{"url":"/dataset/concode","name":"CONCODE","full_name":null,"description_markdown":"A new large dataset with over 100,000 examples consisting of Java classes from online code repositories, and develop a new encoder-decoder architecture that models the interaction between the method documentation and the class environment.\r\n\r\nSource: [Mapping Language to Code in Programmatic Context](/paper/mapping-language-to-code-in-programmatic)","description_withheld":null,"homepage":"https://github.com/sriniiyer/concode","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/mapping-language-to-code-in-programmatic","title":"Mapping Language to Code in Programmatic Context","first_author":"Srinivasan Iyer","url":null},"license":null,"modalities":[],"tasks":[{"name":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"},{"name":"Code Generation","url":"/task/code-generation","datasets_with_task":"/datasets/task/code-generation"},{"name":"Program Synthesis","url":"/task/program-synthesis","datasets_with_task":"/datasets/task/program-synthesis"}],"languages":[],"variants":["CONCODE"],"data_loaders":[{"repo":"https://github.com/sriniiyer/concode","url":"https://github.com/sriniiyer/concode","frameworks":["pytorch"]}],"num_papers_in_archive":46,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/code-generation-on-concode","task":"Code Generation","dataset_variant":"CONCODE","rows":2,"metrics":["Exact Match","BLEU","CodeBLEU"],"first_row_in_archive_order":{"model":"Redcoder-ext","paper":"/paper/retrieval-augmented-code-generation-and","metrics":{"BLEU":"42.5","CodeBLEU":"43.4","Exact Match":"23.4"},"code_links":[{"title":"kagnlp/CodeGenerator","url":"https://github.com/kagnlp/CodeGenerator"},{"title":"rizwan09/redcoder","url":"https://github.com/rizwan09/redcoder"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/codet5-identifier-aware-unified-pre-trained","title":"CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation","date":"2021-09-02","rows_on_this_dataset":1,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":1,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/retrieval-augmented-code-generation-and","title":"Retrieval Augmented Code Generation and Summarization","date":"2021-08-26","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"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":2,"samples_harvested":14,"samples_ran":3,"samples_unverified":11,"pointer_only_for_licence":3,"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."}