{"url":"/task/code-summarization-1","name":"Code Summarization","slug":"code-summarization-1","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":163,"papers_with_code":82,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":8,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/codexglue","name":"CodeXGLUE","full_name":"","num_papers_in_archive":205},{"url":"/dataset/mconala","name":"MCoNaLa","full_name":"Multilingual CoNaLa","num_papers_in_archive":10},{"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/cosqa-1","name":"CoSQA+","full_name":"CoSQA_Plus","num_papers_in_archive":1},{"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},{"url":"/dataset/parallelcorpus-python","name":"ParallelCorpus-Python","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":30,"of":82,"tagged_in_all":163,"items":[{"url":"/paper/a-transformer-based-approach-for-source-code","title":"A Transformer-based Approach for Source Code Summarization","date":"2020-05-01","arxiv_id":"2005.00653","repositories_listed":9,"syntology":null},{"url":"/paper/codexglue-a-machine-learning-benchmark","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","date":"2021-02-09","arxiv_id":"2102.04664","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/recommendations-for-datasets-for-source-code","title":"Recommendations for Datasets for Source Code Summarization","date":"2019-04-04","arxiv_id":"1904.02660","repositories_listed":7,"syntology":null},{"url":"/paper/code2seq-generating-sequences-from-structured","title":"code2seq: Generating Sequences from Structured Representations of Code","date":"2018-08-04","arxiv_id":"1808.01400","repositories_listed":6,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/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","arxiv_id":"2109.00859","repositories_listed":5,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/codet5-open-code-large-language-models-for","title":"CodeT5+: Open Code Large Language Models for Code Understanding and Generation","date":"2023-05-13","arxiv_id":"2305.07922","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/graph-conditioned-sparse-attention-for","title":"Graph Conditioned Sparse-Attention for Improved Source Code Understanding","date":"2021-12-01","arxiv_id":"2112.00663","repositories_listed":2,"syntology":null},{"url":"/paper/retrieval-augmented-code-generation-and","title":"Retrieval Augmented Code Generation and Summarization","date":"2021-08-26","arxiv_id":"2108.11601","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"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/unified-pre-training-for-program","title":"Unified Pre-training for Program Understanding and Generation","date":"2021-03-10","arxiv_id":"2103.06333","repositories_listed":2,"syntology":null},{"url":"/paper/improved-code-summarization-via-a-graph","title":"Improved Code Summarization via a Graph Neural Network","date":"2020-04-06","arxiv_id":"2004.02843","repositories_listed":2,"syntology":null},{"url":"/paper/code-generation-as-a-dual-task-of-code","title":"Code Generation as a Dual Task of Code Summarization","date":"2019-10-14","arxiv_id":"1910.05923","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":3}},{"url":"/paper/improving-automatic-source-code-summarization","title":"Improving Automatic Source Code Summarization via Deep Reinforcement Learning","date":"2018-11-17","arxiv_id":"1811.07234","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/variational-prefix-tuning-for-diverse-and","title":"Variational Prefix Tuning for Diverse and Accurate Code Summarization Using Pre-trained Language Models","date":"2025-05-14","arxiv_id":"2505.09062","repositories_listed":1,"syntology":null},{"url":"/paper/code-summarization-beyond-function-level","title":"Code Summarization Beyond Function Level","date":"2025-02-23","arxiv_id":"2502.16704","repositories_listed":1,"syntology":null},{"url":"/paper/how-to-select-pre-trained-code-models-for","title":"How to Select Pre-Trained Code Models for Reuse? A Learning Perspective","date":"2025-01-07","arxiv_id":"2501.03783","repositories_listed":1,"syntology":null},{"url":"/paper/transducer-tuning-efficient-model-adaptation","title":"Transducer Tuning: Efficient Model Adaptation for Software Tasks Using Code Property Graphs","date":"2024-12-18","arxiv_id":"2412.13467","repositories_listed":1,"syntology":null},{"url":"/paper/model-editing-for-llms4code-how-far-are-we","title":"Model Editing for LLMs4Code: How Far are We?","date":"2024-11-11","arxiv_id":"2411.06638","repositories_listed":1,"syntology":null},{"url":"/paper/building-a-coding-assistant-via-the-retrieval","title":"Building A Coding Assistant via the Retrieval-Augmented Language Model","date":"2024-10-21","arxiv_id":"2410.16229","repositories_listed":1,"syntology":null},{"url":"/paper/xmainframe-a-large-language-model-for","title":"XMainframe: A Large Language Model for Mainframe Modernization","date":"2024-08-05","arxiv_id":"2408.04660","repositories_listed":1,"syntology":null},{"url":"/paper/source-code-summarization-in-the-era-of-large","title":"Source Code Summarization in the Era of Large Language Models","date":"2024-07-09","arxiv_id":"2407.07959","repositories_listed":1,"syntology":null},{"url":"/paper/inversecoder-unleashing-the-power-of","title":"InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct","date":"2024-07-08","arxiv_id":"2407.05700","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":11}},{"url":"/paper/autocoder-enhancing-code-large-language-model","title":"AutoCoder: Enhancing Code Large Language Model with \\textsc{AIEV-Instruct}","date":"2024-05-23","arxiv_id":"2405.14906","repositories_listed":1,"syntology":null},{"url":"/paper/analyzing-the-performance-of-large-language","title":"Analyzing the Performance of Large Language Models on Code Summarization","date":"2024-04-10","arxiv_id":"2404.08018","repositories_listed":1,"syntology":null},{"url":"/paper/csa-trans-code-structure-aware-transformer","title":"CSA-Trans: Code Structure Aware Transformer for AST","date":"2024-04-07","arxiv_id":"2404.05767","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/empirical-studies-of-parameter-efficient","title":"Empirical Studies of Parameter Efficient Methods for Large Language Models of Code and Knowledge Transfer to R","date":"2024-03-16","arxiv_id":"2405.01553","repositories_listed":1,"syntology":null},{"url":"/paper/eyetrans-merging-human-and-machine-attention","title":"EyeTrans: Merging Human and Machine Attention for Neural Code Summarization","date":"2024-02-21","arxiv_id":"2402.14096","repositories_listed":1,"syntology":null},{"url":"/paper/studying-vulnerable-code-entities-in-r","title":"Studying Vulnerable Code Entities in R","date":"2024-02-06","arxiv_id":"2402.04421","repositories_listed":1,"syntology":null},{"url":"/paper/a-prompt-learning-framework-for-source-code","title":"A Prompt Learning Framework for Source Code Summarization","date":"2023-12-26","arxiv_id":"2312.16066","repositories_listed":1,"syntology":null},{"url":"/paper/binary-code-summarization-benchmarking","title":"Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models","date":"2023-12-15","arxiv_id":"2312.09601","repositories_listed":1,"syntology":null}],"syntology_records":9,"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"}}