arXiv subjects

Yunhan Qiao

Publications and source records attributed to Yunhan Qiao.

4 recordsLinked to original sources

arXiv2026

Code Comprehension with GitHub Copilot: Performance Gains, Comprehension Trade-offs, and Behavioral Predictors in Brownfield Programming

Teaching Computer Science (CS) students how to comprehend and maintain legacy code bases is a critical challenge in software engineering education. While Generative AI (GenAI) assistants like GitHub Copilot improve task completion speed and correctness, their impact on code understanding remains unclear. We conducted a within-subject study with 15 graduate CS students completing feature implementation tasks with and without Copilot. Despite significant performance improvements, participants showed no overall comprehension improvement ($p=0.59$), revealing a \textit{comprehension-performance decoupling}. Further analysis uncovered a \textit{comprehension trade-off}: performance gains negatively correlated with reverse engineering comprehension ($ρ=-0.57$, $p=0.026$) but showed a positive trend with implementation comprehension ($ρ=0.50$, $p=0.06$). A follow-up behavioral analysis revealed that \textit{how} students used Copilot determined outcomes: Engaging in verification loops in which programmers actively reviewed generated code strongly predicted comprehension ($p<0.001$, $r=0.96$), with high-comprehension participants verifying code 4.7 times more frequently than low-comprehension participants. These findings suggest that GenAI tools do not inherently undermine comprehension; rather, passive consumption patterns do. This suggests a need to alter programming education to teach system-level verification skills, and the need to redesign educational GenAI tools to scaffold active cognitive engagement.

cs.SE↗

arXiv2025

A Systematic Literature Review of the Use of GenAI Assistants for Code Comprehension: Implications for Computing Education Research and Practice

The ability to comprehend code has long been recognized as an essential skill in software engineering. As programmers lean more heavily on generative artificial intelligence (GenAI) assistants to develop code solutions, it is becoming increasingly important for programmers to comprehend GenAI solutions so that they can verify their appropriateness and properly integrate them into existing code. At the same time, GenAI tools are increasingly being enlisted to provide programmers with tailored explanations of code written both by GenAI and humans. Thus, in computing education, GenAI presents new challenges and opportunities for learners who are trying to comprehend computer programs. To provide computing educators with evidence-based guidance on the use of GenAI to facilitate code comprehension and to identify directions for future research, we present a systematic literature review (SLR) of state-of-the-art approaches and tools that leverage GenAI to enhance code comprehension. Our SLR focuses on 31 studies published between 2022 and 2024. Despite their potential, GenAI assistants often yield inaccurate or unclear explanations, and novice programmers frequently struggle to craft effective prompts, thereby impeding their ability to leverage GenAI to aid code comprehension. Our review classifies GenAI-based approaches and tools, identifies methods used to study them, and summarizes the empirical evaluations of their effectiveness. We consider the implications of our findings for computing education research and practice, and identify directions for future research.

cs.SE↗

arXiv2025

The Effects of GitHub Copilot on Computing Students' Programming Effectiveness, Efficiency, and Processes in Brownfield Programming Tasks

When graduates of computing degree programs enter the software industry, they will most likely join teams working on legacy code bases developed by people other than themselves. In these so-called brownfield software development settings, generative artificial intelligence (GenAI) coding assistants like GitHub Copilot are rapidly transforming software development practices, yet the impact of GenAI on student programmers performing brownfield development tasks remains underexplored. This paper investigates how GitHub Copilot influences undergraduate students' programming performance, behaviors, and understanding when completing brownfield programming tasks in which they add new code to an unfamiliar code base. We conducted a controlled experiment in which 10 undergraduate computer science students completed highly similar brownfield development tasks with and without Copilot in a legacy web application. Using a mixed-methods approach combining performance analysis, behavioral analysis, and exit interviews, we found that students completed tasks 35% faster (p < 0.05) and made 50% more solution progress p (< 0.05) when using Copilot. Moreover, our analysis revealed that, when using Copilot, students spent 11% less time manually writing code (p < 0.05), and 12% less time conducting web searches (p < 0.05), providing evidence of a fundamental shift in how they engaged in programming. In exit interviews, students reported concerns about not understanding how or why Copilot suggestions work. This research suggests the need for computing educators to develop new pedagogical approaches that leverage GenAI assistants' benefits while fostering reflection on how and why GenAI suggestions address brownfield programming tasks. Complete study results and analysis are presented at https://ghcopilot-icer.github.io/.

cs.SE↗

arXiv2025

Automatically Detecting Heterogeneous Bugs in High-Performance Computing Scientific Software

Scientific advancements rely on high-performance computing (HPC) applications that model real-world phenomena through simulations. These applications process vast amounts of data on specialized accelerators (eg., GPUs) using special libraries. Heterogeneous bugs occur in these applications when managing data movement across different platforms, such as CPUs and GPUs, leading to divergent behavior when using heterogeneous platforms compared to using only CPUs. Existing software testing techniques often fail to detect such bugs because either they do not account for platform-specific characteristics or target specific platforms. To address this problem, we present HeteroBugDetect, an automated approach to detect platform-dependent heterogeneous bugs in HPC scientific applications. HeteroBugDetect combines natural-language processing, off-target testing, custom fuzzing, and differential testing to provide an end-to-end solution for detecting platform-specific bugs in scientific applications. We evaluate HeteroBugDetect on LAMMPS, a molecular dynamics simulator, where it detected multiple heterogeneous bugs, enhancing its reliability across diverse HPC environments.

cs.SE↗