{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GGXVXXTCQPZW5YB66AKJR2EP67","short_pith_number":"pith:GGXVXXTC","schema_version":"1.0","canonical_sha256":"31af5bde6283f36ee03ef01498e88ff7f836047582f8d62e62f4ed1363110ece","source":{"kind":"arxiv","id":"2305.02317","version":3},"attestation_state":"computed","paper":{"title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alex Mei, Andy Ouyang, Chinmay Sonar, Daniel Rose, Diba Mirza, Michael Saxon, Ryan He, Vaishnavi Himakunthala, William Yang Wang, Yujie Lu","submitted_at":"2023-05-03T17:58:29Z","abstract_excerpt":"Recent advances in large language models elicit reasoning in a chain-of-thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves multi-step reasoning ability in language models, it is limited by being unimodal and applied mainly to question-answering tasks. We claim that incorporating visual augmentation into reasoning is essential, especially for complex, imaginative tasks. Consequently, we introduce VCoT, a novel method that leverages chain-of-thought prompting with vision-language grounding to recursively bridge the logical gaps within sequenti"},"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":"2305.02317","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T17:58:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2f6190281e4af0376de51fb97e4babbf4d8d82d1ed413c4173ad73692695b8c8","abstract_canon_sha256":"d25b9b5c7b2b882fa649e51ab052131bb1ff8cce980ad08da96a4e5ef8b12f3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:21.067232Z","signature_b64":"TkGRoEprb2piSGI3igTxEv50F1StEqHZUJSZHQp8dYGFBsWwML5z49uftkROETN+KDgykuTpX79/n6NVo6QgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31af5bde6283f36ee03ef01498e88ff7f836047582f8d62e62f4ed1363110ece","last_reissued_at":"2026-07-05T07:36:21.066818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:21.066818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Chain of Thought: Bridging Logical Gaps with Multimodal Infillings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Alex Mei, Andy Ouyang, Chinmay Sonar, Daniel Rose, Diba Mirza, Michael Saxon, Ryan He, Vaishnavi Himakunthala, William Yang Wang, Yujie Lu","submitted_at":"2023-05-03T17:58:29Z","abstract_excerpt":"Recent advances in large language models elicit reasoning in a chain-of-thought that allows models to decompose problems in a human-like fashion. Though this paradigm improves multi-step reasoning ability in language models, it is limited by being unimodal and applied mainly to question-answering tasks. We claim that incorporating visual augmentation into reasoning is essential, especially for complex, imaginative tasks. Consequently, we introduce VCoT, a novel method that leverages chain-of-thought prompting with vision-language grounding to recursively bridge the logical gaps within sequenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02317","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/2305.02317/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":"2305.02317","created_at":"2026-07-05T07:36:21.066874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02317v3","created_at":"2026-07-05T07:36:21.066874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02317","created_at":"2026-07-05T07:36:21.066874+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGXVXXTCQPZW","created_at":"2026-07-05T07:36:21.066874+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGXVXXTCQPZW5YB6","created_at":"2026-07-05T07:36:21.066874+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGXVXXTC","created_at":"2026-07-05T07:36:21.066874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18974","citing_title":"Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00361","citing_title":"ReShift: Aha-Moment-Driven Reasoning-Level Backdoor Attacks on Vision-Language Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23322","citing_title":"Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05748","citing_title":"WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20696","citing_title":"R-CoV: Region-Aware Chain-of-Verification for Alleviating Object Hallucinations in LVLMs","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17800","citing_title":"ReFineVLA: Multimodal Reasoning-Aware Generalist Robotic Policies via Teacher-Guided Fine-Tuning","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67","json":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67.json","graph_json":"https://pith.science/api/pith-number/GGXVXXTCQPZW5YB66AKJR2EP67/graph.json","events_json":"https://pith.science/api/pith-number/GGXVXXTCQPZW5YB66AKJR2EP67/events.json","paper":"https://pith.science/paper/GGXVXXTC"},"agent_actions":{"view_html":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67","download_json":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67.json","view_paper":"https://pith.science/paper/GGXVXXTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02317&json=true","fetch_graph":"https://pith.science/api/pith-number/GGXVXXTCQPZW5YB66AKJR2EP67/graph.json","fetch_events":"https://pith.science/api/pith-number/GGXVXXTCQPZW5YB66AKJR2EP67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67/action/storage_attestation","attest_author":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67/action/author_attestation","sign_citation":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67/action/citation_signature","submit_replication":"https://pith.science/pith/GGXVXXTCQPZW5YB66AKJR2EP67/action/replication_record"}},"created_at":"2026-07-05T07:36:21.066874+00:00","updated_at":"2026-07-05T07:36:21.066874+00:00"}