{"url":"/dataset/dataclue","name":"DataCLUE","full_name":null,"description_markdown":"DataCLUE is the first Data-Centric benchmark applied in NLP field.","description_withheld":null,"homepage":"https://github.com/CLUEbenchmark/DataCLUE","introduced_date":"2021-11-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/dataclue-a-benchmark-suite-for-data-centric","title":"DataCLUE: A Benchmark Suite for Data-centric NLP","first_author":"Liang Xu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["DataCLUE"],"data_loaders":[],"num_papers_in_archive":1,"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":"2026-09-24T18:15:14+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."}