# 5G NR CA-Polar Maximum Likelihood Decoding by GRAND

## TL;DR

This paper evaluates the use of GRAND, a universal ML decoding algorithm, for 5G CA-Polar codes, demonstrating its practical feasibility through simulation results.

## Contribution

It introduces the application of GRAND to 5G CA-Polar codes, showing its efficiency and practicality for decoding in real-world scenarios.

## Key findings

- GRAND achieves near-ML decoding performance for 5G CA-Polar codes.
- Soft detection variant of GRAND improves decoding practicality.
- Simulation results confirm feasibility of GRAND for 5G control channels.

## Abstract

CA-Polar codes have been selected for all control channel communications in 5G NR, but accurate, computationally feasible decoders are still subject to development. Here we report the performance of a recently proposed class of optimally precise Maximum Likelihood (ML) decoders, GRAND, that can be used with any block-code. As published theoretical results indicate that GRAND is computationally efficient for short-length, high-rate codes and 5G CA-Polar codes are in that class, here we consider GRAND's utility for decoding them. Simulation results indicate that decoding of 5G CA-Polar codes by GRAND, and a simple soft detection variant, is a practical possibility.