diff --git a/arxiv-style/main.tex b/arxiv-style/main.tex
index c62f14c..8c7098a 100644
--- a/arxiv-style/main.tex
+++ b/arxiv-style/main.tex
@@ -10,6 +10,7 @@
 \usepackage{amsfonts}       % blackboard math symbols
 \usepackage{nicefrac}       % compact symbols for 1/2, etc.
 \usepackage{microtype}      % microtypography
+\usepackage{amsmath}		% cleveref must be loaded after amsmath!
 \usepackage{cleveref}       % smart cross-referencing
 \usepackage{lipsum}         % Can be removed after putting your text content
 \usepackage{graphicx}
@@ -181,10 +182,10 @@ Discrete ICS variables must remain categorical, making Gaussian diffusion inappr
 
 We therefore adopt masked (absorbing) diffusion for discrete channels, where corruption replaces tokens with a special $\texttt{[MASK]}$ symbol according to a schedule \citep{shi2024simplified}. For each variable $j$, define a masking schedule $\{m_k\}_{k=1}^K$ (with $m_k\in[0,1]$) increasing in $k$. The forward corruption process is:
 \begin{equation}
-q(y^{(j)}_k \mid y^{(j)}_0)=
+q(y^{(j)}_k \mid y^{(j)}_0) =
 \begin{cases}
-y^{(j)}, & \text{with probability } 1-m_k,\\
-\texttt{[MASK]}, & \text{with probability } m_k,
+y^{(j)}_0,            & \text{with probability } 1 - m_k, \\
+\texttt{[MASK]},      & \text{with probability } m_k,
 \end{cases}
 \label{eq:masking_process}
 \end{equation}