{"total":29,"rows":[{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2402.16347","title":"CodeS: Towards Building Open-source Language Models for Text-to-SQL","created":"2024-02-26","cited_by_count":187,"area":null},{"id":"2105.13239","title":"CoSQA: 20,000+ Web Queries for Code Search and Question Answering","created":"2021-05-27","cited_by_count":75,"area":null},{"id":"2203.08388","title":"MCoNaLa: A Benchmark for Code Generation from Multiple Natural Languages","created":"2022-03-16","cited_by_count":41,"area":null},{"id":"2202.06649","title":"On the Importance of Building High-quality Training Datasets for Neural Code Search","created":"2022-02-14","cited_by_count":30,"area":null},{"id":"2104.02443","title":"CodeTrans: Towards Cracking the Language of Silicon's Code Through Self-Supervised Deep Learning and High Performance Computing","created":"2021-04-06","cited_by_count":28,"area":null},{"id":"2110.09610","title":"A Survey on Machine Learning Techniques for Source Code Analysis","created":"2021-10-18","cited_by_count":24,"area":null},{"id":"2401.00288","title":"Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit","created":"2023-12-30","cited_by_count":22,"area":null},{"id":"2201.10866","title":"CodeRetriever: Unimodal and Bimodal Contrastive Learning for Code Search","created":"2022-01-26","cited_by_count":21,"area":null},{"id":"2406.07411","title":"VersiCode: Towards Version-controllable Code Generation","created":"2024-06-11","cited_by_count":17,"area":null},{"id":"2506.18951","title":"SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications","created":"2025-06-23","cited_by_count":16,"area":null},{"id":"2403.16702","title":"ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search","created":"2024-03-25","cited_by_count":12,"area":null},{"id":"2209.08372","title":"CodeQueries: A Dataset of Semantic Queries over Code","created":"2022-09-17","cited_by_count":11,"area":null},{"id":"2106.04447","title":"Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation","created":"2021-06-08","cited_by_count":8,"area":null},{"id":"2101.00259","title":"Code Generation from Natural Language with Less Prior and More Monolingual Data","created":"2021-01-01","cited_by_count":6,"area":null},{"id":"2110.04353","title":"Learning to Describe Solutions for Bug Reports Based on Developer Discussions","created":"2021-10-08","cited_by_count":5,"area":null},{"id":"2305.09438","title":"MPI-rical: Data-Driven MPI Distributed Parallelism Assistance with Transformers","created":"2023-05-16","cited_by_count":5,"area":null},{"id":"2311.03798","title":"Noisy Pair Corrector for Dense Retrieval","created":"2023-11-07","cited_by_count":5,"area":null},{"id":"2108.05198","title":"Natural Language-Guided Programming","created":"2021-08-11","cited_by_count":4,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2202.04847","title":"A Survey on Artificial Intelligence for Source Code: A Dialogue Systems Perspective","created":"2022-02-10","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2212.09132","title":"JEMMA: An Extensible Java Dataset for ML4Code Applications","created":"2022-12-18","cited_by_count":2,"area":null},{"id":"2307.02443","title":"An Exploratory Literature Study on Sharing and Energy Use of Language Models for Source Code","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2405.04126","title":"Refining Joint Text and Source Code Embeddings for Retrieval Task with Parameter-Efficient Fine-Tuning","created":"2024-05-07","cited_by_count":1,"area":null},{"id":"2101.07138","title":"Teach me how to Label: Labeling Functions from Natural Language with Text-to-text Transformers","created":"2021-01-18","cited_by_count":0,"area":null},{"id":"2111.00580","title":"Text Classification for Task-based Source Code Related Questions","created":"2021-10-31","cited_by_count":0,"area":null},{"id":"2312.01921","title":"A Machine Learning Approach Towards SKILL Code Autocompletion","created":"2023-12-04","cited_by_count":0,"area":null},{"id":"2603.07229","title":"A Hybrid LTR-based System via Social Context Embedding for Recommending Solutions of Software Bugs in Developer Communities","created":"2026-03-07","cited_by_count":0,"area":null}],"next_cursor":null}