On Reliability of Patch Correctness Assessment

TL;DR

This paper evaluates the reliability of automated and author-based patch correctness annotations in automatic software repair by constructing a high-quality gold standard through a developer study.

Contribution

It introduces a systematic approach to assess annotation reliability using a gold set created via a user study with professional developers.

Findings

Automated annotation shows limited agreement with the gold set.

Author annotation has subjectivity issues affecting reliability.

The constructed gold set is comparable to other high-quality gold standards.

Abstract

Current state-of-the-art automatic software repair (ASR) techniques rely heavily on incomplete specifications, e.g., test suites, to generate repairs. This, however, may render ASR tools to generate incorrect repairs that do not generalize. To assess patch correctness, researchers have been following two typical ways separately: (1) Automated annotation, wherein patches are automatically labeled by an independent test suite (ITS) - a patch passing the ITS is regarded as correct or generalizable, and incorrect otherwise, (2) Author annotation, wherein authors of ASR techniques annotate correctness labels of patches generated by their and competing tools by themselves. While automated annotation fails to prove that a patch is actually correct, author annotation is prone to subjectivity. This concern has caused an on-going debate on appropriate ways to assess the effectiveness of numerous ASR techniques proposed recently. To address this concern, we propose to assess reliability of author and automated annotations on patch correctness assessment. We do this by first constructing a gold set of correctness labels for 189 randomly selected patches generated by 8 state-of-the-art ASR techniques through a user study involving 35 professional developers as independent annotators. By measuring inter-rater agreement as a proxy for annotation quality - as commonly done in the literature - we demonstrate that our constructed gold set is on par with other high-quality gold sets. We then compare labels generated by author and automated annotations with this gold set to assess reliability of the patch assessment methodologies. We subsequently report several findings and highlight implications for future studies.