{"url":"/dataset/spoc","name":"SPoC","full_name":"Pseudocode-to-Code","description_markdown":"Pseudocode-to-Code (SPoC) is a program synthesis dataset, containing 18,356 programs with human-authored pseudocode and test cases.\r\n\r\nImage source: [https://sumith1896.github.io/spoc/](https://sumith1896.github.io/spoc/)","description_withheld":null,"homepage":"https://sumith1896.github.io/spoc/","introduced_date":"2019-06-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/spoc-search-based-pseudocode-to-code","title":"SPoC: Search-based Pseudocode to Code","first_author":"Sumith Kulal","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Program Synthesis","url":"/task/program-synthesis","datasets_with_task":"/datasets/task/program-synthesis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["SPoC TestP","SPoC TestW","SPoC"],"data_loaders":[{"repo":"https://github.com/uniqueram/LSTM-based-Stock-market-prediction-Project","url":"https://github.com/uniqueram/LSTM-based-Stock-market-prediction-Project","frameworks":[]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/program-synthesis-on-spoc-testp","task":"Program Synthesis","dataset_variant":"SPoC TestP","rows":2,"metrics":["Success rate @budget 100"],"first_row_in_archive_order":{"model":"DrRepair","paper":"/paper/graph-based-self-supervised-program-repair","metrics":{"Success rate @budget 100":"38.5"},"code_links":[{"title":"michiyasunaga/DrRepair","url":"https://github.com/michiyasunaga/DrRepair"},{"title":"worksheets/0x01838644","url":"https://worksheets.codalab.org/worksheets/0x01838644724a433c932bef4cb5c42fbd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/program-synthesis-on-spoc-testw","task":"Program Synthesis","dataset_variant":"SPoC TestW","rows":2,"metrics":["Success rate @budget 100"],"first_row_in_archive_order":{"model":"DrRepair","paper":"/paper/graph-based-self-supervised-program-repair","metrics":{"Success rate @budget 100":"57.0"},"code_links":[{"title":"michiyasunaga/DrRepair","url":"https://github.com/michiyasunaga/DrRepair"},{"title":"worksheets/0x01838644","url":"https://worksheets.codalab.org/worksheets/0x01838644724a433c932bef4cb5c42fbd"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/graph-based-self-supervised-program-repair","title":"Graph-based, Self-Supervised Program Repair from Diagnostic Feedback","date":"2020-05-20","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":4,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/spoc-search-based-pseudocode-to-code","title":"SPoC: Search-based Pseudocode to Code","date":"2019-06-12","rows_on_this_dataset":2,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":6,"samples_ran":4,"samples_unverified":2,"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."}