@article{honfi-dib-2020, title = "White-box software test generation with Microsoft Pex on open source C\# projects: A dataset", journal = "Data in Brief", volume = "31", eid = "105962", pages = "1-10", year = "2020", publisher = "Elsevier", doi = "https://doi.org/10.1016/j.dib.2020.105962", author = "Dávid Honfi and Zoltán Micskei", keywords = "Software testing, Test generation, Symbolic execution, Code coverage, White-box testing", abstract = "The paper presents a dataset on software tests generated using the Microsoft Pex (IntelliTest) test generator tool for 10 open source projects. The projects were selected randomly from popular GitHub repositories written in C\#. The selected projects contain 7187 methods from which Pex was able to generate tests for 2596 methods totaling 38,618 lines of code. Data collection was performed on a cloud virtual machine. The dataset presents metrics about the attributes of the selected projects (e.g., cyclomatic complexity or number of external method calls) and the test generation (e.g., statement and branch coverage, number of warnings). This data is compared to an automated isolation technique in the paper Automated Isolation for White-box Test Generation [1]. To the best of our knowledge, this is the largest public dataset about the test generation performance of Microsoft Pex on open source projects. The dataset highlights current practical challenges and can be used as a baseline for new test generation techniques." }