Abstract: Autoencoder models of source code are an emerging alternative to autoregressive large language models with important benefits for genetic improvement of software. We hypothesize that encoder ...
Our experiment is done in Ubuntu 18.04.6 LTS and in python 3.8. We implement our model by pytorch 1.10 and torch geometric 2.1.0. We train our model on a RTX 3090. The required environments are listed ...
Abstract: Code plagiarism poses a significant challenge in programming communities, necessitating effective detection mechanisms. This paper introduces a novel system that employs Abstract Syntax ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results