{"work":{"id":"e0787102-2f18-46ad-9660-6bfe466e3bbf","openalex_id":null,"doi":null,"arxiv_id":"2307.06942","raw_key":null,"title":"arXiv preprint arXiv:2307.06942 (2023)","authors":null,"authors_text":"Wang, Y","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2307.06942","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-14T19:39:23.498730+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T06:56:47.327445+00:00","updated_at":"2026-05-14T19:39:23.498730+00:00","title_quality_ok":false,"display_title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","render_title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation"},"hub":{"state":{"work_id":"e0787102-2f18-46ad-9660-6bfe466e3bbf","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":2,"first_pith_cited_at":"2023-12-21T18:59:31+00:00","last_pith_cited_at":"2026-05-13T03:43:02+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":"2026-05-15T00:26:15.343385+00:00","tier_text":"hub"},"tier":"hub","role_counts":[],"polarity_counts":[],"runs":{},"summary":{},"graph":{},"authors":[]}}