{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JOXEDJ3GDSO56UZ4E5HF2WALVH","short_pith_number":"pith:JOXEDJ3G","schema_version":"1.0","canonical_sha256":"4bae41a7661c9ddf533c274e5d580ba9fecfd05477c11ac07991166ff0671c1d","source":{"kind":"arxiv","id":"2306.17107","version":2},"attestation_state":"computed","paper":{"title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Diyi Yang, Jiuxiang Gu, Nedim Lipka, Ruiyi Zhang, Tong Sun, Yanzhe Zhang, Yufan Zhou","submitted_at":"2023-06-29T17:08:16Z","abstract_excerpt":"Instruction tuning unlocks the superior capability of Large Language Models (LLM) to interact with humans. Furthermore, recent instruction-following datasets include images as visual inputs, collecting responses for image-based instructions. However, visual instruction-tuned models cannot comprehend textual details within images well. This work enhances the current visual instruction tuning pipeline with text-rich images (e.g., movie posters, book covers, etc.). Specifically, we first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. Moreover,"},"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":"2306.17107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-29T17:08:16Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6951ae9cad2a196cd709fd2c49d51553a366a9588fac3c35f451f87304220ac4","abstract_canon_sha256":"b9860f49ee77825cee7b0e7e3a2754e0be9925d5e88cabf96b47834674fbdf47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:54.754956Z","signature_b64":"qK2sR3vX8V4IMCc7H1oYAUap3RPcYmIxs1zvqLNwVQ2S5aw8NxlLZ5ZECEBkUMkqzC67TojFlWQkDTlNs8+3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bae41a7661c9ddf533c274e5d580ba9fecfd05477c11ac07991166ff0671c1d","last_reissued_at":"2026-07-05T07:40:54.754481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:54.754481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Diyi Yang, Jiuxiang Gu, Nedim Lipka, Ruiyi Zhang, Tong Sun, Yanzhe Zhang, Yufan Zhou","submitted_at":"2023-06-29T17:08:16Z","abstract_excerpt":"Instruction tuning unlocks the superior capability of Large Language Models (LLM) to interact with humans. Furthermore, recent instruction-following datasets include images as visual inputs, collecting responses for image-based instructions. However, visual instruction-tuned models cannot comprehend textual details within images well. This work enhances the current visual instruction tuning pipeline with text-rich images (e.g., movie posters, book covers, etc.). Specifically, we first use publicly available OCR tools to collect results on 422K text-rich images from the LAION dataset. Moreover,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17107","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/2306.17107/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":"2306.17107","created_at":"2026-07-05T07:40:54.754546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17107v2","created_at":"2026-07-05T07:40:54.754546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17107","created_at":"2026-07-05T07:40:54.754546+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOXEDJ3GDSO5","created_at":"2026-07-05T07:40:54.754546+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOXEDJ3GDSO56UZ4","created_at":"2026-07-05T07:40:54.754546+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOXEDJ3G","created_at":"2026-07-05T07:40:54.754546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26287","citing_title":"GeMoE: Gating Entropy is All You Need for Uncertainty-aware Adaptive Routing in MoE-based Large Vision-Language Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":228,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09132","citing_title":"Vision Language Model Helps Private Information De-Identification in Vision Data","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07289","citing_title":"Closed-Form Spectral Regularization for Multi-Task Model Merging","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2308.12067","citing_title":"MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04468","citing_title":"NVILA: Efficient Frontier Visual Language Models","ref_index":115,"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":80,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17726","citing_title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09861","citing_title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00321","citing_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2310.14566","citing_title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":149,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03726","citing_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2403.04652","citing_title":"Yi: Open Foundation Models by 01.AI","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03426","citing_title":"Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00877","citing_title":"OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01800","citing_title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","ref_index":118,"is_internal_anchor":false},{"citing_arxiv_id":"2408.03326","citing_title":"LLaVA-OneVision: Easy Visual Task Transfer","ref_index":168,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH","json":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH.json","graph_json":"https://pith.science/api/pith-number/JOXEDJ3GDSO56UZ4E5HF2WALVH/graph.json","events_json":"https://pith.science/api/pith-number/JOXEDJ3GDSO56UZ4E5HF2WALVH/events.json","paper":"https://pith.science/paper/JOXEDJ3G"},"agent_actions":{"view_html":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH","download_json":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH.json","view_paper":"https://pith.science/paper/JOXEDJ3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17107&json=true","fetch_graph":"https://pith.science/api/pith-number/JOXEDJ3GDSO56UZ4E5HF2WALVH/graph.json","fetch_events":"https://pith.science/api/pith-number/JOXEDJ3GDSO56UZ4E5HF2WALVH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH/action/storage_attestation","attest_author":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH/action/author_attestation","sign_citation":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH/action/citation_signature","submit_replication":"https://pith.science/pith/JOXEDJ3GDSO56UZ4E5HF2WALVH/action/replication_record"}},"created_at":"2026-07-05T07:40:54.754546+00:00","updated_at":"2026-07-05T07:40:54.754546+00:00"}