{"work":{"id":"59f1bbd1-2ddb-4173-821f-545a910ec2aa","openalex_id":"https://openalex.org/W3177765786","doi":"10.18653/v1/2022.acl-long.577","arxiv_id":null,"raw_key":null,"title":"URLhttps://doi.org/10.18653/ v1/2022.acl-long.577","authors":null,"authors_text":"doi: 10","year":2022,"venue":"Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","abstract":null,"external_url":"https://doi.org/10.18653/v1/2022.acl-long.577","cited_by_count":257,"metadata_source":"openalex","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-08T18:49:25.448600+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":false,"display_title":"Deduplicating Training Data Makes Language Models Better","render_title":"Deduplicating Training Data Makes Language Models Better"},"hub":{"state":{"work_id":"59f1bbd1-2ddb-4173-821f-545a910ec2aa","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":19,"external_cited_by_count":257,"distinct_field_count":5,"first_pith_cited_at":"2023-03-30T17:30:36+00:00","last_pith_cited_at":"2026-07-09T12:01:40+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":"2026-08-14T07:59:48.289246+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4}],"polarity_counts":[{"context_polarity":"background","n":2},{"context_polarity":"support","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}