{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JKOVUJ5EKWQROAYEPGLUCB7P7N","short_pith_number":"pith:JKOVUJ5E","canonical_record":{"source":{"id":"2503.12605","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T18:39:13Z","cross_cats_sorted":[],"title_canon_sha256":"6bbcbb84a18d07c4498f9b8ff38bdb8f850ee752f096997a34f2582431104379","abstract_canon_sha256":"187c7779c84c45ead3f1226b8d5fd8f6d21279046e30756bff8905e91f900178"},"schema_version":"1.0"},"canonical_sha256":"4a9d5a27a455a117030479974107effb6a9ae764aea065ba2e26e30dd591d785","source":{"kind":"arxiv","id":"2503.12605","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12605","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12605v2","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12605","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"JKOVUJ5EKWQR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JKOVUJ5EKWQROAYE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JKOVUJ5E","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JKOVUJ5EKWQROAYEPGLUCB7P7N","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12605","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T18:39:13Z","cross_cats_sorted":[],"title_canon_sha256":"6bbcbb84a18d07c4498f9b8ff38bdb8f850ee752f096997a34f2582431104379","abstract_canon_sha256":"187c7779c84c45ead3f1226b8d5fd8f6d21279046e30756bff8905e91f900178"},"schema_version":"1.0"},"canonical_sha256":"4a9d5a27a455a117030479974107effb6a9ae764aea065ba2e26e30dd591d785","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.751417Z","signature_b64":"R+r2tkcclLXPqucW8hDpumrkuN9lTZaMH5iKQpSgt/6qgrMzHmx+EylNC+RV3ybhQQvx7b83Th6LMAcuuXtXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a9d5a27a455a117030479974107effb6a9ae764aea065ba2e26e30dd591d785","last_reissued_at":"2026-05-17T23:38:50.750935Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.750935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12605","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qgUdQWGAJ0fwzlDszlbSiraGbXbOoTLr82zSiEqL4yemuaqx8/DMJaCu2LacN2bu5JZyUdA1uwwxVoPhcokoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:42:10.617946Z"},"content_sha256":"ab482ab7b0a72a8a2f04582f4acd0b3d618a75866285f206be051bef67993d3b","schema_version":"1.0","event_id":"sha256:ab482ab7b0a72a8a2f04582f4acd0b3d618a75866285f206be051bef67993d3b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JKOVUJ5EKWQROAYEPGLUCB7P7N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Multimodal chain-of-thought reasoning receives its first systematic survey and taxonomy.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Fei, Jiebo Luo, Shengqiong Wu, Shuicheng Yan, Yaoting Wang, Yuecheng Zhang, Ziwei Liu","submitted_at":"2025-03-16T18:39:13Z","abstract_excerpt":"By extending the advantage of chain-of-thought (CoT) reasoning in human-like step-by-step processes to multimodal contexts, multimodal CoT (MCoT) reasoning has recently garnered significant research attention, especially in the integration with multimodal large language models (MLLMs). Existing MCoT studies design various methodologies and innovative reasoning paradigms to address the unique challenges of image, video, speech, audio, 3D, and structured data across different modalities, achieving extensive success in applications such as robotics, healthcare, autonomous driving, and multimodal "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we present the first systematic survey of MCoT reasoning, elucidating the relevant foundational concepts and definitions. We offer a comprehensive taxonomy and an in-depth analysis of current methodologies from diverse perspectives across various application scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the surveyed body of MCoT work is sufficiently mature and representative to support a stable taxonomy and that no major relevant papers or challenges have been overlooked in the compilation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal chain-of-thought reasoning receives its first systematic survey and taxonomy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0e7b54ce40c00234e574ca951f865d246f0397257258d89467153699ccad52f9"},"source":{"id":"2503.12605","kind":"arxiv","version":2},"verdict":{"id":"6b1aaef2-4f91-4906-9ebc-c404b4cc89db","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T17:14:02.519364Z","strongest_claim":"we present the first systematic survey of MCoT reasoning, elucidating the relevant foundational concepts and definitions. We offer a comprehensive taxonomy and an in-depth analysis of current methodologies from diverse perspectives across various application scenarios.","one_line_summary":"The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the surveyed body of MCoT work is sufficiently mature and representative to support a stable taxonomy and that no major relevant papers or challenges have been overlooked in the compilation.","pith_extraction_headline":"Multimodal chain-of-thought reasoning receives its first systematic survey and taxonomy."