{"url":"/task/code-documentation-generation","name":"Code Documentation Generation","slug":"code-documentation-generation","description_markdown":"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)","categories":[{"name":"Computer Code","url":"/area/computer-code"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":8,"papers_with_code":7,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":5,"subtasks":1,"parent_tasks":2},"benchmarks":[{"leaderboard":"/sota/code-documentation-generation-on-1","slug":"code-documentation-generation-on-1","dataset":"CodeSearchNet - Java","dataset_url":"/dataset/codesearchnet","rows_in_archive":8,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"CodeTrans-MT-Large","paper_title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","paper_url":"/paper/codetrans-towards-cracking-the-language-of","paper_date":"2021-04-06","arxiv_id":"2104.02443","code_links":[{"title":"agemagician/CodeTrans","url":"https://github.com/agemagician/CodeTrans"}],"syntology":null}},{"leaderboard":"/sota/code-documentation-generation-on-3","slug":"code-documentation-generation-on-3","dataset":"CodeSearchNet - Php","dataset_url":"/dataset/codesearchnet","rows_in_archive":8,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"CodeTrans-MT-Base","paper_title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","paper_url":"/paper/codetrans-towards-cracking-the-language-of","paper_date":"2021-04-06","arxiv_id":"2104.02443","code_links":[{"title":"agemagician/CodeTrans","url":"https://github.com/agemagician/CodeTrans"}],"syntology":null}},{"leaderboard":"/sota/code-documentation-generation-on-5","slug":"code-documentation-generation-on-5","dataset":"CodeSearchNet - JavaScript","dataset_url":"/dataset/codesearchnet","rows_in_archive":8,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"Transformer","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","paper_url":"/paper/codebert-a-pre-trained-model-for-programming","paper_date":"2020-02-19","arxiv_id":"2002.08155","code_links":[{"title":"salesforce/codet5","url":"https://github.com/salesforce/codet5"},{"title":"microsoft/CodeBERT","url":"https://github.com/microsoft/CodeBERT"},{"title":"graykode/commit-autosuggestions","url":"https://github.com/graykode/commit-autosuggestions"},{"title":"sakirinn/llm4cvd","url":"https://github.com/sakirinn/llm4cvd"},{"title":"zhangzwwww/dietcode","url":"https://github.com/zhangzwwww/dietcode"},{"title":"zhangzwwww/dietcodebert","url":"https://github.com/zhangzwwww/dietcodebert"},{"title":"zfj1998/CodeBert-Code2Text","url":"https://github.com/zfj1998/CodeBert-Code2Text"},{"title":"JasonZhu-WHU/CoderAssistant","url":"https://github.com/JasonZhu-WHU/CoderAssistant"},{"title":"aminatadjer/test","url":"https://github.com/aminatadjer/test"}],"syntology":{"n":20,"n_ran":2,"n_unverified":18,"n_pointer_only":4}}},{"leaderboard":"/sota/code-documentation-generation-on","slug":"code-documentation-generation-on","dataset":"CodeSearchNet - Python","dataset_url":"/dataset/codesearchnet","rows_in_archive":7,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"CodeTrans-MT-Base","paper_title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","paper_url":"/paper/codetrans-towards-cracking-the-language-of","paper_date":"2021-04-06","arxiv_id":"2104.02443","code_links":[{"title":"agemagician/CodeTrans","url":"https://github.com/agemagician/CodeTrans"}],"syntology":null}},{"leaderboard":"/sota/code-documentation-generation-on-2","slug":"code-documentation-generation-on-2","dataset":"CodeSearchNet - Go","dataset_url":"/dataset/codesearchnet","rows_in_archive":7,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"CodeBERT (MLM)","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","paper_url":"/paper/codebert-a-pre-trained-model-for-programming","paper_date":"2020-02-19","arxiv_id":"2002.08155","code_links":[{"title":"salesforce/codet5","url":"https://github.com/salesforce/codet5"},{"title":"microsoft/CodeBERT","url":"https://github.com/microsoft/CodeBERT"},{"title":"graykode/commit-autosuggestions","url":"https://github.com/graykode/commit-autosuggestions"},{"title":"sakirinn/llm4cvd","url":"https://github.com/sakirinn/llm4cvd"},{"title":"zhangzwwww/dietcode","url":"https://github.com/zhangzwwww/dietcode"},{"title":"zhangzwwww/dietcodebert","url":"https://github.com/zhangzwwww/dietcodebert"},{"title":"zfj1998/CodeBert-Code2Text","url":"https://github.com/zfj1998/CodeBert-Code2Text"},{"title":"JasonZhu-WHU/CoderAssistant","url":"https://github.com/JasonZhu-WHU/CoderAssistant"},{"title":"aminatadjer/test","url":"https://github.com/aminatadjer/test"}],"syntology":{"n":20,"n_ran":2,"n_unverified":18,"n_pointer_only":4}}},{"leaderboard":"/sota/code-documentation-generation-on-4","slug":"code-documentation-generation-on-4","dataset":"CodeSearchNet - Ruby","dataset_url":"/dataset/codesearchnet","rows_in_archive":7,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"CodeTrans-MT-Base","paper_title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","paper_url":"/paper/codetrans-towards-cracking-the-language-of","paper_date":"2021-04-06","arxiv_id":"2104.02443","code_links":[{"title":"agemagician/CodeTrans","url":"https://github.com/agemagician/CodeTrans"}],"syntology":null}},{"leaderboard":"/sota/code-documentation-generation-on-6","slug":"code-documentation-generation-on-6","dataset":"CodeSearchNet","dataset_url":"/dataset/codesearchnet","rows_in_archive":7,"metrics":["Smoothed BLEU-4"],"first_row_in_archive_order":{"model":"CodeBERT (MLM+RTD)","paper_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","paper_url":"/paper/codebert-a-pre-trained-model-for-programming","paper_date":"2020-02-19","arxiv_id":"2002.08155","code_links":[{"title":"salesforce/codet5","url":"https://github.com/salesforce/codet5"},{"title":"microsoft/CodeBERT","url":"https://github.com/microsoft/CodeBERT"},{"title":"graykode/commit-autosuggestions","url":"https://github.com/graykode/commit-autosuggestions"},{"title":"sakirinn/llm4cvd","url":"https://github.com/sakirinn/llm4cvd"},{"title":"zhangzwwww/dietcode","url":"https://github.com/zhangzwwww/dietcode"},{"title":"zhangzwwww/dietcodebert","url":"https://github.com/zhangzwwww/dietcodebert"},{"title":"zfj1998/CodeBert-Code2Text","url":"https://github.com/zfj1998/CodeBert-Code2Text"},{"title":"JasonZhu-WHU/CoderAssistant","url":"https://github.com/JasonZhu-WHU/CoderAssistant"},{"title":"aminatadjer/test","url":"https://github.com/aminatadjer/test"}],"syntology":{"n":20,"n_ran":2,"n_unverified":18,"n_pointer_only":4}}}],"datasets":[{"url":"/dataset/codesearchnet","name":"CodeSearchNet","full_name":"","num_papers_in_archive":308},{"url":"/dataset/pytorrent","name":"PyTorrent","full_name":"PyTorrent","num_papers_in_archive":5},{"url":"/dataset/deepcom-java","name":"DeepCom-Java","full_name":"","num_papers_in_archive":2},{"url":"/dataset/hybrid-deepcom-java","name":"Java scripts","full_name":"","num_papers_in_archive":1},{"url":"/dataset/notebookcdg","name":"notebookcdg","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/codesearchnet-java","name":"CodeSearchNet - Java"}],"parent_tasks":[{"url":"/task/code-generation","name":"Code Generation"},{"url":"/task/text-generation","name":"Text Generation"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":8,"items":[{"url":"/paper/codebert-a-pre-trained-model-for-programming","title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","date":"2020-02-19","arxiv_id":"2002.08155","repositories_listed":9,"syntology":{"n":20,"n_ran":2,"n_unverified":18,"n_pointer_only":4}},{"url":"/paper/memorization-and-generalization-in-neural","title":"Memorization and Generalization in Neural Code Intelligence Models","date":"2021-06-16","arxiv_id":"2106.08704","repositories_listed":2,"syntology":null},{"url":"/paper/haconvgnn-hierarchical-attention-based","title":"HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebooks","date":"2021-03-31","arxiv_id":"2104.01002","repositories_listed":2,"syntology":null},{"url":"/paper/docagent-a-multi-agent-system-for-automated","title":"DocAgent: A Multi-Agent System for Automated Code Documentation Generation","date":"2025-04-11","arxiv_id":"2504.08725","repositories_listed":1,"syntology":null},{"url":"/paper/repoagent-an-llm-powered-open-source","title":"RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation","date":"2024-02-26","arxiv_id":"2402.16667","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/assemble-foundation-models-for-automatic-code","title":"Assemble Foundation Models for Automatic Code Summarization","date":"2022-01-13","arxiv_id":"2201.05222","repositories_listed":1,"syntology":null},{"url":"/paper/codetrans-towards-cracking-the-language-of","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","date":"2021-04-06","arxiv_id":"2104.02443","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}