{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VLRUFG5OGI3I6RBM2OFDEZS7JI","short_pith_number":"pith:VLRUFG5O","schema_version":"1.0","canonical_sha256":"aae3429bae32368f442cd38a32665f4a308d0868b214baeaed574e884290c944","source":{"kind":"arxiv","id":"2404.03622","version":3},"attestation_state":"computed","paper":{"title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Li Dong, Shaoguang Mao, Wenshan Wu, Yadong Zhang, Yan Xia","submitted_at":"2024-04-04T17:45:08Z","abstract_excerpt":"Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as the Mind's Eye, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (VoT) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guid"},"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":"2404.03622","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T17:45:08Z","cross_cats_sorted":[],"title_canon_sha256":"7576ad024fbc8144bbf50ce6a28f8a4e1e24e070130c740d38aa04ef803139c2","abstract_canon_sha256":"5e4679bc682853c706987736b28e3461c7408886434fbb759debc42d7a624b8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:33.609210Z","signature_b64":"6MlpkrX7Y9NYX/xg20d2YSpmFRmsnDkFzALyseAQuu/FkTMBdtZAopBSKRzFwl0QUC2vL9/gLCNYllovsISHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aae3429bae32368f442cd38a32665f4a308d0868b214baeaed574e884290c944","last_reissued_at":"2026-07-05T09:24:33.608811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:33.608811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Li Dong, Shaoguang Mao, Wenshan Wu, Yadong Zhang, Yan Xia","submitted_at":"2024-04-04T17:45:08Z","abstract_excerpt":"Large language models (LLMs) have exhibited impressive performance in language comprehension and various reasoning tasks. However, their abilities in spatial reasoning, a crucial aspect of human cognition, remain relatively unexplored. Human possess a remarkable ability to create mental images of unseen objects and actions through a process known as the Mind's Eye, enabling the imagination of the unseen world. Inspired by this cognitive capacity, we propose Visualization-of-Thought (VoT) prompting. VoT aims to elicit spatial reasoning of LLMs by visualizing their reasoning traces, thereby guid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03622","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/2404.03622/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":"2404.03622","created_at":"2026-07-05T09:24:33.608864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03622v3","created_at":"2026-07-05T09:24:33.608864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03622","created_at":"2026-07-05T09:24:33.608864+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLRUFG5OGI3I","created_at":"2026-07-05T09:24:33.608864+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLRUFG5OGI3I6RBM","created_at":"2026-07-05T09:24:33.608864+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLRUFG5O","created_at":"2026-07-05T09:24:33.608864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05769","citing_title":"Imagine Before You Predict: Interleaved Latent Visual Reasoning for Video Event Prediction","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22219","citing_title":"Lost in Aggregation: A Multi-Scale Diagnostic Benchmark for LLM Spatial Navigation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI","json":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI.json","graph_json":"https://pith.science/api/pith-number/VLRUFG5OGI3I6RBM2OFDEZS7JI/graph.json","events_json":"https://pith.science/api/pith-number/VLRUFG5OGI3I6RBM2OFDEZS7JI/events.json","paper":"https://pith.science/paper/VLRUFG5O"},"agent_actions":{"view_html":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI","download_json":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI.json","view_paper":"https://pith.science/paper/VLRUFG5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03622&json=true","fetch_graph":"https://pith.science/api/pith-number/VLRUFG5OGI3I6RBM2OFDEZS7JI/graph.json","fetch_events":"https://pith.science/api/pith-number/VLRUFG5OGI3I6RBM2OFDEZS7JI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI/action/storage_attestation","attest_author":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI/action/author_attestation","sign_citation":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI/action/citation_signature","submit_replication":"https://pith.science/pith/VLRUFG5OGI3I6RBM2OFDEZS7JI/action/replication_record"}},"created_at":"2026-07-05T09:24:33.608864+00:00","updated_at":"2026-07-05T09:24:33.608864+00:00"}