{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XFMCH2AC4HGE6PVO3NJHRFWJ3C","short_pith_number":"pith:XFMCH2AC","schema_version":"1.0","canonical_sha256":"b95823e802e1cc4f3eaedb527896c9d8ad685b09e125b553c5dd36f781fada47","source":{"kind":"arxiv","id":"2409.02813","version":3},"attestation_state":"computed","paper":{"title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multimodal models show 17 to 27 percent lower accuracy on MMMU-Pro than on MMMU.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Botao Yu, Ge Zhang, Graham Neubig, Huan Sun, Kai Zhang, Shengbang Tong, Tianyu Zheng, Wenhu Chen, Xiang Yue, Yuansheng Ni, Yubo Wang, Yu Su, Yuxuan Sun","submitted_at":"2024-09-04T15:31:26Z","abstract_excerpt":"This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal models' true understanding and reasoning capabilities through a three-step process based on MMMU: (1) filtering out questions answerable by text-only models, (2) augmenting candidate options, and (3) introducing a vision-only input setting where questions are embedded within images. This setting challenges AI to truly \"see\" and \"read\" simultaneously, testing a fundamental human cognitive skill of seamlessly integrating"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.02813","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T15:31:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"65f7013ef12de1a9b7bc90dab017a73fc9dd8b5e2b271edadf5a123aaa6ccbc0","abstract_canon_sha256":"03fddb64137f7efda7b707f3951553b297797400c7bc0d5b2d748cd0b5e97744"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:12:35.516039Z","signature_b64":"cjlAREPlXZLn40sJgvGWeKyOzojfAA41gda4C7KPcYHF+Jx4xMswebdZK5Hbvv/V/uXEryFOIXojIuc/9sPVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b95823e802e1cc4f3eaedb527896c9d8ad685b09e125b553c5dd36f781fada47","last_reissued_at":"2026-05-18T03:12:35.515185Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:12:35.515185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multimodal models show 17 to 27 percent lower accuracy on MMMU-Pro than on MMMU.","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Botao Yu, Ge Zhang, Graham Neubig, Huan Sun, Kai Zhang, Shengbang Tong, Tianyu Zheng, Wenhu Chen, Xiang Yue, Yuansheng Ni, Yubo Wang, Yu Su, Yuxuan Sun","submitted_at":"2024-09-04T15:31:26Z","abstract_excerpt":"This paper introduces MMMU-Pro, a robust version of the Massive Multi-discipline Multimodal Understanding and Reasoning (MMMU) benchmark. MMMU-Pro rigorously assesses multimodal models' true understanding and reasoning capabilities through a three-step process based on MMMU: (1) filtering out questions answerable by text-only models, (2) augmenting candidate options, and (3) introducing a vision-only input setting where questions are embedded within images. This setting challenges AI to truly \"see\" and \"read\" simultaneously, testing a fundamental human cognitive skill of seamlessly integrating"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results show that model performance is substantially lower on MMMU-Pro than on MMMU, ranging from 16.8% to 26.9% across models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that questions solvable by text-only models require no visual understanding and that embedding questions in images cleanly tests seamless visual-textual integration without introducing new confounds or biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal models show 17 to 27 percent lower accuracy on MMMU-Pro than on MMMU.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a3977abe5b8b889b88d2a55b779339683307583cf28d62d0b016d5a6cb4fe83f"},"source":{"id":"2409.02813","kind":"arxiv","version":3},"verdict":{"id":"95cb3904-d6dd-435d-a5a5-e384df4cfa8d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T00:45:48.228603Z","strongest_claim":"Results show that model performance is substantially lower on MMMU-Pro than on MMMU, ranging from 16.8% to 26.9% across models.","one_line_summary":"MMMU-Pro is a stricter multimodal benchmark that removes text-only solvable questions, augments options, and requires reading text from images, yielding substantially lower model scores of 16.8-26.9%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that questions solvable by text-only models require no visual understanding and that embedding questions in images cleanly tests seamless visual-textual integration without introducing new confounds or biases.","pith_extraction_headline":"Multimodal models show 17 to 27 percent lower accuracy on MMMU-Pro than on MMMU."},"references":{"count":73,"sample":[{"doi":"","year":2024,"title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","work_id":"feef9556-a016-493c-abd2-0c97a23a7ebf","ref_index":1,"cited_arxiv_id":"2404.14219","is_internal_anchor":true},{"doi":"","year":2022,"title":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model","work_id":"6b329e9b-8d3c-474e-ac3e-7f0faf71a56e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Anthropic. 