From e68faa388c32e70e04dce136476b7cc0719b22eb Mon Sep 17 00:00:00 2001
From: Ivan Basov <ibasov@nvidia.com>
Date: Mon, 27 Apr 2026 11:01:36 -0700
Subject: [PATCH] Add publication reference

---
 README.md | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/README.md b/README.md
index e2bcb13..1f34366 100644
--- a/README.md
+++ b/README.md
@@ -19,6 +19,7 @@ The public release exposes a **single user-facing config** and a **single runner
 
 ## Table of Contents
 
+- [Publication](#publication)
 - [High-level workflow](#high-level-workflow)
 - [Quick start (train + inference)](#quick-start-train--inference)
 - [Dependencies](#dependencies)
@@ -43,6 +44,17 @@ The public release exposes a **single user-facing config** and a **single runner
 - [Results](#results)
 - [License](#license)
 
+## Publication
+
+This implementation accompanies the paper:
+
+Christopher Chamberland, Jan Olle, Muyuan Li, Scott Thornton, and Igor Baratta,
+"Fast and accurate AI-based pre-decoders for surface codes,"
+[arXiv:2604.12841](https://arxiv.org/abs/2604.12841), 2026.
+[doi:10.48550/arXiv.2604.12841](https://doi.org/10.48550/arXiv.2604.12841)
+
+Please cite the paper if you use this repository in research or published work.
+
 ## High-level workflow
 
 ```text