Developing a mechanism to study code trustworthiness

Abstract

When software code is acquired from a third party or version control repository, programmers assign a level of trust to the code. This trust prompts them to use the code as-is, make minor changes, or rewrite it, which can increase costs and delay deployment. This paper discusses types of degradations to code based on readability and organization expectations and how to present that code as part of a study on programmer trust. Degradations were applied to sixteen of eighteen Java classes that were labeled as acquired from reputable or unknown sources. In a pilot study, participants were asked to determine a level of trustworthiness and whether they would use the code without changes. The results of the pilot study are presented to provide a baseline for the continuance of the study to a larger set of participants and to make adjustments to the presentation environment to improve user experience.