{"url":"/dataset/ordinaldataset","name":"OrdinalDataset","full_name":"Ordinal Encoding Data set","description_markdown":"It includes 10 data sets that consists of both raw data set and encoded data set where it is encoded through BERT-Sort Encoder with MLM initialization of .\r\n\r\nIn each data set folder, there are original files and encoded data sets with 4 different MLMs. For instance, bank/bank.csv is the original file for raw data set and bank/bank.csv_bs__roberta.csv is encoded raw data set with BERT-Sort Encoder which is initiated with RoBERTa MLM. Both raw and encoded data sets have been used to evaluate the proposed approach in 5 AutoML platforms.","description_withheld":null,"homepage":"https://github.com/marscod/BERT-Sort","introduced_date":"2022-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","title":"BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML","first_author":"Mehdi Bahrami","url":null},"license":{"name":"MIT License","url":"https://github.com/marscod/BERT-Sort/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"AutoML","url":"/task/automl","datasets_with_task":"/datasets/task/automl"},{"name":"Sentence Ordering","url":"/task/sentence-ordering","datasets_with_task":"/datasets/task/sentence-ordering"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OrdinalDataset"],"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/automl-on-ordinaldataset","task":"AutoML","dataset_variant":"OrdinalDataset","rows":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"Zero-shot-BERT-SORT","paper":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","metrics":{"1:1 Accuracy":"+55%"},"code_links":[{"title":"marscod/BERT-Sort","url":"https://github.com/marscod/BERT-Sort"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/bert-sort-a-zero-shot-mlm-semantic-encoder-on","title":"BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML","date":"2022-06-01","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."}