{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R724IKLFSKZ4F6JBMWW6OYUBOK","short_pith_number":"pith:R724IKLF","schema_version":"1.0","canonical_sha256":"8ff5c4296592b3c2f92165ade7628172bbf493452885aae34839d05855ffed5f","source":{"kind":"arxiv","id":"2212.10556","version":2},"attestation_state":"computed","paper":{"title":"Unleashing the Power of Visual Prompting At the Pixel Level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chen Wei, Cihang Xie, Huiyu Wang, Junyang Wu, Xianhang Li, Yuyin Zhou","submitted_at":"2022-12-20T18:57:06Z","abstract_excerpt":"This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image, we treat the prompt as an extra and independent learnable component. We show that the strategy of reconciling the prompt and the image matters, and find that warping the prompt around a properly shrinked image empirically works the best. Second, we re-introduce two \"old tricks\" commonly used in building transferable adversarial examples, i.e., input diversity"},"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":"2212.10556","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-20T18:57:06Z","cross_cats_sorted":[],"title_canon_sha256":"c1db361bfdf63b7093d307fa63fcd097caeb880b27b45447e2eae51548d325d2","abstract_canon_sha256":"b6b9364ace5c68088304a7eb351bad24d5987b7aca2eb66fc2b23dc79c60c890"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:02.098444Z","signature_b64":"m9lrMGT291EAo7SCA/WsUeepblhzmVLQM603rkgzCEwtGSlkAhNORMGYwCUSzqws8hzs9k6z3IO2mhxUp1Y/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ff5c4296592b3c2f92165ade7628172bbf493452885aae34839d05855ffed5f","last_reissued_at":"2026-07-05T05:56:02.097926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:02.097926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing the Power of Visual Prompting At the Pixel Level","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Chen Wei, Cihang Xie, Huiyu Wang, Junyang Wu, Xianhang Li, Yuyin Zhou","submitted_at":"2022-12-20T18:57:06Z","abstract_excerpt":"This paper presents a simple and effective visual prompting method for adapting pre-trained models to downstream recognition tasks. Our method includes two key designs. First, rather than directly adding together the prompt and the image, we treat the prompt as an extra and independent learnable component. We show that the strategy of reconciling the prompt and the image matters, and find that warping the prompt around a properly shrinked image empirically works the best. Second, we re-introduce two \"old tricks\" commonly used in building transferable adversarial examples, i.e., input diversity"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10556","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/2212.10556/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":"2212.10556","created_at":"2026-07-05T05:56:02.097989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10556v2","created_at":"2026-07-05T05:56:02.097989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10556","created_at":"2026-07-05T05:56:02.097989+00:00"},{"alias_kind":"pith_short_12","alias_value":"R724IKLFSKZ4","created_at":"2026-07-05T05:56:02.097989+00:00"},{"alias_kind":"pith_short_16","alias_value":"R724IKLFSKZ4F6JB","created_at":"2026-07-05T05:56:02.097989+00:00"},{"alias_kind":"pith_short_8","alias_value":"R724IKLF","created_at":"2026-07-05T05:56:02.097989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01945","citing_title":"Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00776","citing_title":"Latent Diffusion Pretraining for Crystal Property Prediction","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06440","citing_title":"Visual prompting reimagined: The power of the Activation Prompts","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK","json":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK.json","graph_json":"https://pith.science/api/pith-number/R724IKLFSKZ4F6JBMWW6OYUBOK/graph.json","events_json":"https://pith.science/api/pith-number/R724IKLFSKZ4F6JBMWW6OYUBOK/events.json","paper":"https://pith.science/paper/R724IKLF"},"agent_actions":{"view_html":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK","download_json":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK.json","view_paper":"https://pith.science/paper/R724IKLF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10556&json=true","fetch_graph":"https://pith.science/api/pith-number/R724IKLFSKZ4F6JBMWW6OYUBOK/graph.json","fetch_events":"https://pith.science/api/pith-number/R724IKLFSKZ4F6JBMWW6OYUBOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK/action/storage_attestation","attest_author":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK/action/author_attestation","sign_citation":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK/action/citation_signature","submit_replication":"https://pith.science/pith/R724IKLFSKZ4F6JBMWW6OYUBOK/action/replication_record"}},"created_at":"2026-07-05T05:56:02.097989+00:00","updated_at":"2026-07-05T05:56:02.097989+00:00"}