{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L27N2X5ZCAAUYXEAZ2LQWWIU6N","short_pith_number":"pith:L27N2X5Z","schema_version":"1.0","canonical_sha256":"5ebedd5fb910014c5c80ce970b5914f34f04a18cfe4470ef2153d6422c1b7532","source":{"kind":"arxiv","id":"2209.00647","version":1},"attestation_state":"computed","paper":{"title":"Visual Prompting via Image Inpainting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Amir Bar, Amir Globerson, Trevor Darrell, Yossi Gandelsman","submitted_at":"2022-09-01T17:59:33Z","abstract_excerpt":"How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by prompting in NLP, this paper investigates visual prompting: given input-output image example(s) of a new task at test time and a new input image, the goal is to automatically produce the output image, consistent with the given examples. We show that posing this problem as simple image inpainting - literally just filling in a hole in a concatenated visual prompt image - turns out to be surprisingly effective, provided that the inpainting algorithm has b"},"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":"2209.00647","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-09-01T17:59:33Z","cross_cats_sorted":[],"title_canon_sha256":"4ea9a092ae5362654d5b39aa90e40da0991de5e44bc2fbab05f104a831375bb0","abstract_canon_sha256":"314f62a3976392509fe3000590e720d975c9d0853c2cd8b378b691cd94029c83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:53:52.369646Z","signature_b64":"DjzYm7SRNtCA5C/5uacjmTO9vckE2JOkr1b54PiCMzYCXpUjsp02oCqBGT+sLkG7KRWujgGucKwW55RpSMD/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ebedd5fb910014c5c80ce970b5914f34f04a18cfe4470ef2153d6422c1b7532","last_reissued_at":"2026-07-05T04:53:52.369271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:53:52.369271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Prompting via Image Inpainting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Amir Bar, Amir Globerson, Trevor Darrell, Yossi Gandelsman","submitted_at":"2022-09-01T17:59:33Z","abstract_excerpt":"How does one adapt a pre-trained visual model to novel downstream tasks without task-specific finetuning or any model modification? Inspired by prompting in NLP, this paper investigates visual prompting: given input-output image example(s) of a new task at test time and a new input image, the goal is to automatically produce the output image, consistent with the given examples. We show that posing this problem as simple image inpainting - literally just filling in a hole in a concatenated visual prompt image - turns out to be surprisingly effective, provided that the inpainting algorithm has b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00647","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/2209.00647/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":"2209.00647","created_at":"2026-07-05T04:53:52.369339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.00647v1","created_at":"2026-07-05T04:53:52.369339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00647","created_at":"2026-07-05T04:53:52.369339+00:00"},{"alias_kind":"pith_short_12","alias_value":"L27N2X5ZCAAU","created_at":"2026-07-05T04:53:52.369339+00:00"},{"alias_kind":"pith_short_16","alias_value":"L27N2X5ZCAAUYXEA","created_at":"2026-07-05T04:53:52.369339+00:00"},{"alias_kind":"pith_short_8","alias_value":"L27N2X5Z","created_at":"2026-07-05T04:53:52.369339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.15263","citing_title":"gen2seg: Generative Models Enable Generalizable Instance Segmentation","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N","json":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N.json","graph_json":"https://pith.science/api/pith-number/L27N2X5ZCAAUYXEAZ2LQWWIU6N/graph.json","events_json":"https://pith.science/api/pith-number/L27N2X5ZCAAUYXEAZ2LQWWIU6N/events.json","paper":"https://pith.science/paper/L27N2X5Z"},"agent_actions":{"view_html":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N","download_json":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N.json","view_paper":"https://pith.science/paper/L27N2X5Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.00647&json=true","fetch_graph":"https://pith.science/api/pith-number/L27N2X5ZCAAUYXEAZ2LQWWIU6N/graph.json","fetch_events":"https://pith.science/api/pith-number/L27N2X5ZCAAUYXEAZ2LQWWIU6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N/action/storage_attestation","attest_author":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N/action/author_attestation","sign_citation":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N/action/citation_signature","submit_replication":"https://pith.science/pith/L27N2X5ZCAAUYXEAZ2LQWWIU6N/action/replication_record"}},"created_at":"2026-07-05T04:53:52.369339+00:00","updated_at":"2026-07-05T04:53:52.369339+00:00"}