},"references":{"count":275,"sample":[{"doi":"","year":2024,"title":"Qwen2 Technical Report","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","ref_index":1,"cited_arxiv_id":"2407.10671","is_internal_anchor":true},{"doi":"","year":2024,"title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","work_id":"de9ce5af-0d8d-4b94-9793-64968d9bc06d","ref_index":2,"cited_arxiv_id":"2406.12793","is_internal_anchor":true},{"doi":"","year":2024,"title":"Yi: Open Foundation Models by 01.AI","work_id":"8efee8a1-5e3c-4851-9c65-18e3d1d9e769","ref_index":4,"cited_arxiv_id":"2403.04652","is_internal_anchor":true},{"doi":"","year":2023,"title":"PaLM 2 Technical Report","work_id":"905ee9a7-ea61-4a94-bd62-2600cbe3e315","ref_index":5,"cited_arxiv_id":"2305.10403","is_internal_anchor":true},{"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":6,"cited_arxiv_id":"2404.14219","is_internal_anchor":true}],"resolved_work":275,"snapshot_sha256":"4f0189a36b0f4fafe8e82676c532682c043cf1f03db1908cee8992b7bc5d3e55","internal_anchors":50},"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"},"verdict_id":"6b1aaef2-4f91-4906-9ebc-c404b4cc89db"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vzC0yTm4kYhXiFmk0G4KmHXgYug9WekvDhmT2GLpL8YWmZd5KrJvpnuy1wDRUXTlEFrZEHnhdyG2QCuHdYmxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:42:10.619880Z"},"content_sha256":"cf993ccd59277c516d3aabea9ccefb8c2ec0f74819e946fbd2482432946c7ac1","schema_version":"1.0","event_id":"sha256:cf993ccd59277c516d3aabea9ccefb8c2ec0f74819e946fbd2482432946c7ac1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N/bundle.json","state_url":"https://pith.science/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-09T02:42:10Z","links":{"resolver":"https://pith.science/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N","bundle":"https://pith.science/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N/bundle.json","state":"https://pith.science/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKOVUJ5EKWQROAYEPGLUCB7P7N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JKOVUJ5EKWQROAYEPGLUCB7P7N","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":"187c7779c84c45ead3f1226b8d5fd8f6d21279046e30756bff8905e91f900178","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T18:39:13Z","title_canon_sha256":"6bbcbb84a18d07c4498f9b8ff38bdb8f850ee752f096997a34f2582431104379"},"schema_version":"1.0","source":{"id":"2503.12605","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12605","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12605v2","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12605","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"JKOVUJ5EKWQR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"JKOVUJ5EKWQROAYE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"JKOVUJ5E","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cf993ccd59277c516d3aabea9ccefb8c2ec0f74819e946fbd2482432946c7ac1","target":"graph","created_at":"2026-05-17T23:38:50Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we present the first systematic survey of MCoT reasoning, elucidating the relevant foundational concepts and definitions. We offer a comprehensive taxonomy and an in-depth analysis of current methodologies from diverse perspectives across various application scenarios."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the surveyed body of MCoT work is sufficiently mature and representative to support a stable taxonomy and that no major relevant papers or challenges have been overlooked in the compilation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multimodal chain-of-thought reasoning receives its first systematic survey and taxonomy."