{"work":{"id":"98823083-5573-413f-a371-f50911725458","openalex_id":null,"doi":null,"arxiv_id":"2511.05491","raw_key":null,"title":"Visual spatial tuning.arXiv preprint arXiv:2511.05491,","authors":null,"authors_text":"Rui Yang, Ziyu Zhu, Yanwei Li, Jingjia Huang, Shen Yan, Siyuan Zhou, Zhe Liu, Xiangtai Li, Shuangye Li, Wenqian Wang, Yi Lin, and Hengshuang Zhao","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2511.05491","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T04:29:35.777532+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T06:55:44.056771+00:00","updated_at":"2026-07-04T04:29:35.777532+00:00","title_quality_ok":true,"display_title":"Thinking in space: How multimodal large language models see, remember, and recall spaces","render_title":"Thinking in space: How multimodal large language models see, remember, and recall spaces"},"hub":{"state":{"work_id":"98823083-5573-413f-a371-f50911725458","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":37,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2025-05-22T17:59:03+00:00","last_pith_cited_at":"2026-07-01T12:45:12+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":"2026-07-08T04:21:46.533205+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":8},{"context_role":"baseline","n":3},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":7},{"context_polarity":"baseline","n":3},{"context_polarity":"unclear","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}