{"work":{"id":"c10c912e-59c0-4cd0-b849-c2274cb7a92e","openalex_id":null,"doi":null,"arxiv_id":"2109.10852","raw_key":null,"title":"Pix2seq: A language modeling framework for object detection.arXiv preprint arXiv:2109.10852, 2021","authors":null,"authors_text":"Ting Chen, Saurabh Saxena, Lala Li, David J Fleet, and Ge- offrey Hinton","year":2021,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2109.10852","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-21T19:54:20.146894+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T06:20:16.163124+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Pix2seq: A language modeling framework for object detection","render_title":"Pix2seq: A language modeling framework for object detection"},"hub":{"state":{"work_id":"c10c912e-59c0-4cd0-b849-c2274cb7a92e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":10,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2022-09-14T17:24:07+00:00","last_pith_cited_at":"2026-04-10T03:33:51+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":"2026-06-12T04:59:16.784618+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}