If you use Megadiff, please cite the following technical report: "Megadiff: A Dataset of 600k Java Source Code Changes Categorized by Diff Size". Technical Report 2108.04631, Arxiv; 2021.

Abstract: Digital elevation models (DEMs) are crucial for modeling and analyzing terrestrial environments, but voids in DEMs can compromise their downstream use. Diff-DEM is a self-supervised method ...