{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:T5OX6OTRV7F6VKYOBIYLCODWSY","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":"2830a7f07f654e2ef3ab953735ae3905bc8de21c1f8b9fbd621302bad594ba56","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:56Z","title_canon_sha256":"9e9e37a78307d7f8732ca1b8f4354906dcd44efe3be4fb7fa07901abc1369cfb"},"schema_version":"1.0","source":{"id":"2312.00784","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.00784","created_at":"2026-07-05T08:12:46Z"},{"alias_kind":"arxiv_version","alias_value":"2312.00784v2","created_at":"2026-07-05T08:12:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00784","created_at":"2026-07-05T08:12:46Z"},{"alias_kind":"pith_short_12","alias_value":"T5OX6OTRV7F6","created_at":"2026-07-05T08:12:46Z"},{"alias_kind":"pith_short_16","alias_value":"T5OX6OTRV7F6VKYO","created_at":"2026-07-05T08:12:46Z"},{"alias_kind":"pith_short_8","alias_value":"T5OX6OTR","created_at":"2026-07-05T08:12:46Z"}],"graph_snapshots":[{"event_id":"sha256:1363f4a1aeca672c79b7715bcec421b8d6fcf504462375d8782e5dccc9f70854","target":"graph","created_at":"2026-07-05T08:12:46Z","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/2312.00784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide a user-friendly interface for visual prompting. To address this challenge, we introduce a novel multimodal model capable of decoding arbitrary visual prompts. This allows users to intuitively mark images and interact with the model using natural cues like a \"red bounding box\" or \"pointed arrow\". Our simple design directly overlays visual markers o","authors_text":"Dennis Park, Gregory P. Meyer, Haotian Liu, Mu Cai, Siva Karthik Mustikovela, Yong Jae Lee, Yuning Chai","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:56Z","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00784","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":"sha256:3304c76b3c59df638376858a05a509a86643d1de6b13f546c2a0e5b5943ad469","target":"record","created_at":"2026-07-05T08:12:46Z","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":"2830a7f07f654e2ef3ab953735ae3905bc8de21c1f8b9fbd621302bad594ba56","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:56Z","title_canon_sha256":"9e9e37a78307d7f8732ca1b8f4354906dcd44efe3be4fb7fa07901abc1369cfb"},"schema_version":"1.0","source":{"id":"2312.00784","kind":"arxiv","version":2}},"canonical_sha256":"9f5d7f3a71afcbeaab0e0a30b138769611431543bb6aa1c89c33642609a8aa61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f5d7f3a71afcbeaab0e0a30b138769611431543bb6aa1c89c33642609a8aa61","first_computed_at":"2026-07-05T08:12:46.607352Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:46.607352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+IC6mLdC4s50EmtrXPO1m+XV6SUR6EV06vSOYL+JdNY+wWFDgNjkjriIqBg/nezrulVNGa97qNOIoUXZrEPpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:46.607852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.00784","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3304c76b3c59df638376858a05a509a86643d1de6b13f546c2a0e5b5943ad469","sha256:1363f4a1aeca672c79b7715bcec421b8d6fcf504462375d8782e5dccc9f70854"],"state_sha256":"8e118687f5ce3ce220e1dc0ad069145a5d7f95c7cf1b09cc63a0b3d2b1f444e1"}