Confident Learning-based Network for Detecting Bug-Inducing Commits on SZZ with Noisy Labels
cs.SE
Submitted: 2026-05-27
Updated: 2026-10-29
Comments: After careful re-evaluation by all authors, we identify critical flaws in the experimental design and validation setup of this preliminary version. The empirical results and related claims cannot be reliably supported. Therefore we withdraw this preprint to avoid misleading readers. A substantially revised and revalidated version will be prepared in the future
Code: https://github.com/Vandbs/BIC-Hunter
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Semi-Supervised Classification with Graph Convolutional Networks
- Identifying Root Cause of bugs by Capturing Changed Code Lines with Relational Graph Neural Networks
- Detecting the Root Cause Code Lines in Bug-Fixing Commits by Heterogeneous Graph Learning
- CodeBERT: A Pre-Trained Model for Programming and Natural Languages
- Adam: A Method for Stochastic Optimization
- DeeperGCN: All You Need to Train Deeper GCNs
- Graph Attention Networks
- Relational Graph Attention Networks
- Topology Adaptive Graph Convolutional Networks
Related papers
- ArkEval: Benchmarking and Evaluating Automated CodeRepair for ArkTS
- TestPrism: Rethinking Test Evaluation Beyond a Single Reference
- Mining Workflow Graphs for Black-Box Boundary Testing of Conversational LLM Agents
- Falsification-Based Verification of LLM-Generated Optimization Models: Sound Test Batteries and Their Detection Limits
- GitSkills: A Dataset of Agent Skills on GitHub
- For Coding Agents, the Repository Matters