{"url":"/sota/code-documentation-generation-on-6","task":{"name":"Code Documentation Generation","url":"/task/code-documentation-generation","note":null},"dataset":{"name":"CodeSearchNet","url":"/dataset/codesearchnet"},"category":"Computer Code","categories":["Computer Code"],"category_note":null,"description":"Code Documentation Generation is a supervised task where a code function is the input to the model, and the model generates the documentation for this function.\r\n\r\nDescription from: [CodeTrans: Towards Cracking the Language of Silicone's Code Through Self-Supervised Deep Learning and High Performance Computing](https://arxiv.org/pdf/2104.02443.pdf)","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":["Smoothed BLEU-4"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Smoothed BLEU-4":"higher"}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"CodeBERT (MLM+RTD)","metrics":{"Smoothed BLEU-4":"15.99"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":2,"model":"CodeBERT (MLM)","metrics":{"Smoothed BLEU-4":"15.55"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":3,"model":"pre-train w/ code only","metrics":{"Smoothed BLEU-4":"15.15"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":4,"model":"CodeBERT (RTD)","metrics":{"Smoothed BLEU-4":"15.03"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":5,"model":"RoBERTa","metrics":{"Smoothed BLEU-4":"14.52"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":6,"model":"Transformer","metrics":{"Smoothed BLEU-4":"14.31"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}},{"rank_in_archive_order":7,"model":"seq2seq","metrics":{"Smoothed BLEU-4":"13.36"},"uses_additional_data":false,"paper_date":"2020-02-19","paper":"/paper/codebert-a-pre-trained-model-for-programming","paper_url":"https://arxiv.org/abs/2002.08155v4","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","code":"https://github.com/salesforce/codet5","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4}}],"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":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":18,"n_samples":20,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":126,"n_samples":140,"n_pointer_only_licence":28,"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"}}}