{"work":{"id":"6df227a2-7a70-47c8-ae06-b2d6eee27a57","openalex_id":null,"doi":null,"arxiv_id":"2406.09403","raw_key":"raw:07a524e0323d7f882ceaeb55","title":"Visual sketchpad: Sketching as a visual chain of thought for multimodal language models","authors":null,"authors_text":"Yushi Hu, Weijia Shi, Xingyu Fu, Dan Roth, Mari Ostendorf, Luke Zettlemoyer, Noah A Smith, and Ranjay Krishna","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2406.09403","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-23T20:13:24.847253+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T09:48:48.405300+00:00","updated_at":"2026-05-23T20:13:24.847253+00:00","title_quality_ok":true,"display_title":"Visual sketchpad: Sketching as a visual chain of thought for multimodal language models","render_title":"Visual sketchpad: Sketching as a visual chain of thought for multimodal language models"},"hub":{"state":{"work_id":"6df227a2-7a70-47c8-ae06-b2d6eee27a57","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2024-10-06T14:59:09+00:00","last_pith_cited_at":"2026-05-20T05:46:14+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-01T20:13:46.284693+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}