{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q2EG34XDPKEKK2UA5E6XB6OFH3","short_pith_number":"pith:Q2EG34XD","schema_version":"1.0","canonical_sha256":"86886df2e37a88a56a80e93d70f9c53ec48dc0626b4dd402fe1e312a6aa2d17b","source":{"kind":"arxiv","id":"2502.09621","version":1},"attestation_state":"computed","paper":{"title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chaoyou Fu, Claire Guo, Dongzhi Jiang, Hongsheng Li, Jianhan Jin, Liuhui Wang, Peng Gao, Renrui Zhang, Shen Yan, Xinyan Chen, Yanwei Li, Yu Qi, Ziyu Guo","submitted_at":"2025-02-13T18:59:46Z","abstract_excerpt":"Answering questions with Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), yet its impact on Large Multimodal Models (LMMs) still lacks a systematic assessment and in-depth investigation. In this paper, we introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs, spanning six domains: math, science, OCR, logic, space-time, and general scenes. As the first comprehensive study in this area, we propose a thorough evaluation suite incorporating three novel metrics that assess the reasoning quality, robus"},"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":"2502.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T18:59:46Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"2f7240673bcca6f01c5263835667984f66000c630daada6d9d227d6565c970af","abstract_canon_sha256":"c6632635be071697663c56fb2d391974e1ae7e03f782feaed1eb105e55dc39c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:00.210627Z","signature_b64":"1F5vlL01plIk/iYPaERn+H0vX4J0tSen1R6/MmU16R+fmp3osdl6uqEqW3DxXIverGScjXv26MfrXPsA4u3RCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86886df2e37a88a56a80e93d70f9c53ec48dc0626b4dd402fe1e312a6aa2d17b","last_reissued_at":"2026-07-05T10:14:00.210141Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:00.210141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Zhang, Chaoyou Fu, Claire Guo, Dongzhi Jiang, Hongsheng Li, Jianhan Jin, Liuhui Wang, Peng Gao, Renrui Zhang, Shen Yan, Xinyan Chen, Yanwei Li, Yu Qi, Ziyu Guo","submitted_at":"2025-02-13T18:59:46Z","abstract_excerpt":"Answering questions with Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), yet its impact on Large Multimodal Models (LMMs) still lacks a systematic assessment and in-depth investigation. In this paper, we introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs, spanning six domains: math, science, OCR, logic, space-time, and general scenes. As the first comprehensive study in this area, we propose a thorough evaluation suite incorporating three novel metrics that assess the reasoning quality, robus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09621","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/2502.09621/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":"2502.09621","created_at":"2026-07-05T10:14:00.210205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09621v1","created_at":"2026-07-05T10:14:00.210205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09621","created_at":"2026-07-05T10:14:00.210205+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2EG34XDPKEK","created_at":"2026-07-05T10:14:00.210205+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2EG34XDPKEKK2UA","created_at":"2026-07-05T10:14:00.210205+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2EG34XD","created_at":"2026-07-05T10:14:00.210205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08763","citing_title":"OpenCoF: Learning to Reason Through Video Generation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.30378","citing_title":"OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning","ref_index":16,"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":29,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19852","citing_title":"Are Tools Always Beneficial? Learning to Invoke Tools Adaptively for Dual-Mode Multimodal LLM Reasoning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11991","citing_title":"VGR: Visual Grounded Reasoning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21122","citing_title":"NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06993","citing_title":"Can Textual Reasoning Improve the Performance of MLLMs on Fine-grained Visual Classification?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":178,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15198","citing_title":"ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05015","citing_title":"Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3","json":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3.json","graph_json":"https://pith.science/api/pith-number/Q2EG34XDPKEKK2UA5E6XB6OFH3/graph.json","events_json":"https://pith.science/api/pith-number/Q2EG34XDPKEKK2UA5E6XB6OFH3/events.json","paper":"https://pith.science/paper/Q2EG34XD"},"agent_actions":{"view_html":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3","download_json":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3.json","view_paper":"https://pith.science/paper/Q2EG34XD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09621&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2EG34XDPKEKK2UA5E6XB6OFH3/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2EG34XDPKEKK2UA5E6XB6OFH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3/action/storage_attestation","attest_author":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3/action/author_attestation","sign_citation":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3/action/citation_signature","submit_replication":"https://pith.science/pith/Q2EG34XDPKEKK2UA5E6XB6OFH3/action/replication_record"}},"created_at":"2026-07-05T10:14:00.210205+00:00","updated_at":"2026-07-05T10:14:00.210205+00:00"}