# Characterizing Developer Use of Automatically Generated Patches

## TL;DR

This study investigates how developers utilize automatically generated patches in fixing software defects, revealing that access to such patches does not necessarily improve correctness or speed, but influences understanding and focus during repair.

## Contribution

It provides the first empirical characterization of developer interactions with automatically generated patches in real defect fixing scenarios.

## Key findings

- Access to generated patches does not increase correct fixes.
- Developers focus on understanding defects and patch relationships.
- Generated patches influence developer behavior and focus.

## Abstract

We present a study that characterizes the way developers use automatically generated patches when fixing software defects. Our study tasked two groups of developers with repairing defects in C programs. Both groups were provided with the defective line of code. One was also provided with five automatically generated and validated patches, all of which modified the defective line of code, and one of which was correct. Contrary to our initial expectations, the group with access to the generated patches did not produce more correct patches and did not produce patches in less time. We characterize the main behaviors observed in experimental subjects: a focus on understanding the defect and the relationship of the patches to the original source code. Based on this characterization, we highlight various potentially productive directions for future developer-centric automatic patch generation systems.