{"url":"/dataset/roscoe","name":"ROSCOE","full_name":null,"description_markdown":"**ROSCOE** is a suite of interpretable, unsupervised automatic scores that improve and extend previous text generation evaluation metrics.\r\n\r\nSource: [ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning](https://arxiv.org/pdf/2212.07919v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2212.07919v1.pdf](https://arxiv.org/pdf/2212.07919v1.pdf)","description_withheld":null,"homepage":"https://github.com/facebookresearch/ParlAI/tree/main/projects/roscoe","introduced_date":"2022-12-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/roscoe-a-suite-of-metrics-for-scoring-step-by","title":"ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning","first_author":"Olga Golovneva","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[],"variants":["ROSCOE"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}