{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T3VQWH72UZ5YEDEXYY3O4UMXHC","short_pith_number":"pith:T3VQWH72","schema_version":"1.0","canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","source":{"kind":"arxiv","id":"2411.04952","version":1},"attestation_state":"computed","paper":{"title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Debanjan Mahata, Jaemin Cho, Mohit Bansal, Ozan Irsoy, Yujie He","submitted_at":"2024-11-07T18:29:38Z","abstract_excerpt":"Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rely on text-based retrieval-augmented generation (RAG) that uses text extraction tools such as optical character recognition (OCR). However, there are difficulties in applying these methods in real-world scenarios: (a) questions often require information across different pages or documents, where MLMs cannot handle many long documents; (b) documents often have important informati"},"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":"2411.04952","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T18:29:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0a98a73e60d58e98560ed00b7c8af76fd1d7a23e6aee27ffc0313aeb25fc4ac6","abstract_canon_sha256":"c6a830a1db142fcb673c7320fa018e2b818dd5940e4f2c90955c6265d77eeb6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:36.652618Z","signature_b64":"3yFs0XuJq8sVc5MY3McyBj8LJg/Ut96Y8S4vYrkuYKl23xiR3Ug7cEhosQwb3en+rar4LGf11MLG9HsZc6HqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eeb0b1ffaa67b820c97c636ee5197389e97d34d44e822dd6732efa4bcd985d9","last_reissued_at":"2026-07-05T09:32:36.651945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:36.651945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Debanjan Mahata, Jaemin Cho, Mohit Bansal, Ozan Irsoy, Yujie He","submitted_at":"2024-11-07T18:29:38Z","abstract_excerpt":"Document visual question answering (DocVQA) pipelines that answer questions from documents have broad applications. Existing methods focus on handling single-page documents with multi-modal language models (MLMs), or rely on text-based retrieval-augmented generation (RAG) that uses text extraction tools such as optical character recognition (OCR). However, there are difficulties in applying these methods in real-world scenarios: (a) questions often require information across different pages or documents, where MLMs cannot handle many long documents; (b) documents often have important informati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04952","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/2411.04952/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":"2411.04952","created_at":"2026-07-05T09:32:36.652035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04952v1","created_at":"2026-07-05T09:32:36.652035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04952","created_at":"2026-07-05T09:32:36.652035+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3VQWH72UZ5Y","created_at":"2026-07-05T09:32:36.652035+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3VQWH72UZ5YEDEX","created_at":"2026-07-05T09:32:36.652035+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3VQWH72","created_at":"2026-07-05T09:32:36.652035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23581","citing_title":"Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19960","citing_title":"Stellar: Scalable Multimodal Document Retrieval for Natural Language Queries","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08979","citing_title":"EviProp: Seeded Relevance Diffusion on Chunk-Page Graphs for Long Multimodal Document Retrieval","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07252","citing_title":"Constrained Dominant Sets for Multimodal Document Question Answering","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04240","citing_title":"Overview of the EReL@MIR 2025 Multimodal Document Retrieval Challenge (Track 1)","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14906","citing_title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","ref_index":33,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28344","citing_title":"PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29399","citing_title":"LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26122","citing_title":"DocArena: Turning Raw Documents into Controllable Training Environments for Document Search Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13415","citing_title":"Attention Grounded Enhancement for Visual Document Retrieval","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00104","citing_title":"R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09552","citing_title":"MCERF: Advancing Multimodal LLM Evaluation of Engineering Documentation with Enhanced Retrieval","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23061","citing_title":"MoDora: Tree-Based Semi-Structured Document Analysis System","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23885","citing_title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12882","citing_title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02640","citing_title":"Overcoming the \"Impracticality\" of RAG: Proposing a Real-World Benchmark and Multi-Dimensional Diagnostic Framework","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12812","citing_title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","ref_index":44,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21304","citing_title":"PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12812","citing_title":"DocSeeker: Structured Visual Reasoning with Evidence Grounding for Long Document Understanding","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07019","citing_title":"LensVLM: Selective Context Expansion for Compressed Visual Representation of Text","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC","json":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC.json","graph_json":"https://pith.science/api/pith-number/T3VQWH72UZ5YEDEXYY3O4UMXHC/graph.json","events_json":"https://pith.science/api/pith-number/T3VQWH72UZ5YEDEXYY3O4UMXHC/events.json","paper":"https://pith.science/paper/T3VQWH72"},"agent_actions":{"view_html":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC","download_json":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC.json","view_paper":"https://pith.science/paper/T3VQWH72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04952&json=true","fetch_graph":"https://pith.science/api/pith-number/T3VQWH72UZ5YEDEXYY3O4UMXHC/graph.json","fetch_events":"https://pith.science/api/pith-number/T3VQWH72UZ5YEDEXYY3O4UMXHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/action/storage_attestation","attest_author":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/action/author_attestation","sign_citation":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/action/citation_signature","submit_replication":"https://pith.science/pith/T3VQWH72UZ5YEDEXYY3O4UMXHC/action/replication_record"}},"created_at":"2026-07-05T09:32:36.652035+00:00","updated_at":"2026-07-05T09:32:36.652035+00:00"}