# Classifying the Correctness of Generated White-Box Tests: An Exploratory Study

## TL;DR

This study explores how developers identify faults in automatically generated white-box tests, revealing significant misclassification rates that suggest current evaluations may overestimate their fault detection capabilities.

## Contribution

It provides empirical evidence on human classification performance of generated tests, highlighting the importance of considering human factors in test evaluation.

## Key findings

- Participants misclassified 33% of fault-encoding tests.
- Participants misclassified 25% of correct tests.
- Human classification errors can lower perceived fault detection capability.

## Abstract

White-box test generator tools rely only on the code under test to select test inputs, and capture the implementation's output as assertions. If there is a fault in the implementation, it could get encoded in the generated tests. Tool evaluations usually measure fault-detection capability using the number of such fault-encoding tests. However, these faults are only detected, if the developer can recognize that the encoded behavior is faulty. We designed an exploratory study to investigate how developers perform in classifying generated white-box test as faulty or correct. We carried out the study in a laboratory setting with 54 graduate students. The tests were generated for two open-source projects with the help of the IntelliTest tool. The performance of the participants were analyzed using binary classification metrics and by coding their observed activities. The results showed that participants incorrectly classified a large number of both fault-encoding and correct tests (with median misclassification rate 33% and 25% respectively). Thus the real fault-detection capability of test generators could be much lower than typically reported, and we suggest to take this human factor into account when evaluating generated white-box tests.