Semi-supervised PU learning models predict unrelated CI build failures with precision 0.70-0.88 and AUC 0.63-0.97 across seven Apache projects using 33 features like CI latency and repeated errors.
Support- ing continuous integration by code-churn based test selection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Is this Build Failure Related to my Patch? An Empirical Study of Unrelated Build Failures in Continuous Integration
Semi-supervised PU learning models predict unrelated CI build failures with precision 0.70-0.88 and AUC 0.63-0.97 across seven Apache projects using 33 features like CI latency and repeated errors.