{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QVQWTDYNLCNJLFWETCFJ572UAV","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":"cd99dd70742e0e4faea18993386adc16c46ab89da28d2fd7210b4e528ba4f4e0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T14:10:16Z","title_canon_sha256":"731ce90e4fbf183163e3ed4554afc88f4456fddb94f9d29330856000544f0cc1"},"schema_version":"1.0","source":{"id":"2412.12932","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12932","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12932v3","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12932","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"QVQWTDYNLCNJ","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"QVQWTDYNLCNJLFWE","created_at":"2026-07-05T10:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"QVQWTDYN","created_at":"2026-07-05T10:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:bd864e16340e3f6323d86033227893e7a735023ec9b7524315dac0a6c45e420b","target":"graph","created_at":"2026-07-05T10:27:21Z","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/2412.12932/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hao Fei, Jin Zhang, Libo Qin, Min Li, Qiguang Chen, Wanxiang Che, Xiaocheng Feng, Zihui Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T14:10:16Z","title":"CoMT: A Novel Benchmark for Chain of Multi-modal Thought on Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12932","kind":"arxiv","version":3},"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":"sha256:4a7872c6b8b890c36edd91aceb9fde23fc247bcb8b5e621c37b51cbcf0862f24","target":"record","created_at":"2026-07-05T10:27:21Z","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":"cd99dd70742e0e4faea18993386adc16c46ab89da28d2fd7210b4e528ba4f4e0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T14:10:16Z","title_canon_sha256":"731ce90e4fbf183163e3ed4554afc88f4456fddb94f9d29330856000544f0cc1"},"schema_version":"1.0","source":{"id":"2412.12932","kind":"arxiv","version":3}},"canonical_sha256":"8561698f0d589a9596c4988a9eff54056a20221c14a42a50fd922926525ff735","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8561698f0d589a9596c4988a9eff54056a20221c14a42a50fd922926525ff735","first_computed_at":"2026-07-05T10:27:21.958035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:21.958035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V+HC+DwMqqReCVTAa6H6XoK6Vuudd3EDoh0Dm4CrSb5xsxyvHz2pHwBiqZu5Ggkqy0WG23uFZnOHN/H3dtGLDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:21.958523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12932","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a7872c6b8b890c36edd91aceb9fde23fc247bcb8b5e621c37b51cbcf0862f24","sha256:bd864e16340e3f6323d86033227893e7a735023ec9b7524315dac0a6c45e420b"],"state_sha256":"6e5c8b0fa0c526a2af34894a6d7fd17b9b968b0097d03d75861f5bd73601abf5"}