}],"snapshot_sha256":"0e7b54ce40c00234e574ca951f865d246f0397257258d89467153699ccad52f9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"By extending the advantage of chain-of-thought (CoT) reasoning in human-like step-by-step processes to multimodal contexts, multimodal CoT (MCoT) reasoning has recently garnered significant research attention, especially in the integration with multimodal large language models (MLLMs). Existing MCoT studies design various methodologies and innovative reasoning paradigms to address the unique challenges of image, video, speech, audio, 3D, and structured data across different modalities, achieving extensive success in applications such as robotics, healthcare, autonomous driving, and multimodal ","authors_text":"Hao Fei, Jiebo Luo, Shengqiong Wu, Shuicheng Yan, Yaoting Wang, Yuecheng Zhang, Ziwei Liu","cross_cats":[],"headline":"Multimodal chain-of-thought reasoning receives its first systematic survey and taxonomy.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T18:39:13Z","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey"},"references":{"count":275,"internal_anchors":50,"resolved_work":275,"sample":[{"cited_arxiv_id":"2407.10671","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen2 Technical Report","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","year":2024},{"cited_arxiv_id":"2406.12793","doi":"","is_internal_anchor":true,"ref_index":2,"title":"ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools","work_id":"de9ce5af-0d8d-4b94-9793-64968d9bc06d","year":2024},{"cited_arxiv_id":"2403.04652","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Yi: Open Foundation Models by 01.AI","work_id":"8efee8a1-5e3c-4851-9c65-18e3d1d9e769","year":2024},{"cited_arxiv_id":"2305.10403","doi":"","is_internal_anchor":true,"ref_index":5,"title":"PaLM 2 Technical Report","work_id":"905ee9a7-ea61-4a94-bd62-2600cbe3e315","year":2023},{"cited_arxiv_id":"2404.14219","doi":"","is_internal_anchor":true,"ref_index":6,"title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","work_id":"feef9556-a016-493c-abd2-0c97a23a7ebf","year":2024}],"snapshot_sha256":"4f0189a36b0f4fafe8e82676c532682c043cf1f03db1908cee8992b7bc5d3e55"},"source":{"id":"2503.12605","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T17:14:02.519364Z","id":"6b1aaef2-4f91-4906-9ebc-c404b4cc89db","model_set":{"reader":"grok-4.3"},"one_line_summary":"The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multimodal chain-of-thought reasoning receives its first systematic survey and taxonomy.","strongest_claim":"we present the first systematic survey of MCoT reasoning, elucidating the relevant foundational concepts and definitions. We offer a comprehensive taxonomy and an in-depth analysis of current methodologies from diverse perspectives across various application scenarios.","weakest_assumption":"That the surveyed body of MCoT work is sufficiently mature and representative to support a stable taxonomy and that no major relevant papers or challenges have been overlooked in the compilation."}},"verdict_id":"6b1aaef2-4f91-4906-9ebc-c404b4cc89db"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ab482ab7b0a72a8a2f04582f4acd0b3d618a75866285f206be051bef67993d3b","target":"record","created_at":"2026-05-17T23:38:50Z","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":"187c7779c84c45ead3f1226b8d5fd8f6d21279046e30756bff8905e91f900178","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-16T18:39:13Z","title_canon_sha256":"6bbcbb84a18d07c4498f9b8ff38bdb8f850ee752f096997a34f2582431104379"},"schema_version":"1.0","source":{"id":"2503.12605","kind":"arxiv","version":2}},"canonical_sha256":"4a9d5a27a455a117030479974107effb6a9ae764aea065ba2e26e30dd591d785","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a9d5a27a455a117030479974107effb6a9ae764aea065ba2e26e30dd591d785","first_computed_at":"2026-05-17T23:38:50.750935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.750935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+r2tkcclLXPqucW8hDpumrkuN9lTZaMH5iKQpSgt/6qgrMzHmx+EylNC+RV3ybhQQvx7b83Th6LMAcuuXtXAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.751417Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12605","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab482ab7b0a72a8a2f04582f4acd0b3d618a75866285f206be051bef67993d3b","sha256:cf993ccd59277c516d3aabea9ccefb8c2ec0f74819e946fbd2482432946c7ac1"],"state_sha256":"5842acdaccb27f3da6e3f392e6f6cf59e6428b77a491ad05605d57ad2de121b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BhJFM92OUJ3No38RH1J8H0s7Uw5vDfdWoX9YFlieiOPrpyC89kiMCrw5CrNqgomGDhqeDXiTs+xcPqXgDtDlCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T02:42:10.624844Z","bundle_sha256":"b52427b2ad48b105da726f70c1af75f540f33a4134b1b35137299a0440155cb9"}}