-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
18 additions
and
16 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,12 @@ | ||
<div class="flex flex-col items-center mt-10 p-4"> | ||
<section class="mb-12 text-center max-w-3xl"> | ||
<div class="flex flex-col space-y-16"> | ||
<!-- Abstract Section --> | ||
<section class="mb-12 w-full"></section> | ||
<h2 class="text-3xl font-semibold mb-8" id="paper">Paper</h2> | ||
<a href="assets/pdf/bugsynth.pdf">[Full pdf]</a> | ||
<p align="left">This paper presents BugSynth, a tool that automatically generates buggy programs by combining language models and program verification techniques. While error benchmarks are becoming increasingly important for evaluating error detectors and addressing the issue of insufficient training data for language models, existing methods for constructing these benchmarks have some limitations. BugSynth automatically generates programs with clearly defined locations of division-by-zero bugs without requiring the original program. Experimental results show that BugSynth achieved a 51% success rate in generation, and it was confirmed that the benchmarks constructed are of similar difficulty to those created by humans when evaluating static analyzers.</p> | ||
</section> | ||
</div> | ||
</section> | ||
</div> |