{"url":"/dataset/synbols","name":"Synbols","full_name":null,"description_markdown":"Synbols is a dataset generator designed for probing the behavior of learning algorithms. By defining the distribution over latent factors one can craft a dataset specifically tailored to answer specific questions about a given algorithm.\r\n\r\nDefault versions of these datasets are also materialized and can serve as benchmarks.","description_withheld":null,"homepage":"https://github.com/ElementAI/synbols","introduced_date":"2020-09-14","introduced_date_note":null,"introduced_by":{"paper":"/paper/synbols-probing-learning-algorithms-with","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","first_author":"Alexandre Lacoste","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Interactive","url":"/datasets/modality/interactive"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"}],"variants":["Synbols"],"data_loaders":[{"repo":"https://github.com/ElementAI/synbols","url":"https://github.com/ElementAI/synbols","frameworks":[]}],"num_papers_in_archive":11,"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."}