arXiv subjects

Taehyoun Kim

Publications and source records attributed to Taehyoun Kim.

2 recordsLinked to original sources

arXiv2026

ReDef: Do Code Language Models Truly Understand Code Changes for Just-in-Time Software Defect Prediction?

Just-in-Time software defect prediction (JIT-SDP) plays a critical role in prioritizing risky code changes during code review and continuous integration. However, existing datasets often suffer from noisy labels and low precision in identifying bug-inducing commits. To address this, we present ReDef (Revert-based Defect dataset), a high-confidence benchmark of function-level modifications curated from 22 large-scale C/C++ projects. Defective cases are anchored by revert commits, while clean cases are validated through post-hoc history checks. Ambiguous instances are conservatively filtered out via a GPT-assisted triage process involving multiple votes and audits. This pipeline yields 3,164 defective and 10,268 clean modifications, offering substantially more reliable labels than prior resources. Beyond dataset construction, we provide a systematic evaluation of how Code Language Models (CLMs)-specifically CodeBERT, CodeT5+, UniXcoder, and Qwen2.5-reason about code modifications. We first investigate which input encodings most effectively expose change information under five different strategies. We then design four counterfactual perturbation strategies (e.g., swapping added/deleted blocks, inverting diff polarity) to serve as diagnostic probes. We posit that if models genuinely capture change semantics, such distortions should lead to a clear decline in predictive performance. Our results show that compact diff-style encodings consistently outperform whole-function formats across all CLMs, supported by rigorous statistical confirmation. However, under counterfactual tests, performance remains effectively stable, revealing that what appears to be robustness in fact reflects a reliance on superficial cues rather than true semantic understanding.

cs.SE↗

arXiv2025

Deep Synthetic Cross-Project Approaches for Software Reliability Growth Modeling

Software Reliability Growth Models (SRGMs) are widely used to predict software reliability based on defect discovery data collected during testing or operational phases. However, their predictive accuracy often degrades in data-scarce environments, such as early-stage testing or safety-critical systems. Although cross-project transfer learning has been explored to mitigate this issue by leveraging data from past projects, its applicability remains limited due to the scarcity and confidentiality of real-world datasets. To overcome these limitations, we propose Deep Synthetic Cross-project SRGM (DSC-SRGM), a novel approach that integrates synthetic data generation with cross-project transfer learning. Synthetic datasets are generated using traditional SRGMs to preserve the statistical characteristics of real-world defect discovery trends. A cross-correlation-based clustering method is applied to identify synthetic datasets with patterns similar to the target project. These datasets are then used to train a deep learning model for reliability prediction. The proposed method is evaluated on 60 real-world datasets, and its performance is compared with both traditional SRGMs and cross-project deep learning models trained on real-world datasets. DSC-SRGM achieves up to 23.3% improvement in predictive accuracy over traditional SRGMs and 32.2% over cross-project deep learning models trained on real-world datasets. However, excessive use of synthetic data or a naive combination of synthetic and real-world data may degrade prediction performance, highlighting the importance of maintaining an appropriate data balance. These findings indicate that DSC-SRGM is a promising approach for software reliability prediction in data-scarce environments.

cs.SE↗