Sample MATLAB code for GRAND has now been released on GitHub, linked through this website

GRAND (Guessing Random Additive Noise Decoding) was developed by Muriel Médard (MIT, USA) with Rabia Tugce Yazicigil (Boston University, USA), Ken R. Duffy (Hamilton Institute, Maynooth University, Ireland) and their groups. GRAND offers a single, energy efficient, precise decoder for a broad swathe of codes with a small footprint, and much more. GRAND is a methodology based on an innovative paradigm. It aims to identify the noise effect that has impacted the data, solely using the codebook for what it is: a hash of that data.

The primary features of GRAND are:

1: Decodes any moderate redundancy code, regardless of structure and length, with provably maximal accuracy.

2: Exists for both soft and hard detection.

3: Is inherently highly parallelizable, resulting in desirably low latency.

4: Has proven energy efficient silicon implementation of hard detection.

Information on the GRAND decoder can be found at Papers, videos, and tutorial slides are available on the website. They highly recommend going over them before getting started on the code. The code is only available for non-commercial purposes.