{"url":"/dataset/column-correlation-data","name":"Column Correlation Data","full_name":null,"description_markdown":"Contains correlation data for 119,384 column pairs, taken from 3,952 data sets, including Pearson correlation, Spearman correlation, and Theil's U. This data can be used, e.g., for approaches that predict column correlation based on column properties, including column names.","description_withheld":null,"homepage":"https://github.com/itrummer/DataCorrelationPredictionWithNLP","introduced_date":"2021-07-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/can-deep-neural-networks-predict-data","title":"Can Deep Neural Networks Predict Data Correlations from Column Names?","first_author":"Immanuel Trummer","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["Column Correlation Data"],"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":"2026-09-25T09:33:49+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."}