{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q2EG34XDPKEKK2UA5E6XB6OFH3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6632635be071697663c56fb2d391974e1ae7e03f782feaed1eb105e55dc39c9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T18:59:46Z","title_canon_sha256":"2f7240673bcca6f01c5263835667984f66000c630daada6d9d227d6565c970af"},"schema_version":"1.0","source":{"id":"2502.09621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09621","created_at":"2026-07-05T10:14:00Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09621v1","created_at":"2026-07-05T10:14:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09621","created_at":"2026-07-05T10:14:00Z"},{"alias_kind":"pith_short_12","alias_value":"Q2EG34XDPKEK","created_at":"2026-07-05T10:14:00Z"},{"alias_kind":"pith_short_16","alias_value":"Q2EG34XDPKEKK2UA","created_at":"2026-07-05T10:14:00Z"},{"alias_kind":"pith_short_8","alias_value":"Q2EG34XD","created_at":"2026-07-05T10:14:00Z"}],"graph_snapshots":[{"event_id":"sha256:483ad8f62dc1d2952f105a4b14350562f48380e01fb02b93392724a5faadc725","target":"graph","created_at":"2026-07-05T10:14:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.09621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T18:59:46Z","title":"MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09621","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ad0f504e570eaa1123eddfd3322c3d9b3cab5a50ba0a32f18c8d548923a9f016","target":"record","created_at":"2026-07-05T10:14:00Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6632635be071697663c56fb2d391974e1ae7e03f782feaed1eb105e55dc39c9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T18:59:46Z","title_canon_sha256":"2f7240673bcca6f01c5263835667984f66000c630daada6d9d227d6565c970af"},"schema_version":"1.0","source":{"id":"2502.09621","kind":"arxiv","version":1}},"canonical_sha256":"86886df2e37a88a56a80e93d70f9c53ec48dc0626b4dd402fe1e312a6aa2d17b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86886df2e37a88a56a80e93d70f9c53ec48dc0626b4dd402fe1e312a6aa2d17b","first_computed_at":"2026-07-05T10:14:00.210141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:00.210141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1F5vlL01plIk/iYPaERn+H0vX4J0tSen1R6/MmU16R+fmp3osdl6uqEqW3DxXIverGScjXv26MfrXPsA4u3RCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:00.210627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad0f504e570eaa1123eddfd3322c3d9b3cab5a50ba0a32f18c8d548923a9f016","sha256:483ad8f62dc1d2952f105a4b14350562f48380e01fb02b93392724a5faadc725"],"state_sha256":"fd1721b437d89a19f21757dc2a0145ebf6462cf3abee95e7947f3bb6ec5cab08"}