{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WFR4QI6GINBRQNTDLPJUTP7WDZ","short_pith_number":"pith:WFR4QI6G","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"},"canonical_sha256":"b163c823c643431836635bd349bff61e4fb4375a7144f513dd9bb932522a2798","source":{"kind":"arxiv","id":"2306.04356","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04356","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04356v2","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04356","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"WFR4QI6GINBR","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"WFR4QI6GINBRQNTD","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"WFR4QI6G","created_at":"2026-07-05T07:23:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WFR4QI6GINBRQNTDLPJUTP7WDZ","target":"record","payload":{"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"},"canonical_sha256":"b163c823c643431836635bd349bff61e4fb4375a7144f513dd9bb932522a2798","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"},"source_kind":"arxiv","source_id":"2306.04356","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CF/x2BUUB2tu0tEmKe/+dlLAYBguuLHS1muuIugK9Nrah+B0dywNz2D32o5gZr9guJLgSJgE35kjDHwB/dC/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T06:59:28.497000Z"},"content_sha256":"d310414d2c9e41eac9154a9c7c26e3ea24ed293f249eedd1f32cc3363a42128e","schema_version":"1.0","event_id":"sha256:d310414d2c9e41eac9154a9c7c26e3ea24ed293f249eedd1f32cc3363a42128e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WFR4QI6GINBRQNTDLPJUTP7WDZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uWRARqRvss2G5lXKPzpCEpnWuxm7FFJL0LhHZUgKSo9hy+tKRpWxt/cLr/k2GoK7B4kZpMk59u7devVEiT+mDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T06:59:28.497384Z"},"content_sha256":"f5e35440b242adc04d81ba399ccbf36d33034b8e665187f89fa58650da30e93a","schema_version":"1.0","event_id":"sha256:f5e35440b242adc04d81ba399ccbf36d33034b8e665187f89fa58650da30e93a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/bundle.json","state_url":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T06:59:28Z","links":{"resolver":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ","bundle":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/bundle.json","state":"https://pith.science/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WFR4QI6GINBRQNTDLPJUTP7WDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WFR4QI6GINBRQNTDLPJUTP7WDZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"778a754f7a096e26c97599c71891028bff221c7e9391d3893765cb695e1dccf6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:39:56Z","title_canon_sha256":"cf8366d923fff01cf26248cfe6104750d2ce664afaac539ed8d3be2767131875"},"schema_version":"1.0","source":{"id":"2306.04356","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04356","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04356v2","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04356","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"WFR4QI6GINBR","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"pith_short_16","alias_value":"WFR4QI6GINBRQNTD","created_at":"2026-07-05T07:23:03Z"},{"alias_kind":"pith_short_8","alias_value":"WFR4QI6G","created_at":"2026-07-05T07:23:03Z"}],"graph_snapshots":[{"event_id":"sha256:f5e35440b242adc04d81ba399ccbf36d33034b8e665187f89fa58650da30e93a","target":"graph","created_at":"2026-07-05T07:23:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.04356/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jian Yang, Lingfeng Yang, Xiang Li, Xinlong Wang, Yueze Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:39:56Z","title":"Fine-Grained Visual Prompting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04356","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d310414d2c9e41eac9154a9c7c26e3ea24ed293f249eedd1f32cc3363a42128e","target":"record","created_at":"2026-07-05T07:23:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"778a754f7a096e26c97599c71891028bff221c7e9391d3893765cb695e1dccf6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-07T11:39:56Z","title_canon_sha256":"cf8366d923fff01cf26248cfe6104750d2ce664afaac539ed8d3be2767131875"},"schema_version":"1.0","source":{"id":"2306.04356","kind":"arxiv","version":2}},"canonical_sha256":"b163c823c643431836635bd349bff61e4fb4375a7144f513dd9bb932522a2798","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b163c823c643431836635bd349bff61e4fb4375a7144f513dd9bb932522a2798","first_computed_at":"2026-07-05T07:23:03.330089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:03.330089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LfRZ3eO5Xv7pHeh/da6S2ITRTe3UO5TnfD//PxAdGEbkpF88VdPeJG0yhoO1uiwCjWWdNWWc1fdf2T/s5RtvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:03.330637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04356","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d310414d2c9e41eac9154a9c7c26e3ea24ed293f249eedd1f32cc3363a42128e","sha256:f5e35440b242adc04d81ba399ccbf36d33034b8e665187f89fa58650da30e93a"],"state_sha256":"08a86cb05f7658461fd3e19aaf398d1214a17e0a3ef582c8619d289b9afdff4b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"03qnYC7yZRzy3ZlydK10+/HudzxWec2hG6APoAzhP6w/i0paG/CcGxlrlyDXo2WFClMqfJwE6jPutwS5Q9kIAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T06:59:28.499299Z","bundle_sha256":"227219184906e9de15ff2939a04118dea8c570653ae490301d68acda26c2b99d"}}