{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CQHDSOMIUPDAFCWO6XT52SVNQI","short_pith_number":"pith:CQHDSOMI","schema_version":"1.0","canonical_sha256":"140e393988a3c6028acef5e7dd4aad8221466e52b8c931aaef0277be80dfc54a","source":{"kind":"arxiv","id":"2406.03150","version":1},"attestation_state":"computed","paper":{"title":"Sample-specific Masks for Visual Reprogramming-based Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chengyi Cai, Feng Liu, Jianzhong Qi, Lei Feng, Zesheng Ye","submitted_at":"2024-06-05T11:15:43Z","abstract_excerpt":"Visual reprogramming (VR) is a prompting technique that aims to re-purpose a pre-trained model (e.g., a classifier on ImageNet) to target tasks (e.g., medical data prediction) by learning a small-scale pattern added into input images instead of tuning considerable parameters within the model. The location of the pattern within input samples is usually determined by a pre-defined mask shared across all samples. In this paper, we show that the shared mask potentially limits VR's generalization and increases its approximation error due to the lack of sample-level adaptation. Motivated by this fin"},"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":"2406.03150","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-05T11:15:43Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e2cfbb0fa63d1bdcc688d47dce00ceb23f380cf22c37801dab4193161a167796","abstract_canon_sha256":"0c9bfb4cbf7b474a954bfd800e5927be70850970d4bef5e0dfd7796a2388e1c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:52.060851Z","signature_b64":"OmqJx6jz158R5tiOmqS+5fxiOlaT0uUj32Pi6QBko+K4Tz5OWaI+n/A4U9TfAfCOl/w4mDU3GlpBhFR1fp06Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"140e393988a3c6028acef5e7dd4aad8221466e52b8c931aaef0277be80dfc54a","last_reissued_at":"2026-07-05T08:27:52.060425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:52.060425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-specific Masks for Visual Reprogramming-based Prompting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chengyi Cai, Feng Liu, Jianzhong Qi, Lei Feng, Zesheng Ye","submitted_at":"2024-06-05T11:15:43Z","abstract_excerpt":"Visual reprogramming (VR) is a prompting technique that aims to re-purpose a pre-trained model (e.g., a classifier on ImageNet) to target tasks (e.g., medical data prediction) by learning a small-scale pattern added into input images instead of tuning considerable parameters within the model. The location of the pattern within input samples is usually determined by a pre-defined mask shared across all samples. In this paper, we show that the shared mask potentially limits VR's generalization and increases its approximation error due to the lack of sample-level adaptation. Motivated by this fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03150","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/2406.03150/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":"2406.03150","created_at":"2026-07-05T08:27:52.060473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03150v1","created_at":"2026-07-05T08:27:52.060473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03150","created_at":"2026-07-05T08:27:52.060473+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQHDSOMIUPDA","created_at":"2026-07-05T08:27:52.060473+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQHDSOMIUPDAFCWO","created_at":"2026-07-05T08:27:52.060473+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQHDSOMI","created_at":"2026-07-05T08:27:52.060473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09532","citing_title":"Seeing is Believing: Robust Vision-Guided Cross-Modal Prompt Learning under Label Noise","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI","json":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI.json","graph_json":"https://pith.science/api/pith-number/CQHDSOMIUPDAFCWO6XT52SVNQI/graph.json","events_json":"https://pith.science/api/pith-number/CQHDSOMIUPDAFCWO6XT52SVNQI/events.json","paper":"https://pith.science/paper/CQHDSOMI"},"agent_actions":{"view_html":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI","download_json":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI.json","view_paper":"https://pith.science/paper/CQHDSOMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03150&json=true","fetch_graph":"https://pith.science/api/pith-number/CQHDSOMIUPDAFCWO6XT52SVNQI/graph.json","fetch_events":"https://pith.science/api/pith-number/CQHDSOMIUPDAFCWO6XT52SVNQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI/action/storage_attestation","attest_author":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI/action/author_attestation","sign_citation":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI/action/citation_signature","submit_replication":"https://pith.science/pith/CQHDSOMIUPDAFCWO6XT52SVNQI/action/replication_record"}},"created_at":"2026-07-05T08:27:52.060473+00:00","updated_at":"2026-07-05T08:27:52.060473+00:00"}