{"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"}