{"work":{"id":"fda95042-555b-4a64-9d35-7978eb50b269","openalex_id":null,"doi":null,"arxiv_id":"2506.04308","raw_key":null,"title":"arXiv preprint arXiv:2506.04308 (2025) 1","authors":null,"authors_text":"Zhou, E","year":2025,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2506.04308","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-07-04T19:30:08.026359+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T01:10:09.464846+00:00","updated_at":"2026-07-04T19:30:08.026359+00:00","title_quality_ok":false,"display_title":"RoboRefer: Towards spatial referring with rea- soning in vision-language models for robotics","render_title":"RoboRefer: Towards spatial referring with rea- soning in vision-language models for robotics"},"hub":{"state":{"work_id":"fda95042-555b-4a64-9d35-7978eb50b269","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":27,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-10-15T17:30:05+00:00","last_pith_cited_at":"2026-06-30T22:57:43+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":"2026-08-23T16:19:45.366664+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"dataset","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_dataset","n":2},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}