{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RPT32H5LX2L26EPZELD7ZONHAF","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":"fb8eb7af8bde350257c5b814c0ef8773d687a5cb43b557bd77737a3134e676b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T17:57:40Z","title_canon_sha256":"f80873e44385b15277b97a0c20ad19fa47fc32319fe461484e0fa6c3ddf57f24"},"schema_version":"1.0","source":{"id":"2410.14668","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14668","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14668v4","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14668","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_12","alias_value":"RPT32H5LX2L2","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_16","alias_value":"RPT32H5LX2L26EPZ","created_at":"2026-07-05T10:21:25Z"},{"alias_kind":"pith_short_8","alias_value":"RPT32H5L","created_at":"2026-07-05T10:21:25Z"}],"graph_snapshots":[{"event_id":"sha256:ecac569329abb8afe9ccef7d61f2def1792bedcfc2174735d6b107edf7d1ef4b","target":"graph","created_at":"2026-07-05T10:21:25Z","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/2410.14668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Chain of Thought (MCoT) is a popular prompting strategy for improving the performance of multimodal large language models (MLLMs) across a range of complex reasoning tasks. Despite its popularity, there is a notable absence of automated methods for evaluating the quality of reasoning steps in MCoT. To address this gap, we propose Multimodal Chain-of-Thought Evaluation (MiCEval), a framework designed to assess the correctness of reasoning chains by evaluating the quality of both the description and each reasoning step. The evaluation of the description component focuses on the accura","authors_text":"Hanjie Chen, Haojing Chen, Jeff Z. Pan, Jie He, Jingyu Li, Lanyu Chen, V\\'ictor Guti\\'errez-Basulto, Xiongtao Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T17:57:40Z","title":"MiCEval: Unveiling Multimodal Chain of Thought's Quality via Image Description and Reasoning Steps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14668","kind":"arxiv","version":4},"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":"sha256:8a49098f60d87ed33d9db5b45f7d7c5dd94bd0fc63f638888e72ec7d31cfe093","target":"record","created_at":"2026-07-05T10:21:25Z","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":"fb8eb7af8bde350257c5b814c0ef8773d687a5cb43b557bd77737a3134e676b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-18T17:57:40Z","title_canon_sha256":"f80873e44385b15277b97a0c20ad19fa47fc32319fe461484e0fa6c3ddf57f24"},"schema_version":"1.0","source":{"id":"2410.14668","kind":"arxiv","version":4}},"canonical_sha256":"8be7bd1fabbe97af11f922c7fcb9a70171c5cf81abca6d7b09aadad346788394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8be7bd1fabbe97af11f922c7fcb9a70171c5cf81abca6d7b09aadad346788394","first_computed_at":"2026-07-05T10:21:25.109756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:25.109756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kvTXvovkJboSVoZmUysPagGwNgd4GoW00Sh2Bc18OwviFRXQkcToNqn7Pyy71IG7U/2NtMga/RUnRyF9UTnMAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:25.110306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14668","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a49098f60d87ed33d9db5b45f7d7c5dd94bd0fc63f638888e72ec7d31cfe093","sha256:ecac569329abb8afe9ccef7d61f2def1792bedcfc2174735d6b107edf7d1ef4b"],"state_sha256":"af4f4ff63fd0eeb6fd3ce26718b067b07fb091e96d14e5a8c2e53bb53c172dca"}