arXiv subjects

Ruksit Rojpaisarnkit

Publications and source records attributed to Ruksit Rojpaisarnkit.

7 recordsLinked to original sources

arXiv2026

When is Generated Code Difficult to Comprehend? Assessing AI Agent Python Code Proficiency in the Wild

The rapid adoption of AI coding agents is fundamentally shifting software developers' roles from code authors to code reviewers. While developers spend a significant portion of their time reading and comprehending code, the linguistic proficiency and complexity of the Python code generated by these agents remain largely unexplored. This study investigates the code proficiency of AI agents to determine the skill level required for developers to maintain their code. Leveraging the AIDev dataset, we mined 591 pull requests containing 5,027 Python files generated by three distinct AI agents and employed pycefr, a static analysis tool that maps Python constructs to six proficiency levels, ranging from A1 (Basic) to C2 (Mastery), to analyze the code. Our results reveal that: AI agents predominantly generate Basic-level code, with over 90% of constructs falling into the A1 and A2 categories, and less than 1% classified as Mastery (C2); AI agents' and humans' pull requests share a broadly similar proficiency profile; High-proficiency code by AI agents are from feature addition and bug fixing tasks. These findings suggest that while AI-generated code is generally accessible to developers with basic Python skills, specific tasks may require advanced proficiency to review and maintain complex, agent-generated constructs.

cs.SE↗

arXiv2025

How Natural Language Proficiency Shapes GenAI Code for Software Engineering Tasks

With the widespread adoption of Foundation Model (FM)-powered tools in software engineering, the natural language prompt has become a critical interface between developers and Large Language Models (LLMs). While much research has focused on prompt structure, the natural language proficiency is an underexplored factor that can influence the quality of generated code. This paper investigates whether the English language proficiency itself independent of the prompting technique affects the proficiency and correctness of code generated by LLMs. Using the HumanEval dataset, we systematically varied the English proficiency of prompts from basic to advanced for 164 programming tasks and measured the resulting code proficiency and correctness. Our findings show that LLMs default to an intermediate (B2) natural language level. While the effect on the resulting code proficiency was model-dependent, we found that higher-proficiency prompts consistently yielded more correct code across all models. These results demonstrate that natural language proficiency is a key lever for controlling code generation, helping developers tailor AI output and improve the reliability of solutions.

cs.SE↗

arXiv2024

jscefr: A Framework to Evaluate the Code Proficiency for JavaScript

In this paper, we present jscefr (pronounced jes-cee-fer), a tool that detects the use of different elements of the JavaScript (JS) language, effectively measuring the level of proficiency required to comprehend and deal with a fragment of JavaScript code in software maintenance tasks. Based on the pycefr tool, the tool incorporates JavaScript elements and the well-known Common European Framework of Reference for Languages (CEFR) and utilizes the official ECMAScript JavaScript documentation from the Mozilla Developer Network. jscefr categorizes JS code into six levels based on proficiency. jscefr can detect and classify 138 different JavaScript code constructs. To evaluate, we apply our tool to three JavaScript projects of the NPM ecosystem, with interesting results. A video demonstrating the tool's availability and usage is available at https://youtu.be/Ehh-Prq59Pc.

cs.SE↗

arXiv2024

Towards Identifying Code Proficiency through the Analysis of Python Textbooks

Python, one of the most prevalent programming languages today, is widely utilized in various domains, including web development, data science, machine learning, and DevOps. Recent scholarly efforts have proposed a methodology to assess Python competence levels, similar to how proficiency in natural languages is evaluated. This method involves assigning levels of competence to Python constructs, for instance, placing simple 'print' statements at the most basic level and abstract base classes at the most advanced. The aim is to gauge the level of proficiency a developer must have to understand a piece of source code. This is particularly crucial for software maintenance and evolution tasks, such as debugging or adding new features. For example, in a code review process, this method could determine the competence level required for reviewers. However, categorizing Python constructs by proficiency levels poses significant challenges. Prior attempts, which relied heavily on expert opinions and developer surveys, have led to considerable discrepancies. In response, this paper presents a new approach to identifying Python competency levels through the systematic analysis of introductory Python programming textbooks. By comparing the sequence in which Python constructs are introduced in these textbooks with the current state of the art, we have uncovered notable discrepancies in the order of introduction of Python constructs. Our study underscores a misalignment in the sequences, demonstrating that pinpointing proficiency levels is not trivial. Insights from the study serve as pivotal steps toward reinforcing the idea that textbooks serve as a valuable source for evaluating developers' proficiency, and particularly in terms of their ability to undertake maintenance and evolution tasks.

cs.SE↗

arXiv2024

Characterising Contributions that Coincide with Vulnerability Mitigation in NPM Libraries

With the urgent need to secure supply chains among Open Source libraries, attention has focused on mitigating vulnerabilities detected in these libraries. Although awareness has improved recently, most studies still report delays in the mitigation process. This suggests that developers still have to deal with other contributions that occur during the period of fixing vulnerabilities, such as coinciding Pull Requests (PRs) and Issues, yet the impact of these contributions remains unclear. To characterize these contributions, we conducted a mixed-method empirical study to analyze NPM GitHub projects affected by 554 different vulnerability advisories, mining a total of 4,699 coinciding PRs and Issues. We believe that tool development and improved workload management for developers have the potential to create a more efficient and effective vulnerability mitigation process.

cs.SE↗

arXiv2022

Visualizing Contributor Code Competency for PyPI Libraries: Preliminary Results

Python is known to be used by beginners to professional programmers. Python provides functionality to its community of users through PyPI libraries, which allows developers to reuse functionalities to an application. However, it is unknown the extent to which these PyPI libraries require proficient code in their implementation. We conjecture that PyPI contributors may decide to implement more advanced Pythonic code, or stick with more basic Python code. Are complex codes only committed by few contributors, or only to specific files? The new idea in this paper is to confirm who and where complex code is implemented. Hence, we present a visualization to show the relationship between proficient code, contributors, and files. Analyzing four PyPI projects, we are able to explore which files contain more elegant code, and which contributors committed to these files. Our results show that most files contain more basic competency files, and that not every contributor contributes competent code. We show how~our visualization is able to summarize such information, and opens up different possibilities for understanding how to make elegant contributions.

cs.SE↗

arXiv2022

Intertwining Ecosystems: A Large Scale Empirical Study of Libraries that Cross Software Ecosystems

An increase in diverse technology stacks and third-party library usage has led developers to inevitably switch technologies. To assist these developers, maintainers have started to release their libraries to multiple technologies, i.e., a cross-ecosystem library. Our goal is to explore the extent to which these cross-ecosystem libraries are intertwined between ecosystems. We perform a large-scale empirical study of 1.1 million libraries from five different software ecosystems, i.e., PyPI for Python, CRAN for R, Maven for Java, RubyGems for Ruby, and NPM for JavaScript to identify 4,146 GitHub projects that release libraries to these five ecosystems. Analyzing their contributions, we first find that a significant majority (median of 37.5%) of contributors of these cross-ecosystem libraries come from a single ecosystem, while also receiving a significant portion of contributions (median of 24.06%) from outside their target ecosystems. We also find that a cross-ecosystem library is written using multiple programming languages. Specifically, three (i.e., PyPI, CRAN, RubyGems) out of the five ecosystems has the majority of source code is written using languages not specific to that ecosystem. As ecosystems become intertwined, this opens up new avenues for research, such as whether or not cross-ecosystem libraries will solve the search for replacement libraries, or how these libraries fit within each ecosystem just to name a few.

cs.SE↗