03-14T17:59:59Z","abstract_excerpt":"We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone. A challenging issue in visual prompting is that image datasets sometimes have a large data diversity whereas a per-dataset generic prompt can hardly handle the complex distribution shift toward the original pretraining data distribution properly. To address this issue, we propose a dataset Diversity-Aware prompting strategy whose initialization is realized by a Meta-prompt. Specifically, we cluster the downstream da"},"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":"2303.08138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-14T17:59:59Z","cross_cats_sorted":[],"title_canon_sha256":"da8057df924b37d2360e9595f0939b163a35fbff1f99a09d0f276da3ae64cfb3","abstract_canon_sha256":"056e6281d53df28a7ef613d649e70999c1c045295717c9982d9c618bdef08574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:15.264492Z","signature_b64":"GrTcwpAe87JQ9mFzbVQe65Yn7Vks8IKjncAEyyFWO0czcZEjVOsjcKokp3wwlPpPQ/yTN9yTcredZ1jkgbiKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2223ec243d9e0051964f33d1707d508e91c0691728ea0c66ca25773eab845f38","last_reissued_at":"2026-07-05T05:51:15.263980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:15.263980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity-Aware Meta Visual Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongdong Chen, Feifei Wang, Gang Hua, Nenghai Yu, Qidong Huang, Weiming Zhang, Xiaoyi Dong","submitted_at":"2023-03-14T17:59:59Z","abstract_excerpt":"We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone. A challenging issue in visual prompting is that image datasets sometimes have a large data diversity whereas a per-dataset generic prompt can hardly handle the complex distribution shift toward the original pretraining data distribution properly. To address this issue, we propose a dataset Diversity-Aware prompting strategy whose initialization is realized by a Meta-prompt. Specifically, we cluster the downstream da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08138","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/2303.08138/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":"2303.08138","created_at":"2026-07-05T05:51:15.264046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08138v1","created_at":"2026-07-05T05:51:15.264046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08138","created_at":"2026-07-05T05:51:15.264046+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIR6YJB5TYAF","created_at":"2026-07-05T05:51:15.264046+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIR6YJB5TYAFDFSP","created_at":"2026-07-05T05:51:15.264046+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIR6YJB5","created_at":"2026-07-05T05:51:15.264046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14718","citing_title":"GraphTheft: Quantifying Privacy Risks in Graph Prompt Learning","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2","json":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2.json","graph_json":"https://pith.science/api/pith-number/EIR6YJB5TYAFDFSPGPIXA7KQR2/graph.json","events_json":"https://pith.science/api/pith-number/EIR6YJB5TYAFDFSPGPIXA7KQR2/events.json","paper":"https://pith.science/paper/EIR6YJB5"},"agent_actions":{"view_html":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2","download_json":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2.json","view_paper":"https://pith.science/paper/EIR6YJB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08138&json=true","fetch_graph":"https://pith.science/api/pith-number/EIR6YJB5TYAFDFSPGPIXA7KQR2/graph.json","fetch_events":"https://pith.science/api/pith-number/EIR6YJB5TYAFDFSPGPIXA7KQR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2/action/storage_attestation","attest_author":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2/action/author_attestation","sign_citation":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2/action/citation_signature","submit_replication":"https://pith.science/pith/EIR6YJB5TYAFDFSPGPIXA7KQR2/action/replication_record"}},"created_at":"2026-07-05T05:51:15.264046+00:00","updated_at":"2026-07-05T05:51:15.264046+00:00"}