{"work":{"id":"92cf0344-30a9-4e1f-abf7-129e5682dcda","openalex_id":null,"doi":null,"arxiv_id":"2305.13169","raw_key":null,"title":"A pretrainer's guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity, 2023","authors":null,"authors_text":"Longpre, Shayne, Gregory Yauney, Emily Reif, Katherine Lee, Adam Roberts, Barret Zoph, Denny Zhou, Jason Wei, Kevin Robinson, David Mimno, et al","year":2023,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2305.13169","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-24T08:49:13.918939+00:00","pith_arxiv_id":null,"created_at":"2026-05-10T22:46:40.214664+00:00","updated_at":"2026-05-24T08:49:13.918939+00:00","title_quality_ok":true,"display_title":"A pretrainer’s guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity","render_title":"A pretrainer’s guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity"},"hub":{"state":{"work_id":"92cf0344-30a9-4e1f-abf7-129e5682dcda","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2023-03-31T17:28:46+00:00","last_pith_cited_at":"2026-05-21T05:02:51+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":"2026-05-27T05:07:28.801105+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}