{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TGHOHXQZ73FAA5LYLPHV4RDAHX","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":"52c4e395099f704e4bb62403dbaea670a5387274e159d3cc618e42c613acc0cb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T15:59:41Z","title_canon_sha256":"aba158dab104046e8c6881c370ff8f3ac368b32170e3f9657c8415b800d78001"},"schema_version":"1.0","source":{"id":"2606.22565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22565","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22565v1","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22565","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"TGHOHXQZ73FA","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"pith_short_16","alias_value":"TGHOHXQZ73FAA5LY","created_at":"2026-06-23T02:13:41Z"},{"alias_kind":"pith_short_8","alias_value":"TGHOHXQZ","created_at":"2026-06-23T02:13:41Z"}],"graph_snapshots":[{"event_id":"sha256:a1dc986d708ed0bad00ce43d01cc303aca0781bf975c13ba903715e1b76035a7","target":"graph","created_at":"2026-06-23T02:13:41Z","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/2606.22565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-Thought (CoT) has become a standard method for improving reasoning capabilities in large language models (LLMs) by eliciting step-by-step thinking, but its effectiveness in multimodal tasks remains unclear. In this paper, we aim to systematically investigate the key question: What can multimodal Chain-of-Thought reasoning do, and where and why does it fall short? To this end, we evaluate 12 multimodal tasks across perception and reasoning categories using both 14 non-reasoning models and 8 reasoning models. Our analysis reveals several important findings: (1) CoT is not a free lunch a","authors_text":"Hongbang Yuan, Jun Zhao, Kang Liu, Kejian Zhu, Pengfei Cao, Yubo Chen, Yupu Hao, Zhuoran Jin","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T15:59:41Z","title":"Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22565","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":"sha256:82f4cbef1d5fd4f63a5f707e3205be4a677f5ef80c53738b1091ce73a0790eff","target":"record","created_at":"2026-06-23T02:13:41Z","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":"52c4e395099f704e4bb62403dbaea670a5387274e159d3cc618e42c613acc0cb","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T15:59:41Z","title_canon_sha256":"aba158dab104046e8c6881c370ff8f3ac368b32170e3f9657c8415b800d78001"},"schema_version":"1.0","source":{"id":"2606.22565","kind":"arxiv","version":1}},"canonical_sha256":"998ee3de19feca0075785bcf5e44603df0b6bfcb170029d46e0e4839313f2bc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"998ee3de19feca0075785bcf5e44603df0b6bfcb170029d46e0e4839313f2bc3","first_computed_at":"2026-06-23T02:13:41.740495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:41.740495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rzPOXYMhXngBCo2gArfHzct6Kq2KkF9fqszA5TsevyBBlcSXaPfvvGSNeHZ9IMENJGB+62Y4W3k235bIlHtMCw==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:41.740915Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82f4cbef1d5fd4f63a5f707e3205be4a677f5ef80c53738b1091ce73a0790eff","sha256:a1dc986d708ed0bad00ce43d01cc303aca0781bf975c13ba903715e1b76035a7"],"state_sha256":"3ee806ccbda830737f8623a04210721a71c969fc3ca395c9357ebd82399a0363"}