diff --git a/main.tex b/main.tex
index b66a419..8488662 100644
--- a/main.tex
+++ b/main.tex
@@ -555,7 +555,7 @@ spread.}
 We have described the end-to-end pipeline for training a 1.2B Transformer with
 {\sc AstrAI}: data preprocessing with JSON-driven tokenization and packing,
 a 24-layer GQA-SwiGLU architecture, callback-based training with a hybrid
-Muon/AdamW optimizer under DDP/FSDP executors, and cosine scheduling. We
+Muon/AdamW optimizer under DDP/FSDP executors, and WSD scheduling. We
 further analyzed numerical stability under BF16, showing that GPT-2 residual
 scaling ($\sigma_o = 0.02/\sqrt{2L}$) reduces per-block residual variance
 by a factor of 48, keeping post-24-layer variance at $1.34$ versus $17.5$