diff --git a/main.tex b/main.tex
index 01e487f..d8853da 100644
--- a/main.tex
+++ b/main.tex
@@ -154,14 +154,16 @@ pipeline proceeds as follows:
     previously kept sample $\mathbf{s}'$.
 \end{enumerate}
 
-In addition to deduplication, instruction--response pairs whose
-response contains fewer than 15 tokens are discarded.
-Short replies exhibit high per-token variance in both
-conditional and unconditional loss (Appendix~\ref{sec:ifd_bias},
-Figure~\ref{fig:length_bias}), which would otherwise distort
-the IFD-based difficulty estimates used for downstream sample
-selection.  This length floor is applied per-field, analogous to
-the pretraining filter described above.
+A length filter is applied to SFT samples based on the IFD
+length-bias analysis in Appendix~\ref{sec:ifd_bias}
+(Figure~\ref{fig:length_bias}): instruction--response pairs
+whose response contains fewer than 15 tokens are discarded,
+because short replies exhibit both high per-token perplexity
+($L_{\text{uncond}} \approx 6\text{--}8$, PPL~$\approx 400\text{--}3000$)
+and wide variance in both $L_{\text{cond}}$ and $L_{\text{uncond}}$,
+which would distort downstream IFD-based difficulty estimates.
+The threshold is applied per-field, analogous to the pretraining
+filter described above.
 
 \subsection{DPO Data Generation}