{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:T5OX6OTRV7F6VKYOBIYLCODWSY","short_pith_number":"pith:T5OX6OTR","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"},"canonical_sha256":"9f5d7f3a71afcbeaab0e0a30b138769611431543bb6aa1c89c33642609a8aa61","source":{"kind":"arxiv","id":"2312.00784","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:T5OX6OTRV7F6VKYOBIYLCODWSY","target":"record","payload":{"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"},"canonical_sha256":"9f5d7f3a71afcbeaab0e0a30b138769611431543bb6aa1c89c33642609a8aa61","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"},"source_kind":"arxiv","source_id":"2312.00784","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":"2026-07-05T08:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eX4vJazp5zmndzlkXqNxYCPBOm6R6fbWyHxE2IHCPPEJBL5CMnCH+3tmrsj+xhsoOEqTyAymS6kBuEgyZ4AHDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:51:10.429525Z"},"content_sha256":"3304c76b3c59df638376858a05a509a86643d1de6b13f546c2a0e5b5943ad469","schema_version":"1.0","event_id":"sha256:3304c76b3c59df638376858a05a509a86643d1de6b13f546c2a0e5b5943ad469"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:T5OX6OTRV7F6VKYOBIYLCODWSY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9UJwe7Mhohxurwhntq8LSZovoW5oYzNGrc2qPXmBqQhWUr4uyoo6ZQ3YrIoD0XqOgpp4UVIVjIjUS7HuvFoiDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:51:10.430070Z"},"content_sha256":"1363f4a1aeca672c79b7715bcec421b8d6fcf504462375d8782e5dccc9f70854","schema_version":"1.0","event_id":"sha256:1363f4a1aeca672c79b7715bcec421b8d6fcf504462375d8782e5dccc9f70854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/bundle.json","state_url":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/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":"2026-08-06T07:51:10Z","links":{"resolver":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY","bundle":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/bundle.json","state":"https://pith.science/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5OX6OTRV7F6VKYOBIYLCODWSY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"owGZZFHuvfbpoaYwm2iRFOjcYKzmwhjsFP7Itjs+ipnm847+hs6cACSbyvyNVEEnXs0xb19+YbvMBR2agRzXDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:51:10.434126Z","bundle_sha256":"c1d8c49819719fa06d756e93911f9ea5f9b2a344511c7ae00792839eafd13c56"}}