AgentSZZ is an LLM-agent framework that identifies bug-inducing commits with up to 27.2% higher F1 scores than prior methods by enabling adaptive exploration and causal tracing, especially for cross-file and ghost commits.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SE 2years
2026 2roles
background 1polarities
background 1representative citing papers
Large-scale experiments reveal that uncertainty quantification in defect prediction is highly context-dependent, with UQ-performance and UQ-calibration correlations varying by setting and often weakening or reversing in cross-project scenarios.
citing papers explorer
-
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
AgentSZZ is an LLM-agent framework that identifies bug-inducing commits with up to 27.2% higher F1 scores than prior methods by enabling adaptive exploration and causal tracing, especially for cross-file and ghost commits.
-
Understanding Software Defect Prediction: A Large-scale Empirical Study Across Uncertainty Quantification and Performance Evaluation
Large-scale experiments reveal that uncertainty quantification in defect prediction is highly context-dependent, with UQ-performance and UQ-calibration correlations varying by setting and often weakening or reversing in cross-project scenarios.