{"work":{"id":"d774cb51-7f06-48c6-9dea-33285f55ce87","openalex_id":"https://openalex.org/W4396786216","doi":"10.48550/arxiv.2405.02246","arxiv_id":"2405.02246","raw_key":null,"title":"arXiv preprint arXiv:2405.02246 , year=","authors":null,"authors_text":"Laurençon, H","year":2024,"venue":"arXiv (Cornell University)","abstract":null,"external_url":"https://arxiv.org/abs/2405.02246","cited_by_count":17,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T22:44:15.189920+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":false,"display_title":"What matters when building vision-language models?","render_title":"What matters when building vision-language models?"},"hub":{"state":{"work_id":"d774cb51-7f06-48c6-9dea-33285f55ce87","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":24,"external_cited_by_count":17,"distinct_field_count":7,"first_pith_cited_at":"2024-06-24T17:59:42+00:00","last_pith_cited_at":"2026-07-01T14:25:43+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":"2026-08-23T03:19:32.205082+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"method","n":2},{"context_role":"baseline","n":1},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"use_method","n":2},{"context_polarity":"baseline","n":1},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}