{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2XAMK6IRE5NDL2GHB2OS5RPXEA","short_pith_number":"pith:2XAMK6IR","schema_version":"1.0","canonical_sha256":"d5c0c57911275a35e8c70e9d2ec5f72035a8bc58c3aa53a7a8b0b8e15eaf5364","source":{"kind":"arxiv","id":"2307.02499","version":1},"attestation_state":"computed","paper":{"title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anwen Hu, Chenliang Li, Chenlin Zhao, Fei Huang, Guohai Xu, Haiyang Xu, Jiabo Ye, Ji Zhang, Junfeng Tian, Ming Yan, Qian Qi, Qinghao Ye, Yuhao Dan","submitted_at":"2023-07-04T11:28:07Z","abstract_excerpt":"Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs), including mPLUG-Owl, have demonstrated promising zero-shot capabilities in shallow OCR-free text recognition, indicating their potential for OCR-free document understanding. Nevertheless, without in-domain training, these models tend to ignore fine-grained OCR features, such as sophisticated tables or large blocks of text, which are essential for OCR-free document understanding. In this paper,"},"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":"2307.02499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T11:28:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"660be02768fcddfbd845514082783f256ec6745c224cdd42fbb6627eec5ffb06","abstract_canon_sha256":"eadaff09361df2302fd67597ce06f61214a6aac08478726fc88a6825f6fea7d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:20.808137Z","signature_b64":"P8QQnbCQIhMnDDfz4Z2TVdDw0rvDGkg/FMFdMgfqMAX3qzzoJ3CLME7ncoXGvXK0ixUZkEnJbKRMU+9b0LYmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c0c57911275a35e8c70e9d2ec5f72035a8bc58c3aa53a7a8b0b8e15eaf5364","last_reissued_at":"2026-07-05T06:28:20.807595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:20.807595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anwen Hu, Chenliang Li, Chenlin Zhao, Fei Huang, Guohai Xu, Haiyang Xu, Jiabo Ye, Ji Zhang, Junfeng Tian, Ming Yan, Qian Qi, Qinghao Ye, Yuhao Dan","submitted_at":"2023-07-04T11:28:07Z","abstract_excerpt":"Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs), including mPLUG-Owl, have demonstrated promising zero-shot capabilities in shallow OCR-free text recognition, indicating their potential for OCR-free document understanding. Nevertheless, without in-domain training, these models tend to ignore fine-grained OCR features, such as sophisticated tables or large blocks of text, which are essential for OCR-free document understanding. In this paper,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02499","kind":"arxiv","version":1},"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/2307.02499/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":"2307.02499","created_at":"2026-07-05T06:28:20.807662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02499v1","created_at":"2026-07-05T06:28:20.807662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02499","created_at":"2026-07-05T06:28:20.807662+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XAMK6IRE5ND","created_at":"2026-07-05T06:28:20.807662+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XAMK6IRE5NDL2GH","created_at":"2026-07-05T06:28:20.807662+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XAMK6IR","created_at":"2026-07-05T06:28:20.807662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25343","citing_title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17030","citing_title":"Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24530","citing_title":"Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document Retrieval","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25343","citing_title":"Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.14061","citing_title":"LLM Agents Can See Code Repositories","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05970","citing_title":"PDF-WuKong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2503.14075","citing_title":"Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":5,"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":65,"is_internal_anchor":false},{"citing_arxiv_id":"2510.15253","citing_title":"Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04257","citing_title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01704","citing_title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","ref_index":49,"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":31,"is_internal_anchor":false},{"citing_arxiv_id":"2410.10594","citing_title":"VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12937","citing_title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02880","citing_title":"InstructTable: Improving Table Structure Recognition Through Instructions","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12812","citing_title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12812","citing_title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11042","citing_title":"Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04380","citing_title":"CPT: Controllable and Editable Design Variations with Language Models","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA","json":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA.json","graph_json":"https://pith.science/api/pith-number/2XAMK6IRE5NDL2GHB2OS5RPXEA/graph.json","events_json":"https://pith.science/api/pith-number/2XAMK6IRE5NDL2GHB2OS5RPXEA/events.json","paper":"https://pith.science/paper/2XAMK6IR"},"agent_actions":{"view_html":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA","download_json":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA.json","view_paper":"https://pith.science/paper/2XAMK6IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02499&json=true","fetch_graph":"https://pith.science/api/pith-number/2XAMK6IRE5NDL2GHB2OS5RPXEA/graph.json","fetch_events":"https://pith.science/api/pith-number/2XAMK6IRE5NDL2GHB2OS5RPXEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA/action/storage_attestation","attest_author":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA/action/author_attestation","sign_citation":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA/action/citation_signature","submit_replication":"https://pith.science/pith/2XAMK6IRE5NDL2GHB2OS5RPXEA/action/replication_record"}},"created_at":"2026-07-05T06:28:20.807662+00:00","updated_at":"2026-07-05T06:28:20.807662+00:00"}