{"url":"/dataset/capes","name":"capes","full_name":null,"description_markdown":"Approximately 240,000 documents were collected and aligned using the Hunalign tool.\r\n\r\nSource: [A Parallel Corpus of Theses and Dissertations Abstracts](/paper/a-parallel-corpus-of-theses-and-dissertations)","description_withheld":null,"homepage":"https://sites.google.com/view/felipe-soares/datasets#h.p_kxOR6EhHm2a6","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-parallel-corpus-of-theses-and-dissertations","title":"A Parallel Corpus of Theses and Dissertations Abstracts","first_author":"Felipe Soares","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["capes"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/soarescmsa/capes","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Wauplin/tmp_metadata","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/capes","frameworks":["tf","pytorch","jax"]}],"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":"2026-09-24T18:15:14+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."}