2024. https://www.anthropic.com/news/claude-3-5-sonnet Claude 3.5 sonnet. https://www.anthropic.com/news/claude-3-5-sonnet","work_id":"96b9c6f9-1b0f-4ba0-8672-291abf39729a","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/iccv.2015.279","year":2015,"title":"Lawrence Zitnick, and Devi Parikh","work_id":"acf6495e-ae4c-4644-a52d-ff5e1c2ca351","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","work_id":"87bfa84a-e663-4165-806f-93ef439d88d0","ref_index":5,"cited_arxiv_id":"2308.01390","is_internal_anchor":true}],"resolved_work":73,"snapshot_sha256":"58820cbc906ff527e64ce8277deef03a21627afc9ebe631942072f2079f71631","internal_anchors":24},"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":"2409.02813","created_at":"2026-05-18T03:12:35.515334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02813v3","created_at":"2026-05-18T03:12:35.515334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02813","created_at":"2026-05-18T03:12:35.515334+00:00"},{"alias_kind":"pith_short_12","alias_value":"XFMCH2AC4HGE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"XFMCH2AC4HGE6PVO","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"XFMCH2AC","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":39,"internal_anchor_count":39,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":242,"is_internal_anchor":true},{"citing_arxiv_id":"2502.13923","citing_title":"Qwen2.5-VL Technical Report","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2505.16416","citing_title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16517","citing_title":"Customizing an LLM for Enterprise Software Engineering","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15777","citing_title":"SaaS-Bench: Can Computer-Use Agents Leverage Real-World SaaS to Solve Professional Workflows?","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15951","citing_title":"From Failure to Feedback: Group Revision Unlocks Hard Cases in Object-Level Grounding","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16517","citing_title":"Customizing an LLM for Enterprise Software Engineering","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19726","citing_title":"Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2503.17352","citing_title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2507.06448","citing_title":"Perception-Aware Policy Optimization for Multimodal Reasoning","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2508.19652","citing_title":"Self-Rewarding Vision-Language Model via Reasoning Decomposition","ref_index":27,"is_internal_anchor":true},{"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":133,"is_internal_anchor":true},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":112,"is_internal_anchor":true},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2501.08313","citing_title":"MiniMax-01: Scaling Foundation Models with Lightning Attention","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12034","citing_title":"Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27389","citing_title":"COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2501.13826","citing_title":"Video-MMMU: Evaluating Knowledge Acquisition from Multi-Discipline Professional Videos","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12034","citing_title":"Boosting Omni-Modal Language Models: Staged Post-Training with Visually Debiased Evaluation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11629","citing_title":"OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27083","citing_title":"Co-Evolving Policy Distillation","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27389","citing_title":"COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09614","citing_title":"Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2503.01743","citing_title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C","json":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C.json","graph_json":"https://pith.science/api/pith-number/XFMCH2AC4HGE6PVO3NJHRFWJ3C/graph.json","events_json":"https://pith.science/api/pith-number/XFMCH2AC4HGE6PVO3NJHRFWJ3C/events.json","paper":"https://pith.science/paper/XFMCH2AC"},"agent_actions":{"view_html":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C","download_json":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C.json","view_paper":"https://pith.science/paper/XFMCH2AC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02813&json=true","fetch_graph":"https://pith.science/api/pith-number/XFMCH2AC4HGE6PVO3NJHRFWJ3C/graph.json","fetch_events":"https://pith.science/api/pith-number/XFMCH2AC4HGE6PVO3NJHRFWJ3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C/action/storage_attestation","attest_author":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C/action/author_attestation","sign_citation":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C/action/citation_signature","submit_replication":"https://pith.science/pith/XFMCH2AC4HGE6PVO3NJHRFWJ3C/action/replication_record"}},"created_at":"2026-05-18T03:12:35.515334+00:00","updated_at":"2026-05-18T03:12:35.515334+00:00"}