{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SVP4GZ7LGVI4EBBUGNJT5D4G5K","short_pith_number":"pith:SVP4GZ7L","schema_version":"1.0","canonical_sha256":"955fc367eb3551c2043433533e8f86eaaf94fe99c175b2e574782e135610d887","source":{"kind":"arxiv","id":"2311.07574","version":2},"attestation_state":"computed","paper":{"title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo He, Junke Wang, Lingchen Meng, Yu-Gang Jiang, Zejia Weng, Zuxuan Wu","submitted_at":"2023-11-13T18:59:31Z","abstract_excerpt":"Existing visual instruction tuning methods typically prompt large language models with textual descriptions to generate instruction-following data. Despite the promising performance achieved, these descriptions are derived from image annotations, which are oftentimes coarse-grained. Furthermore, the instructions might even contradict the visual content without observing the entire visual context. To address this challenge, we introduce a fine-grained visual instruction dataset, LVIS-Instruct4V, which contains 220K visually aligned and context-aware instructions produced by prompting the powerf"},"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":"2311.07574","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-13T18:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"aad59ecce37cb86b27232fb7a421ea4f041be25bd8d8632a3190218ee62bb617","abstract_canon_sha256":"a251f95707be0a89b30b584d194f31294684b3d919e43ee3994a1e032e522d6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:12.571208Z","signature_b64":"PmbhbTo5zKjPMd+cJ29Za3jEA85NDoffQ0Akf2Dtw/fdtzQkliG+iOoGl2uCEdK6sLCKSTEq0W+tKYO6ZVdVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"955fc367eb3551c2043433533e8f86eaaf94fe99c175b2e574782e135610d887","last_reissued_at":"2026-07-05T07:18:12.570665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:12.570665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo He, Junke Wang, Lingchen Meng, Yu-Gang Jiang, Zejia Weng, Zuxuan Wu","submitted_at":"2023-11-13T18:59:31Z","abstract_excerpt":"Existing visual instruction tuning methods typically prompt large language models with textual descriptions to generate instruction-following data. Despite the promising performance achieved, these descriptions are derived from image annotations, which are oftentimes coarse-grained. Furthermore, the instructions might even contradict the visual content without observing the entire visual context. To address this challenge, we introduce a fine-grained visual instruction dataset, LVIS-Instruct4V, which contains 220K visually aligned and context-aware instructions produced by prompting the powerf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07574","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/2311.07574/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":"2311.07574","created_at":"2026-07-05T07:18:12.570723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07574v2","created_at":"2026-07-05T07:18:12.570723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07574","created_at":"2026-07-05T07:18:12.570723+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVP4GZ7LGVI4","created_at":"2026-07-05T07:18:12.570723+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVP4GZ7LGVI4EBBU","created_at":"2026-07-05T07:18:12.570723+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVP4GZ7L","created_at":"2026-07-05T07:18:12.570723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07836","citing_title":"Infinity-Parser2 Technical Report","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":264,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28551","citing_title":"DataComp-VLM: Improved Open Datasets for Vision-Language Models","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09925","citing_title":"FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2402.03766","citing_title":"MobileVLM V2: Faster and Stronger Baseline for Vision Language Model","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2501.01957","citing_title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16420","citing_title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2312.16886","citing_title":"MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices","ref_index":121,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2409.17146","citing_title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2403.20330","citing_title":"Are We on the Right Way for Evaluating Large Vision-Language Models?","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05525","citing_title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07897","citing_title":"Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":245,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K","json":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K.json","graph_json":"https://pith.science/api/pith-number/SVP4GZ7LGVI4EBBUGNJT5D4G5K/graph.json","events_json":"https://pith.science/api/pith-number/SVP4GZ7LGVI4EBBUGNJT5D4G5K/events.json","paper":"https://pith.science/paper/SVP4GZ7L"},"agent_actions":{"view_html":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K","download_json":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K.json","view_paper":"https://pith.science/paper/SVP4GZ7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07574&json=true","fetch_graph":"https://pith.science/api/pith-number/SVP4GZ7LGVI4EBBUGNJT5D4G5K/graph.json","fetch_events":"https://pith.science/api/pith-number/SVP4GZ7LGVI4EBBUGNJT5D4G5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K/action/storage_attestation","attest_author":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K/action/author_attestation","sign_citation":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K/action/citation_signature","submit_replication":"https://pith.science/pith/SVP4GZ7LGVI4EBBUGNJT5D4G5K/action/replication_record"}},"created_at":"2026-07-05T07:18:12.570723+00:00","updated_at":"2026-07-05T07:18:12.570723+00:00"}