AgenticSZZ reframes bug-inducing commit identification as temporal knowledge graph search navigated by an LLM agent, reporting F1 scores of 0.47-0.79 and up to 34% improvement over prior SZZ methods on three datasets.
Software Eng.39, 6 (2013), 757–773
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.SE 3years
2026 3representative citing papers
Diff-only features, especially structural code complexity, predict risky commits at F1 ~0.81 across Prime Video and ApacheJIT, while raw change-volume metrics add noise.
EZR.py shows that a compact, readable Python toolkit can match or exceed state-of-the-art tools like SHAP, LIME, SMAC3, and FASTREAD on over 120 tabular SE tasks while running 500 times faster and using far less labeled data.
citing papers explorer
-
AgenticSZZ: Temporal Knowledge Graph-Guided Agentic Bug-Inducing Commit Identification
AgenticSZZ reframes bug-inducing commit identification as temporal knowledge graph search navigated by an LLM agent, reporting F1 scores of 0.47-0.79 and up to 34% improvement over prior SZZ methods on three datasets.
-
Deployment Risk Assessment Using Diff-Aware Features: A Case Study at Prime Video
Diff-only features, especially structural code complexity, predict risky commits at F1 ~0.81 across Prime Video and ApacheJIT, while raw change-volume metrics add noise.
-
Can AI be Easy? Lessons Learned from the EZR.py Toolkit
EZR.py shows that a compact, readable Python toolkit can match or exceed state-of-the-art tools like SHAP, LIME, SMAC3, and FASTREAD on over 120 tabular SE tasks while running 500 times faster and using far less labeled data.