{"work":{"id":"b7899c66-9ee1-45bf-8a1d-223b8959dee6","openalex_id":null,"doi":null,"arxiv_id":"2302.11713","raw_key":null,"title":"Can pre-trained vision and language models answer visual information-seeking questions? arXiv preprint arXiv:2302.11713, 2023","authors":null,"authors_text":"Yang Chen, Hexiang Hu, Yi Luan, Haitian Sun, Soravit Changpinyo, Alan Ritter, and Ming-Wei Chang","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2302.11713","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-19T13:52:19.892363+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T05:55:59.354543+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Can pre-trained vision and language models answer visual information-seeking questions?","render_title":"Can pre-trained vision and language models answer visual information-seeking questions?"},"hub":{"state":{"work_id":"b7899c66-9ee1-45bf-8a1d-223b8959dee6","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":12,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2023-05-29T18:58:38+00:00","last_pith_cited_at":"2026-04-29T08:29:44+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":"2026-06-08T18:24:04.482905+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}