{"url":"/task/code-classification","name":"Code Classification","slug":"code-classification","description_markdown":null,"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":39,"papers_with_code":15,"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/xcodeeval","name":"xCodeEval","full_name":"xCodeEval","num_papers_in_archive":15},{"url":"/dataset/pytorrent","name":"PyTorrent","full_name":"PyTorrent","num_papers_in_archive":5},{"url":"/dataset/spectre-v1","name":"Spectre-v1","full_name":"","num_papers_in_archive":3},{"url":"/dataset/a-software-maintainability-dataset","name":"A Software Maintainability Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/fixeval","name":"FixEval","full_name":"FixEval","num_papers_in_archive":1},{"url":"/dataset/isadetect-dataset","name":"ISAdetect dataset","full_name":"ISAdetect binary file and object code dataset","num_papers_in_archive":1},{"url":"/dataset/taco-topics-in-algorithmic-code-generation","name":"TACO-BAAI","full_name":"Topics in Algorithmic Code generation dataset","num_papers_in_archive":1},{"url":"/dataset/codescan","name":"CodeSCAN","full_name":"ScreenCast ANalysis for Video Programming Tutorials","num_papers_in_archive":0}],"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":15,"of":15,"tagged_in_all":39,"items":[{"url":"/paper/codes-a-distribution-shift-benchmark-dataset","title":"CodeS: Towards Code Model Generalization Under Distribution Shift","date":"2022-06-11","arxiv_id":"2206.05480","repositories_listed":2,"syntology":null},{"url":"/paper/embedding-java-classes-with-code2vec","title":"Embedding Java Classes with code2vec: Improvements from Variable Obfuscation","date":"2020-04-06","arxiv_id":"2004.02942","repositories_listed":2,"syntology":null},{"url":"/paper/castle-benchmarking-dataset-for-static-code","title":"CASTLE: Benchmarking Dataset for Static Code Analyzers and LLMs towards CWE Detection","date":"2025-03-12","arxiv_id":"2503.09433","repositories_listed":1,"syntology":null},{"url":"/paper/codeprompt-improving-source-code-related","title":"Enhancing Source Code Classification Effectiveness via Prompt Learning Incorporating Knowledge Features","date":"2024-01-10","arxiv_id":"2401.05544","repositories_listed":1,"syntology":null},{"url":"/paper/graph-convolutions-enrich-the-self-attention","title":"Graph Convolutions Enrich the Self-Attention in Transformers!","date":"2023-12-07","arxiv_id":"2312.04234","repositories_listed":1,"syntology":{"n":29,"n_ran":19,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/a-general-purpose-self-supervised-model-for","title":"A General-Purpose Self-Supervised Model for Computational Pathology","date":"2023-08-29","arxiv_id":"2308.15474","repositories_listed":1,"syntology":null},{"url":"/paper/understanding-programs-by-exploiting-fuzzing","title":"Understanding Programs by Exploiting (Fuzzing) Test Cases","date":"2023-05-23","arxiv_id":"2305.13592","repositories_listed":1,"syntology":null},{"url":"/paper/the-earlybird-catches-the-bug-on-exploiting","title":"The EarlyBIRD Catches the Bug: On Exploiting Early Layers of Encoder Models for More Efficient Code Classification","date":"2023-05-08","arxiv_id":"2305.04940","repositories_listed":1,"syntology":null},{"url":"/paper/heterogeneous-directed-hypergraph-neural","title":"Heterogeneous Directed Hypergraph Neural Network over abstract syntax tree (AST) for Code Classification","date":"2023-05-07","arxiv_id":"2305.04228","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-code-classification-by-mixup-based","title":"MIXCODE: Enhancing Code Classification by Mixup-Based Data Augmentation","date":"2022-10-06","arxiv_id":"2210.03003","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-mixup-based-graph-learning-for","title":"On the Effectiveness of Hybrid Pooling in Mixup-Based Graph Learning for Language Processing","date":"2022-10-06","arxiv_id":"2210.03123","repositories_listed":1,"syntology":null},{"url":"/paper/learning-program-semantics-with-code","title":"Learning Program Semantics with Code Representations: An Empirical Study","date":"2022-03-22","arxiv_id":"2203.11790","repositories_listed":1,"syntology":null},{"url":"/paper/semantic-code-classification-for-automated","title":"Semantic Code Classification for Automated Machine Learning","date":"2022-01-25","arxiv_id":"2201.11252","repositories_listed":1,"syntology":null},{"url":"/paper/project-codenet-a-large-scale-ai-for-code","title":"CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Tasks","date":"2021-05-25","arxiv_id":"2105.12655","repositories_listed":1,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/scc-automatic-classification-of-code-snippets","title":"SCC: Automatic Classification of Code Snippets","date":"2018-09-21","arxiv_id":"1809.07945","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"}}