{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WH5A5AIZS4TBIJW4JI2HLS2I4D","short_pith_number":"pith:WH5A5AIZ","schema_version":"1.0","canonical_sha256":"b1fa0e811997261426dc4a3475cb48e0c6deb94d76109c63935a1c785c05d9a0","source":{"kind":"arxiv","id":"2503.13964","version":1},"attestation_state":"computed","paper":{"title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongtu Zhu, Huaxiu Yao, Peng Xia, Ruiyi Zhang, Siwei Han, Tong Sun, Yun Li","submitted_at":"2025-03-18T06:57:21Z","abstract_excerpt":"Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single modal, failing to effectively integrate textual and visual cues. These approaches struggle with complex multi-modal reasoning, limiting their performance on real-world documents. We present MDocAgent (A Multi-Modal Multi-Agent Framework for Document Understanding), a novel RAG and multi-agent framework that leverages both text and image. Our system employs five s"},"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":"2503.13964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-18T06:57:21Z","cross_cats_sorted":[],"title_canon_sha256":"8fe8a47991f4e26798f5eb6b904580669fb57ae35de2a116f470838b154926a7","abstract_canon_sha256":"d26d0abac586edafd041eb10668a422efeb9f7d60b6c2150d6262079766335cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:51.648534Z","signature_b64":"GJIpBzEP6HBBeP3pm9A+NyphKIZYZK/EyL3N/X+fdkOq/mJKzFmiFRlJC/ZaUAHZzZi1vgegN4UNBPQeHlSrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1fa0e811997261426dc4a3475cb48e0c6deb94d76109c63935a1c785c05d9a0","last_reissued_at":"2026-07-05T10:33:51.647907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:51.647907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hongtu Zhu, Huaxiu Yao, Peng Xia, Ruiyi Zhang, Siwei Han, Tong Sun, Yun Li","submitted_at":"2025-03-18T06:57:21Z","abstract_excerpt":"Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single modal, failing to effectively integrate textual and visual cues. These approaches struggle with complex multi-modal reasoning, limiting their performance on real-world documents. We present MDocAgent (A Multi-Modal Multi-Agent Framework for Document Understanding), a novel RAG and multi-agent framework that leverages both text and image. Our system employs five s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13964","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/2503.13964/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":"2503.13964","created_at":"2026-07-05T10:33:51.647977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13964v1","created_at":"2026-07-05T10:33:51.647977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13964","created_at":"2026-07-05T10:33:51.647977+00:00"},{"alias_kind":"pith_short_12","alias_value":"WH5A5AIZS4TB","created_at":"2026-07-05T10:33:51.647977+00:00"},{"alias_kind":"pith_short_16","alias_value":"WH5A5AIZS4TBIJW4","created_at":"2026-07-05T10:33:51.647977+00:00"},{"alias_kind":"pith_short_8","alias_value":"WH5A5AIZ","created_at":"2026-07-05T10:33:51.647977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08979","citing_title":"EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29648","citing_title":"Hybrid Retriever Evolution for Multimodal Document Reasoning Agents","ref_index":3,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13213","citing_title":"Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22281","citing_title":"DocPrune:Efficient Document Question Answering via Background, Question, and Comprehension-aware Token Pruning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D","json":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D.json","graph_json":"https://pith.science/api/pith-number/WH5A5AIZS4TBIJW4JI2HLS2I4D/graph.json","events_json":"https://pith.science/api/pith-number/WH5A5AIZS4TBIJW4JI2HLS2I4D/events.json","paper":"https://pith.science/paper/WH5A5AIZ"},"agent_actions":{"view_html":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D","download_json":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D.json","view_paper":"https://pith.science/paper/WH5A5AIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13964&json=true","fetch_graph":"https://pith.science/api/pith-number/WH5A5AIZS4TBIJW4JI2HLS2I4D/graph.json","fetch_events":"https://pith.science/api/pith-number/WH5A5AIZS4TBIJW4JI2HLS2I4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D/action/storage_attestation","attest_author":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D/action/author_attestation","sign_citation":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D/action/citation_signature","submit_replication":"https://pith.science/pith/WH5A5AIZS4TBIJW4JI2HLS2I4D/action/replication_record"}},"created_at":"2026-07-05T10:33:51.647977+00:00","updated_at":"2026-07-05T10:33:51.647977+00:00"}