{"url":"/dataset/oos-cg","name":"OOS_CG","full_name":null,"description_markdown":"The dataset identifies the shortcomings of existing benchmarks in evaluating the problem of compositional generalization, which under\u0002scores the need for the development of datasets tailored to assess compositional generalization in open intent detection tasks.","description_withheld":null,"homepage":"https://github.com/fangyihao/gptaug/tree/main/data/oos_cg","introduced_date":"2023-08-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/chatgpt-as-data-augmentation-for","title":"ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection","first_author":"Yihao Fang","url":null},"license":{"name":"MIT License","url":"https://github.com/fangyihao/gptaug/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Open Intent Detection","url":"/task/open-intent-detection","datasets_with_task":"/datasets/task/open-intent-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OOS_CG"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-intent-detection-on-oos-cg","task":"Open Intent Detection","dataset_variant":"OOS_CG","rows":1,"metrics":["F1 Score"],"first_row_in_archive_order":{"model":"ADB+GPTAUG-F4","paper":"/paper/chatgpt-as-data-augmentation-for","metrics":{"F1 Score":"56.18"},"code_links":[{"title":"fangyihao/gptaug","url":"https://github.com/fangyihao/gptaug"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/chatgpt-as-data-augmentation-for","title":"ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection","date":"2023-08-25","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}