{"url":"/dataset/sciduet","name":"SciDuet","full_name":null,"description_markdown":"**SciDuet** is a dataset for training and benchmarking models for automating document-to-slides generation. It consists of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). This dataset contains  1,088 papers and 10,034 slides.","description_withheld":null,"homepage":"https://github.com/IBM/document2slides","introduced_date":"2021-05-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/d2s-document-to-slide-generation-via-query","title":"D2S: Document-to-Slide Generation Via Query-Based Text Summarization","first_author":"Edward Sun","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SciDuet"],"data_loaders":[{"repo":"https://github.com/IBM/document2slides","url":"https://github.com/IBM/document2slides","frameworks":[]}],"num_papers_in_archive":4,"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."}