{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WBOCGK55QSQHIDW3BY7ZUWNQNF","short_pith_number":"pith:WBOCGK55","canonical_record":{"source":{"id":"2403.20271","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T16:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"9b2d57aca6d574777347802df8b9caa2dbed3dc68b4489b8f83896f5e840d796","abstract_canon_sha256":"775db813b1c577354b8423eadcdce0eff1100281b017220a78ef01c5f30246cb"},"schema_version":"1.0"},"canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","source":{"kind":"arxiv","id":"2403.20271","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.20271","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.20271v3","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20271","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"WBOCGK55QSQH","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"WBOCGK55QSQHIDW3","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"WBOCGK55","created_at":"2026-07-05T10:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WBOCGK55QSQHIDW3BY7ZUWNQNF","target":"record","payload":{"canonical_record":{"source":{"id":"2403.20271","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T16:26:20Z","cross_cats_sorted":[],"title_canon_sha256":"9b2d57aca6d574777347802df8b9caa2dbed3dc68b4489b8f83896f5e840d796","abstract_canon_sha256":"775db813b1c577354b8423eadcdce0eff1100281b017220a78ef01c5f30246cb"},"schema_version":"1.0"},"canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:08.193958Z","signature_b64":"yRpBu9VhObd2I0byq0DnU5qmUsdD7xbYUCt4rREAEKPcWpM/iF4MF5pCxkJ9pw+WR6T7DaD/a/F1W2XGXwHRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","last_reissued_at":"2026-07-05T10:18:08.193499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:08.193499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.20271","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BnOEj3j72UjWHvLABvvhdwrYrtwM9Ayi3W4wwlcZY4ETgLHCKxqQ99XfaU0xeBvO0DHxPPw6dz9olfma7e3JAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:55:33.669598Z"},"content_sha256":"6ef85ae1cf7186466e3eb1a3e6ebe1f192665f65bf9c7ed6f9b43a0aa330792b","schema_version":"1.0","event_id":"sha256:6ef85ae1cf7186466e3eb1a3e6ebe1f192665f65bf9c7ed6f9b43a0aa330792b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WBOCGK55QSQHIDW3BY7ZUWNQNF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bocheng Zou, Hongsheng Li, Peng Gao, Ruichuan An, Shanghang Zhang, Siyuan Huang, Weifeng Lin, Xinyu Wei, Yulin Luo","submitted_at":"2024-03-29T16:26:20Z","abstract_excerpt":"In this paper, we present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs). Visual prompts allow users to interact through multi-modal instructions, enhancing the models' interactivity and fine-grained image comprehension. In this framework, we propose a general architecture adaptable to different pre-trained MLLMs, enabling it to recognize various types of visual prompts (such as points, bounding boxes, and free-form shapes) alongside language understanding. Additionally, we introduce MDVP-I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20271","kind":"arxiv","version":3},"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/2403.20271/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":"2026-07-05T10:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9LYoXlg24AeIYEjm/UK0NTeQlTZHR57YW5nl9HBLP1tjWzvhpI5zNZ0ZDRfdyhUkOuOOC84o3PCiSVmv7b2LDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T20:55:33.670108Z"},"content_sha256":"abf87a0b209bc7373357f93995fa4c2aa51c4beab84f74f5628a0d2865572480","schema_version":"1.0","event_id":"sha256:abf87a0b209bc7373357f93995fa4c2aa51c4beab84f74f5628a0d2865572480"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/bundle.json","state_url":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/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":"2026-08-08T20:55:33Z","links":{"resolver":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF","bundle":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/bundle.json","state":"https://pith.science/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBOCGK55QSQHIDW3BY7ZUWNQNF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WBOCGK55QSQHIDW3BY7ZUWNQNF","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":"775db813b1c577354b8423eadcdce0eff1100281b017220a78ef01c5f30246cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T16:26:20Z","title_canon_sha256":"9b2d57aca6d574777347802df8b9caa2dbed3dc68b4489b8f83896f5e840d796"},"schema_version":"1.0","source":{"id":"2403.20271","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.20271","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2403.20271v3","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.20271","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"WBOCGK55QSQH","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"WBOCGK55QSQHIDW3","created_at":"2026-07-05T10:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"WBOCGK55","created_at":"2026-07-05T10:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:abf87a0b209bc7373357f93995fa4c2aa51c4beab84f74f5628a0d2865572480","target":"graph","created_at":"2026-07-05T10:18:08Z","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/2403.20271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present the Draw-and-Understand framework, exploring how to integrate visual prompting understanding capabilities into Multimodal Large Language Models (MLLMs). Visual prompts allow users to interact through multi-modal instructions, enhancing the models' interactivity and fine-grained image comprehension. In this framework, we propose a general architecture adaptable to different pre-trained MLLMs, enabling it to recognize various types of visual prompts (such as points, bounding boxes, and free-form shapes) alongside language understanding. Additionally, we introduce MDVP-I","authors_text":"Bocheng Zou, Hongsheng Li, Peng Gao, Ruichuan An, Shanghang Zhang, Siyuan Huang, Weifeng Lin, Xinyu Wei, Yulin Luo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T16:26:20Z","title":"Draw-and-Understand: Leveraging Visual Prompts to Enable MLLMs to Comprehend What You Want"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.20271","kind":"arxiv","version":3},"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":"sha256:6ef85ae1cf7186466e3eb1a3e6ebe1f192665f65bf9c7ed6f9b43a0aa330792b","target":"record","created_at":"2026-07-05T10:18:08Z","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":"775db813b1c577354b8423eadcdce0eff1100281b017220a78ef01c5f30246cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T16:26:20Z","title_canon_sha256":"9b2d57aca6d574777347802df8b9caa2dbed3dc68b4489b8f83896f5e840d796"},"schema_version":"1.0","source":{"id":"2403.20271","kind":"arxiv","version":3}},"canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b05c232bbd84a0740edb0e3f9a59b0694b997c3a8062859973861ac35c1ba3ec","first_computed_at":"2026-07-05T10:18:08.193499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:08.193499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yRpBu9VhObd2I0byq0DnU5qmUsdD7xbYUCt4rREAEKPcWpM/iF4MF5pCxkJ9pw+WR6T7DaD/a/F1W2XGXwHRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:08.193958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.20271","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ef85ae1cf7186466e3eb1a3e6ebe1f192665f65bf9c7ed6f9b43a0aa330792b","sha256:abf87a0b209bc7373357f93995fa4c2aa51c4beab84f74f5628a0d2865572480"],"state_sha256":"fc78bea9d1c47fcd5b8be86863d5a756b3c990702fbbcf95c8c9158dee10d9ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPAqWgYVmAkTFNOUypaWTmjo3W2ryBZJ+v3OrekJ8gyDcc+e4rOQheap0//820vUELnEU1mxpe+eERPKMdkqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T20:55:33.681436Z","bundle_sha256":"79e12f2a69c6e77bf135135e71c01e760c054b28c0509806c1341773a3a565fa"}}