{"work":{"id":"a309097d-9350-42a1-9232-7b765166f2da","openalex_id":null,"doi":null,"arxiv_id":"2304.14108","raw_key":null,"title":"Datacomp: In search of the next generation of multimodal datasets","authors":null,"authors_text":"Samir Yitzhak Gadre, Gabriel Ilharco, Alex Fang, Jonathan Hayase, Georgios Smyrnis, Thao Nguyen, Ryan Marten, Mitchell Wortsman, Dhruba Ghosh, Jieyu Zhang, Eyal Or- gad, Rahim Entezari, Giannis Daras, Sarah Pratt, Vivek Ramanujan, Yonatan B","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2304.14108","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-22T19:52:01.975794+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T18:31:12.922875+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Datacomp: In search of the next generation of multimodal datasets","render_title":"Datacomp: In search of the next generation of multimodal datasets"},"hub":{"state":{"work_id":"a309097d-9350-42a1-9232-7b765166f2da","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":15,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2023-07-11T17:57:40+00:00","last_pith_cited_at":"2026-05-19T04:39:28+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":"2026-06-08T22:13:53.592184+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"baseline","n":1},{"context_role":"other","n":1}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"unclear","n":2},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}