{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FTAXDLOWHZBB3GJCGY63FVBLRS","short_pith_number":"pith:FTAXDLOW","schema_version":"1.0","canonical_sha256":"2cc171add63e421d9922363db2d42b8caf0a5ee7428a66ca76fff0cf9f007099","source":{"kind":"arxiv","id":"2501.05444","version":1},"attestation_state":"computed","paper":{"title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huichen Will Wang, Jiawei Gu, Lijuan Wang, Linjie Li, Yu Cheng, Yunzhuo Hao, Zhengyuan Yang","submitted_at":"2025-01-09T18:55:52Z","abstract_excerpt":"The ability to organically reason over and with both text and images is a pillar of human intelligence, yet the ability of Multimodal Large Language Models (MLLMs) to perform such multimodal reasoning remains under-explored. Existing benchmarks often emphasize text-dominant reasoning or rely on shallow visual cues, failing to adequately assess integrated visual and textual reasoning. We introduce EMMA (Enhanced MultiModal reAsoning), a benchmark targeting organic multimodal reasoning across mathematics, physics, chemistry, and coding. EMMA tasks demand advanced cross-modal reasoning that canno"},"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":"2501.05444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:55:52Z","cross_cats_sorted":[],"title_canon_sha256":"45ee57ab91e8b62e29ad475b90b30acedfbec966e5be7e8f147853ccddb3f5b7","abstract_canon_sha256":"2092757901d7fe35f83ba6c89c43590bf0efb3c59eb859a575149aaa7e0bb33e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:10.004621Z","signature_b64":"nOocXfHyBw9ADms++gqdKWRCbyv/pm6RiNlVDpzoIgscmq94X6PaqTkFypqe1B4JAW3nPAevSHlAcViiV2ZbDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cc171add63e421d9922363db2d42b8caf0a5ee7428a66ca76fff0cf9f007099","last_reissued_at":"2026-07-05T09:59:10.004174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:10.004174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huichen Will Wang, Jiawei Gu, Lijuan Wang, Linjie Li, Yu Cheng, Yunzhuo Hao, Zhengyuan Yang","submitted_at":"2025-01-09T18:55:52Z","abstract_excerpt":"The ability to organically reason over and with both text and images is a pillar of human intelligence, yet the ability of Multimodal Large Language Models (MLLMs) to perform such multimodal reasoning remains under-explored. Existing benchmarks often emphasize text-dominant reasoning or rely on shallow visual cues, failing to adequately assess integrated visual and textual reasoning. We introduce EMMA (Enhanced MultiModal reAsoning), a benchmark targeting organic multimodal reasoning across mathematics, physics, chemistry, and coding. EMMA tasks demand advanced cross-modal reasoning that canno"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05444","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/2501.05444/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":"2501.05444","created_at":"2026-07-05T09:59:10.004231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05444v1","created_at":"2026-07-05T09:59:10.004231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05444","created_at":"2026-07-05T09:59:10.004231+00:00"},{"alias_kind":"pith_short_12","alias_value":"FTAXDLOWHZBB","created_at":"2026-07-05T09:59:10.004231+00:00"},{"alias_kind":"pith_short_16","alias_value":"FTAXDLOWHZBB3GJC","created_at":"2026-07-05T09:59:10.004231+00:00"},{"alias_kind":"pith_short_8","alias_value":"FTAXDLOW","created_at":"2026-07-05T09:59:10.004231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26535","citing_title":"From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00248","citing_title":"Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05966","citing_title":"Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25571","citing_title":"AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2511.23253","citing_title":"AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15792","citing_title":"Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17352","citing_title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.14945","citing_title":"Learning to Reason under Off-Policy Guidance","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18154","citing_title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2603.20633","citing_title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14054","citing_title":"Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":241,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09614","citing_title":"Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21510","citing_title":"OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20183","citing_title":"Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS","json":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS.json","graph_json":"https://pith.science/api/pith-number/FTAXDLOWHZBB3GJCGY63FVBLRS/graph.json","events_json":"https://pith.science/api/pith-number/FTAXDLOWHZBB3GJCGY63FVBLRS/events.json","paper":"https://pith.science/paper/FTAXDLOW"},"agent_actions":{"view_html":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS","download_json":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS.json","view_paper":"https://pith.science/paper/FTAXDLOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05444&json=true","fetch_graph":"https://pith.science/api/pith-number/FTAXDLOWHZBB3GJCGY63FVBLRS/graph.json","fetch_events":"https://pith.science/api/pith-number/FTAXDLOWHZBB3GJCGY63FVBLRS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS/action/storage_attestation","attest_author":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS/action/author_attestation","sign_citation":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS/action/citation_signature","submit_replication":"https://pith.science/pith/FTAXDLOWHZBB3GJCGY63FVBLRS/action/replication_record"}},"created_at":"2026-07-05T09:59:10.004231+00:00","updated_at":"2026-07-05T09:59:10.004231+00:00"}