{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QVQWTDYNLCNJLFWETCFJ572UAV","short_pith_number":"pith:QVQWTDYN","schema_version":"1.0","canonical_sha256":"8561698f0d589a9596c4988a9eff54056a20221c14a42a50fd922926525ff735","source":{"kind":"arxiv","id":"2412.12932","version":3},"attestation_state":"computed","paper":{"title":"CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Fei, Jin Zhang, Libo Qin, Min Li, Qiguang Chen, Wanxiang Che, Xiaocheng Feng, Zihui Cheng","submitted_at":"2024-12-17T14:10:16Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output, which leads to significant drawbacks such as missing visual operations and vague expressions. Motivated by this, we introduce a novel Chain of Multi-modal Thought (CoMT) benchmark to address these limitations. Different from the traditional MCoT benchmark, CoMT requires both multi-modal input and m"},"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":"2412.12932","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T14:10:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"731ce90e4fbf183163e3ed4554afc88f4456fddb94f9d29330856000544f0cc1","abstract_canon_sha256":"cd99dd70742e0e4faea18993386adc16c46ab89da28d2fd7210b4e528ba4f4e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:21.958523Z","signature_b64":"V+HC+DwMqqReCVTAa6H6XoK6Vuudd3EDoh0Dm4CrSb5xsxyvHz2pHwBiqZu5Ggkqy0WG23uFZnOHN/H3dtGLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8561698f0d589a9596c4988a9eff54056a20221c14a42a50fd922926525ff735","last_reissued_at":"2026-07-05T10:27:21.958035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:21.958035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hao Fei, Jin Zhang, Libo Qin, Min Li, Qiguang Chen, Wanxiang Che, Xiaocheng Feng, Zihui Cheng","submitted_at":"2024-12-17T14:10:16Z","abstract_excerpt":"Large Vision-Language Models (LVLMs) have recently demonstrated amazing success in multi-modal tasks, including advancements in Multi-modal Chain-of-Thought (MCoT) reasoning. Despite these successes, current benchmarks still follow a traditional paradigm with multi-modal input and text-modal output, which leads to significant drawbacks such as missing visual operations and vague expressions. Motivated by this, we introduce a novel Chain of Multi-modal Thought (CoMT) benchmark to address these limitations. Different from the traditional MCoT benchmark, CoMT requires both multi-modal input and m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12932","kind":"arxiv","version":3},"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/2412.12932/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":"2412.12932","created_at":"2026-07-05T10:27:21.958085+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12932v3","created_at":"2026-07-05T10:27:21.958085+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12932","created_at":"2026-07-05T10:27:21.958085+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVQWTDYNLCNJ","created_at":"2026-07-05T10:27:21.958085+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVQWTDYNLCNJLFWE","created_at":"2026-07-05T10:27:21.958085+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVQWTDYN","created_at":"2026-07-05T10:27:21.958085+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.07536","citing_title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":174,"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":128,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV","json":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV.json","graph_json":"https://pith.science/api/pith-number/QVQWTDYNLCNJLFWETCFJ572UAV/graph.json","events_json":"https://pith.science/api/pith-number/QVQWTDYNLCNJLFWETCFJ572UAV/events.json","paper":"https://pith.science/paper/QVQWTDYN"},"agent_actions":{"view_html":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV","download_json":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV.json","view_paper":"https://pith.science/paper/QVQWTDYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12932&json=true","fetch_graph":"https://pith.science/api/pith-number/QVQWTDYNLCNJLFWETCFJ572UAV/graph.json","fetch_events":"https://pith.science/api/pith-number/QVQWTDYNLCNJLFWETCFJ572UAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV/action/storage_attestation","attest_author":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV/action/author_attestation","sign_citation":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV/action/citation_signature","submit_replication":"https://pith.science/pith/QVQWTDYNLCNJLFWETCFJ572UAV/action/replication_record"}},"created_at":"2026-07-05T10:27:21.958085+00:00","updated_at":"2026-07-05T10:27:21.958085+00:00"}