{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WFR4QI6GINBRQNTDLPJUTP7WDZ","short_pith_number":"pith:WFR4QI6G","schema_version":"1.0","canonical_sha256":"b163c823c643431836635bd349bff61e4fb4375a7144f513dd9bb932522a2798","source":{"kind":"arxiv","id":"2306.04356","version":2},"attestation_state":"computed","paper":{"title":"Fine-Grained Visual Prompting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Lingfeng Yang, Xiang Li, Xinlong Wang, Yueze Wang","submitted_at":"2023-06-07T11:39:56Z","abstract_excerpt":"Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited performance in instance-level tasks that demand precise localization and recognition. Previous works have suggested that incorporating visual prompts, such as colorful boxes or circles, can improve the ability of models to recognize objects of interest. Nonetheless, compared to language prompting, visual prompting designs are rarely explored. Existing approaches, which employ coarse visual cues such as colorful boxe"},"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":"2306.04356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:39:56Z","cross_cats_sorted":[],"title_canon_sha256":"cf8366d923fff01cf26248cfe6104750d2ce664afaac539ed8d3be2767131875","abstract_canon_sha256":"778a754f7a096e26c97599c71891028bff221c7e9391d3893765cb695e1dccf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:03.330637Z","signature_b64":"LfRZ3eO5Xv7pHeh/da6S2ITRTe3UO5TnfD//PxAdGEbkpF88VdPeJG0yhoO1uiwCjWWdNWWc1fdf2T/s5RtvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b163c823c643431836635bd349bff61e4fb4375a7144f513dd9bb932522a2798","last_reissued_at":"2026-07-05T07:23:03.330089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:03.330089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Visual Prompting","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Lingfeng Yang, Xiang Li, Xinlong Wang, Yueze Wang","submitted_at":"2023-06-07T11:39:56Z","abstract_excerpt":"Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited performance in instance-level tasks that demand precise localization and recognition. Previous works have suggested that incorporating visual prompts, such as colorful boxes or circles, can improve the ability of models to recognize objects of interest. Nonetheless, compared to language prompting, visual prompting designs are rarely explored. Existing approaches, which employ coarse visual cues such as colorful boxe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04356","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/2306.04356/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":"2306.04356","created_at":"2026-07-05T07:23:03.330146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04356v2","created_at":"2026-07-05T07:23:03.330146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04356","created_at":"2026-07-05T07:23:03.330146+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFR4QI6GINBR","created_at":"2026-07-05T07:23:03.330146+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFR4QI6GINBRQNTD","created_at":"2026-07-05T07:23:03.330146+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFR4QI6G","created_at":"2026-07-05T07:23:03.330146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20971","citing_title":"UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ","json":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ.json","graph_json":"https://pith.science/api/pith-number/WFR4QI6GINBRQNTDLPJUTP7WDZ/graph.json","events_json":"https://pith.science/api/pith-number/WFR4QI6GINBRQNTDLPJUTP7WDZ/events.json","paper":"https://pith.science/paper/WFR4QI6G"},"agent_actions":{"view_html":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ","download_json":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ.json","view_paper":"https://pith.science/paper/WFR4QI6G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04356&json=true","fetch_graph":"https://pith.science/api/pith-number/WFR4QI6GINBRQNTDLPJUTP7WDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WFR4QI6GINBRQNTDLPJUTP7WDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/action/storage_attestation","attest_author":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/action/author_attestation","sign_citation":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/action/citation_signature","submit_replication":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/action/replication_record"}},"created_at":"2026-07-05T07:23:03.330146+00:00","updated_at":"2026-07-05T07:23:03.330146+00:00"}