{"url":"/dataset/codesc","name":"CoDesc","full_name":null,"description_markdown":"**CoDesc** is a large dataset of 4.2m Java source code and parallel data of their description from code search, and code summarization studies.","description_withheld":null,"homepage":"https://github.com/csebuetnlp/CoDesc","introduced_date":"2021-05-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/codesc-a-large-code-description-parallel","title":"CoDesc: A Large Code-Description Parallel Dataset","first_author":"Masum Hasan","url":null},"license":{"name":"MIT License","url":"https://github.com/code-desc/CoDesc/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Source Code Summarization","url":"/task/code-summarization","datasets_with_task":"/datasets/task/code-summarization"},{"name":"Code Search","url":"/task/code-search","datasets_with_task":"/datasets/task/code-search"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CoDesc"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/code-search-on-codesc","task":"Code Search","dataset_variant":"CoDesc","rows":3,"metrics":["Test MRR"],"first_row_in_archive_order":{"model":"Self-attention","paper":"/paper/codesc-a-large-code-description-parallel","metrics":{"Test MRR":"0.839"},"code_links":[{"title":"csebuetnlp/CoDesc","url":"https://github.com/csebuetnlp/CoDesc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/source-code-summarization-on-codesc","task":"Source Code Summarization","dataset_variant":"CoDesc","rows":1,"metrics":["BLEU-4"],"first_row_in_archive_order":{"model":"Transformer","paper":"/paper/codesc-a-large-code-description-parallel","metrics":{"BLEU-4":"45.89"},"code_links":[{"title":"csebuetnlp/CoDesc","url":"https://github.com/csebuetnlp/CoDesc"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/codesc-a-large-code-description-parallel","title":"CoDesc: A Large Code-Description Parallel Dataset","date":"2021-05-29","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":1,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":8,"samples_ran":1,"samples_unverified":7,"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."}