Update manuscript template configuration and presentation

manuscript/main/main.tex

@@ -1,6 +1,6 @@
 % ICASSP 2027 working draft: results and mechanism claims are not yet frozen.
 % Four technical pages maximum; the optional fifth page contains references only.
-% Use the final author kit and resolve every TODO before submission.
+% Uses the repository's ICASSP 2027 author kit; resolve every TODO before submission.
 \documentclass{article}
 \usepackage{spconf}
 \usepackage{amsmath,amssymb,graphicx,hyperref,xcolor}
@@ -278,9 +278,8 @@ person boxes. Dashes indicate unmeasured values; locked rows await the final
 matched dense/boundary reruns.}
 \label{tab:main}
 \centering
-\scriptsize
-\setlength{\tabcolsep}{2.6pt}
-\resizebox{\textwidth}{!}{%
+\normalsize
+\setlength{\tabcolsep}{2pt}
 \begin{tabular}{@{}lccccccccccccc@{}}
 \hline
 & \multicolumn{10}{c}{Dense mAP at prediction horizon (s) $\uparrow$}
@@ -317,7 +316,7 @@ Locked $G+A+V$ (optional)
   & -- & -- & -- & -- & -- & -- & -- & -- & -- & --
   & -- & -- & --\\
 \hline
-\end{tabular}}
+\end{tabular}
 \end{table*}
 
 Alongside these models, a planned causal current-activity classifier repeats
@@ -356,7 +355,7 @@ a matched Qwen 1-Hz control; MiniCPM 5-Hz tail rows require GPU verification.
 
 \subsection{Streaming and Context Analysis}
 
-Table~\ref{tab:ablation} reserves a tail-refresh $\times$ local-audio
+Table~\ref{tab:ablation} reserves a tail-refresh/local-audio
 comparison. Completed-only states update at 2-s closures and are causally
 held between them; tail-aware states use the observed partial block at every
 cutoff. Enabled local audio remains 5~Hz. Common startup rows and valid pairs
@@ -369,7 +368,7 @@ AP (percent). Transfer reports $G+A-G$ deltas (points) after interface audits.
 Dashes are unmeasured, not zero.}
 \label{tab:ablation}
 \centering
-\scriptsize
+\normalsize
 \setlength{\tabcolsep}{3pt}
 \begin{tabular}{@{}lcccc@{}}
 \hline