{"url":"/dataset/tud","name":"TUD","full_name":"Table Uniformity Dataset","description_markdown":"Dataset to reproduce results for the paper [Detecting CSV file dialects by table uniformity measurement and data type inference](https://content.iospress.com/articles/data-science/ds240062), DOI [ds240062](https://doi.org/10.3233/DS-240062).","description_withheld":null,"homepage":"https://zenodo.org/records/11331538","introduced_date":"2024-02-15","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"CSV dialect detection","url":"/task/csv-dialect-detection","datasets_with_task":"/datasets/task/csv-dialect-detection"}],"languages":[],"variants":["TUD"],"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/csv-dialect-detection-on-tud","task":"CSV dialect detection","dataset_variant":"TUD","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"F1 Score","paper":"/paper/detecting-csv-file-dialects-by-table","metrics":{"1:1 Accuracy":"0.9260"},"code_links":[{"title":"ws-garcia/vba-csv-interface","url":"https://github.com/ws-garcia/vba-csv-interface"},{"title":"ws-garcia/CSVsniffer","url":"https://github.com/ws-garcia/CSVsniffer"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/detecting-csv-file-dialects-by-table","title":"Detecting CSV File Dialects by Table Uniformity Measurement and Data Type Inference","date":"2024-02-15","rows_on_this_dataset":1,"code_links":2,"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."}