{"total":23,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252,"area":null},{"id":"2308.01861","title":"ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation","created":"2023-08-03","cited_by_count":168,"area":null},{"id":"2307.14936","title":"PanGu-Coder2: Boosting Large Language Models for Code with Ranking Feedback","created":"2023-07-27","cited_by_count":69,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"area":null},{"id":"2306.10763","title":"Guiding Language Models of Code with Global Context using Monitors","created":"2023-06-19","cited_by_count":20,"area":null},{"id":"2503.17502","title":"Large Language Models (LLMs) for Source Code Analysis: applications, models and datasets","created":"2025-03-21","cited_by_count":16,"area":null},{"id":"2304.03816","title":"Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptions","created":"2023-04-07","cited_by_count":14,"area":null},{"id":"2406.18294","title":"Hierarchical Context Pruning: Optimizing Real-World Code Completion with Repository-Level Pretrained Code LLMs","created":"2024-06-26","cited_by_count":13,"area":null},{"id":"2504.08734","title":"Towards an Understanding of Context Utilization in Code Intelligence","created":"2025-04-11","cited_by_count":10,"area":null},{"id":"2406.01359","title":"R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models","created":"2024-06-03","cited_by_count":9,"area":null},{"id":"2404.18255","title":"PatentGPT: A Large Language Model for Intellectual Property","created":"2024-04-28","cited_by_count":8,"area":null},{"id":"2403.15747","title":"CodeShell Technical Report","created":"2024-03-23","cited_by_count":6,"area":null},{"id":"2406.15325","title":"Bug In the Code Stack: Can LLMs Find Bugs in Large Python Code Stacks","created":"2024-06-21","cited_by_count":6,"area":null},{"id":"2403.16097","title":"Can Language Models Pretend Solvers? Logic Code Simulation with LLMs","created":"2024-03-24","cited_by_count":4,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2309.07804","title":"Pop Quiz! Do Pre-trained Code Models Possess Knowledge of Correct API Names?","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2402.12782","title":"Advancing GenAI Assisted Programming--A Comparative Study on Prompt Efficiency and Code Quality Between GPT-4 and GLM-4","created":"2024-02-20","cited_by_count":3,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2409.05028","title":"GUI Test Migration via Abstraction and Concretization","created":"2024-09-08","cited_by_count":1,"area":null},{"id":"2504.20673","title":"CoCo-Bench: A Comprehensive Code Benchmark For Multi-task Large Language Model Evaluation","created":"2025-04-29","cited_by_count":1,"area":null},{"id":"2607.11245","title":"An Empirical Study for Android-to-OpenHarmony GUI Test Migration","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}