{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:M7O6VYPDPF5PNQIXIFQQ2VGM7X","short_pith_number":"pith:M7O6VYPD","canonical_record":{"source":{"id":"2312.14135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:55:06Z","cross_cats_sorted":[],"title_canon_sha256":"af4f4f786b4e30bf44b3095475f0584850633866730bf6dfd73a142fb0af8da2","abstract_canon_sha256":"381044713e83d04b261db987328d60ac004ad952d3be9c81b2870df5a3d05893"},"schema_version":"1.0"},"canonical_sha256":"67ddeae1e3797af6c11741610d54ccfdf8aae9316906f50aa6c49809ef4a022f","source":{"kind":"arxiv","id":"2312.14135","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14135","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14135v2","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14135","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"pith_short_12","alias_value":"M7O6VYPDPF5P","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"pith_short_16","alias_value":"M7O6VYPDPF5PNQIX","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"pith_short_8","alias_value":"M7O6VYPD","created_at":"2026-07-05T07:27:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:M7O6VYPDPF5PNQIXIFQQ2VGM7X","target":"record","payload":{"canonical_record":{"source":{"id":"2312.14135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:55:06Z","cross_cats_sorted":[],"title_canon_sha256":"af4f4f786b4e30bf44b3095475f0584850633866730bf6dfd73a142fb0af8da2","abstract_canon_sha256":"381044713e83d04b261db987328d60ac004ad952d3be9c81b2870df5a3d05893"},"schema_version":"1.0"},"canonical_sha256":"67ddeae1e3797af6c11741610d54ccfdf8aae9316906f50aa6c49809ef4a022f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:55.330696Z","signature_b64":"qVzGP3wvdX15Z67QVdsUuuyY4E1HML4IED8CJbWHeR8F560SFgAenFnzipvnPAeeiskKg2j0zy4C7+vQc94MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ddeae1e3797af6c11741610d54ccfdf8aae9316906f50aa6c49809ef4a022f","last_reissued_at":"2026-07-05T07:27:55.330144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:55.330144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.14135","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":"2026-07-05T07:27:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+BAP6FDAZ2k+FgG6VgF7eNHFhvQczEz+YPbxrIUlIlsLPWGm1ZexFNqdzSHWJBtX678bkNIzoSUUZPiT5RTsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:17:54.895623Z"},"content_sha256":"788dcaa9e841c4ac43fc6f1f0667440f0fbc77220af0b8db0fbb5ab657326bd1","schema_version":"1.0","event_id":"sha256:788dcaa9e841c4ac43fc6f1f0667440f0fbc77220af0b8db0fbb5ab657326bd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:M7O6VYPDPF5PNQIXIFQQ2VGM7X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Penghao Wu, Saining Xie","submitted_at":"2023-12-21T18:55:06Z","abstract_excerpt":"When we look around and perform complex tasks, how we see and selectively process what we see is crucial. However, the lack of this visual search mechanism in current multimodal LLMs (MLLMs) hinders their ability to focus on important visual details, especially when handling high-resolution and visually crowded images. To address this, we introduce V*, an LLM-guided visual search mechanism that employs the world knowledge in LLMs for efficient visual querying. When combined with an MLLM, this mechanism enhances collaborative reasoning, contextual understanding, and precise targeting of specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14135","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/2312.14135/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":"2026-07-05T07:27:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"faZPhXk2iSgbyzNVJJAqtkzUcY+IgY9BkxQ1j6Y4OFezYMLiHU9K/ldeL1ekc95bk5DCoCFF209Q2n7K6fSICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:17:54.896123Z"},"content_sha256":"226a90c6c05f56b2cf21f8c05f66dcafbe854f65fabe1b4684d1a6ecdf63f875","schema_version":"1.0","event_id":"sha256:226a90c6c05f56b2cf21f8c05f66dcafbe854f65fabe1b4684d1a6ecdf63f875"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X/bundle.json","state_url":"https://pith.science/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X/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":"2026-08-05T15:17:54Z","links":{"resolver":"https://pith.science/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X","bundle":"https://pith.science/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X/bundle.json","state":"https://pith.science/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7O6VYPDPF5PNQIXIFQQ2VGM7X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:M7O6VYPDPF5PNQIXIFQQ2VGM7X","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":"381044713e83d04b261db987328d60ac004ad952d3be9c81b2870df5a3d05893","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:55:06Z","title_canon_sha256":"af4f4f786b4e30bf44b3095475f0584850633866730bf6dfd73a142fb0af8da2"},"schema_version":"1.0","source":{"id":"2312.14135","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.14135","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"arxiv_version","alias_value":"2312.14135v2","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.14135","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"pith_short_12","alias_value":"M7O6VYPDPF5P","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"pith_short_16","alias_value":"M7O6VYPDPF5PNQIX","created_at":"2026-07-05T07:27:55Z"},{"alias_kind":"pith_short_8","alias_value":"M7O6VYPD","created_at":"2026-07-05T07:27:55Z"}],"graph_snapshots":[{"event_id":"sha256:226a90c6c05f56b2cf21f8c05f66dcafbe854f65fabe1b4684d1a6ecdf63f875","target":"graph","created_at":"2026-07-05T07:27:55Z","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/2312.14135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When we look around and perform complex tasks, how we see and selectively process what we see is crucial. However, the lack of this visual search mechanism in current multimodal LLMs (MLLMs) hinders their ability to focus on important visual details, especially when handling high-resolution and visually crowded images. To address this, we introduce V*, an LLM-guided visual search mechanism that employs the world knowledge in LLMs for efficient visual querying. When combined with an MLLM, this mechanism enhances collaborative reasoning, contextual understanding, and precise targeting of specifi","authors_text":"Penghao Wu, Saining Xie","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:55:06Z","title":"V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.14135","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":"sha256:788dcaa9e841c4ac43fc6f1f0667440f0fbc77220af0b8db0fbb5ab657326bd1","target":"record","created_at":"2026-07-05T07:27:55Z","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":"381044713e83d04b261db987328d60ac004ad952d3be9c81b2870df5a3d05893","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T18:55:06Z","title_canon_sha256":"af4f4f786b4e30bf44b3095475f0584850633866730bf6dfd73a142fb0af8da2"},"schema_version":"1.0","source":{"id":"2312.14135","kind":"arxiv","version":2}},"canonical_sha256":"67ddeae1e3797af6c11741610d54ccfdf8aae9316906f50aa6c49809ef4a022f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67ddeae1e3797af6c11741610d54ccfdf8aae9316906f50aa6c49809ef4a022f","first_computed_at":"2026-07-05T07:27:55.330144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:55.330144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qVzGP3wvdX15Z67QVdsUuuyY4E1HML4IED8CJbWHeR8F560SFgAenFnzipvnPAeeiskKg2j0zy4C7+vQc94MDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:55.330696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.14135","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:788dcaa9e841c4ac43fc6f1f0667440f0fbc77220af0b8db0fbb5ab657326bd1","sha256:226a90c6c05f56b2cf21f8c05f66dcafbe854f65fabe1b4684d1a6ecdf63f875"],"state_sha256":"4884b20d0d97a1e1e5f1e2c772734c1f31a2c7e731d82da444be6e3d4fe20150"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZKmnQGJzioOjYUztHw8eV/kbtsnnQQkdTTPV5UiS8AxUChMAMJphTHcShUtDVXnykWiZYc15k4iL3GwohLVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:17:54.899840Z","bundle_sha256":"329449ee813a746e98a1d269c5300c74e12c8435b57aef91a779f176245cba31"}}