{"work":{"id":"e9ffc77d-3e81-4a7f-9861-704f9accb1db","openalex_id":null,"doi":null,"arxiv_id":"2211.04325","raw_key":null,"title":"Will we run out of data? limits of llm scaling based on human-generated data, 2024","authors":null,"authors_text":"Pablo Villalobos, Jaime Sevilla, Lennart Heim, Tamay Besiroglu, Marius Hobbhahn, and Anson Ho","year":2022,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2211.04325","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-24T03:08:48.120481+00:00","pith_arxiv_id":null,"created_at":"2026-05-11T00:05:50.334774+00:00","updated_at":"2026-05-24T03:08:48.120481+00:00","title_quality_ok":true,"display_title":"Will we run out of data? an analysis of the limits of scaling datasets in machine learning","render_title":"Will we run out of data? an analysis of the limits of scaling datasets in machine learning"},"hub":{"state":{"work_id":"e9ffc77d-3e81-4a7f-9861-704f9accb1db","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":18,"external_cited_by_count":null,"distinct_field_count":10,"first_pith_cited_at":"2023-05-25T17:18:55+00:00","last_pith_cited_at":"2026-05-18T15:18:29+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":"2026-06-05T05:48:36.941984+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4}],"polarity_counts":[{"context_polarity":"background","n":4}],"runs":{},"summary":{},"graph":{},"authors":[]}}