{"url":"/sota/code-search-on-codesc","task":{"name":"Code Search","url":"/task/code-search","note":null},"dataset":{"name":"CoDesc","url":"/dataset/codesc"},"category":"Computer Code","categories":["Computer Code"],"category_note":null,"description":"The goal of **Code Search** is to retrieve code fragments from a large code corpus that most closely match a developer’s intent, which is expressed in natural language.\r\n\r\n\r\n<span class=\"description-source\">Source: [When Deep Learning Met Code Search ](https://arxiv.org/abs/1905.03813)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Test MRR"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Test MRR":"higher"}},"counts":{"rows":3,"rows_with_code":3,"rows_with_paper_page":3,"rows_dated":3,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Self-attention","metrics":{"Test MRR":"0.839"},"uses_additional_data":false,"paper_date":"2021-05-29","paper":"/paper/codesc-a-large-code-description-parallel","paper_url":"https://arxiv.org/abs/2105.14220v1","paper_title":"CoDesc: A Large Code-Description Parallel Dataset","code":"https://github.com/csebuetnlp/CoDesc","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"NBOW","metrics":{"Test MRR":"0.812"},"uses_additional_data":false,"paper_date":"2021-05-29","paper":"/paper/codesc-a-large-code-description-parallel","paper_url":"https://arxiv.org/abs/2105.14220v1","paper_title":"CoDesc: A Large Code-Description Parallel Dataset","code":"https://github.com/csebuetnlp/CoDesc","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"RNN","metrics":{"Test MRR":"0.766"},"uses_additional_data":false,"paper_date":"2021-05-29","paper":"/paper/codesc-a-large-code-description-parallel","paper_url":"https://arxiv.org/abs/2105.14220v1","paper_title":"CoDesc: A Large Code-Description Parallel Dataset","code":"https://github.com/csebuetnlp/CoDesc","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":3,"rows_with_any_sample_ran":3,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":1,"n_unverified":7,"n_samples":8,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":3,"n_unverified":21,"n_samples":24,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}