{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T5OX6OTRV7F6VKYOBIYLCODWSY","short_pith_number":"pith:T5OX6OTR","schema_version":"1.0","canonical_sha256":"9f5d7f3a71afcbeaab0e0a30b138769611431543bb6aa1c89c33642609a8aa61","source":{"kind":"arxiv","id":"2312.00784","version":2},"attestation_state":"computed","paper":{"title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dennis Park, Gregory P. Meyer, Haotian Liu, Mu Cai, Siva Karthik Mustikovela, Yong Jae Lee, Yuning Chai","submitted_at":"2023-12-01T18:59:56Z","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"},"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":"2312.00784","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T18:59:56Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"9e9e37a78307d7f8732ca1b8f4354906dcd44efe3be4fb7fa07901abc1369cfb","abstract_canon_sha256":"2830a7f07f654e2ef3ab953735ae3905bc8de21c1f8b9fbd621302bad594ba56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:46.607852Z","signature_b64":"+IC6mLdC4s50EmtrXPO1m+XV6SUR6EV06vSOYL+JdNY+wWFDgNjkjriIqBg/nezrulVNGa97qNOIoUXZrEPpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f5d7f3a71afcbeaab0e0a30b138769611431543bb6aa1c89c33642609a8aa61","last_reissued_at":"2026-07-05T08:12:46.607352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:46.607352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dennis Park, Gregory P. Meyer, Haotian Liu, Mu Cai, Siva Karthik Mustikovela, Yong Jae Lee, Yuning Chai","submitted_at":"2023-12-01T18:59:56Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00784","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/2312.00784/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":"2312.00784","created_at":"2026-07-05T08:12:46.607413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00784v2","created_at":"2026-07-05T08:12:46.607413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00784","created_at":"2026-07-05T08:12:46.607413+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5OX6OTRV7F6","created_at":"2026-07-05T08:12:46.607413+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5OX6OTRV7F6VKYO","created_at":"2026-07-05T08:12:46.607413+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5OX6OTR","created_at":"2026-07-05T08:12:46.607413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15297","citing_title":"DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY","json":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY.json","graph_json":"https://pith.science/api/pith-number/T5OX6OTRV7F6VKYOBIYLCODWSY/graph.json","events_json":"https://pith.science/api/pith-number/T5OX6OTRV7F6VKYOBIYLCODWSY/events.json","paper":"https://pith.science/paper/T5OX6OTR"},"agent_actions":{"view_html":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY","download_json":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY.json","view_paper":"https://pith.science/paper/T5OX6OTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00784&json=true","fetch_graph":"https://pith.science/api/pith-number/T5OX6OTRV7F6VKYOBIYLCODWSY/graph.json","fetch_events":"https://pith.science/api/pith-number/T5OX6OTRV7F6VKYOBIYLCODWSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/action/storage_attestation","attest_author":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/action/author_attestation","sign_citation":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/action/citation_signature","submit_replication":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/action/replication_record"}},"created_at":"2026-07-05T08:12:46.607413+00:00","updated_at":"2026-07-05T08:12:46.607413+00:00"}