{"url":"/dataset/duolingo-spaced-repetition-data","name":"Duolingo Spaced Repetition Data","full_name":null,"description_markdown":"This is a gzipped CSV file containing the 13 million Duolingo student learning traces used in experiments by Settles & Meeder (2016). For more details and replication source code, visit: https://github.com/duolingo/halflife-regression (2016-06-07)","description_withheld":null,"homepage":"https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/N8XJME","introduced_date":"2016-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-trainable-spaced-repetition-model-for","title":"A Trainable Spaced Repetition Model for Language Learning","first_author":"Burr Settles","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Acquisition","url":"/task/language-acquisition","datasets_with_task":"/datasets/task/language-acquisition"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Multilingual","url":"/datasets/language/multilingual"},{"name":"Portuguese","url":"/datasets/language/portuguese"}],"variants":["Duolingo Spaced Repetition Data"],"data_loaders":[],"num_papers_in_archive":3,"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."}