Contextual Predictive Mutation Testing

TL;DR

MutationBERT is a novel machine learning approach that improves the accuracy and efficiency of predictive mutation testing by encoding mutation and test context, reducing computational costs and enhancing detection performance.

Contribution

This paper introduces MutationBERT, a new encoding method for predictive mutation testing that outperforms existing approaches in precision, recall, and F1 score, and reduces testing time.

Findings

MutationBERT saves 33% of testing time compared to prior methods.

It outperforms state-of-the-art in both same project and cross project settings.

It improves detection of hard-to-find mutants.

Abstract

Mutation testing is a powerful technique for assessing and improving test suite quality that artificially introduces bugs and checks whether the test suites catch them. However, it is also computationally expensive and thus does not scale to large systems and projects. One promising recent approach to tackling this scalability problem uses machine learning to predict whether the tests will detect the synthetic bugs, without actually running those tests. However, existing predictive mutation testing approaches still misclassify 33% of detection outcomes on a randomly sampled set of mutant-test suite pairs. We introduce MutationBERT, an approach for predictive mutation testing that simultaneously encodes the source method mutation and test method, capturing key context in the input representation. Thanks to its higher precision, MutationBERT saves 33% of the time spent by a prior approach on checking/verifying live mutants. MutationBERT, also outperforms the state-of-the-art in both same project and cross project settings, with meaningful improvements in precision, recall, and F1 score. We validate our input representation, and aggregation approaches for lifting predictions from the test matrix level to the test suite level, finding similar improvements in performance. MutationBERT not only enhances the state-of-the-art in predictive mutation testing, but also presents practical benefits for real-world applications, both in saving developer time and finding hard to detect mutants.