Condense targeted analysis tables

manuscript/targeted/main.tex

@@ -327,8 +327,8 @@ Completed blocks + observed tail & 70.85 & 59.17 & -- \\
 
 \fi
 \begin{table}[t]
-\caption{Pending paired $\G\rightarrow\G+\A$ transfer (unmeasured).
-EC is EasyCom; MiniCPM first needs readout/refresh/history audits.}
+\caption{Pending paired $\G\rightarrow\G+\A$ comparison on EasyCom
+across Qwen2.5-Omni backbone sizes (unmeasured).}
 \label{tab:backbone}
 \centering\normalsize
 \setlength{\tabcolsep}{3pt}
@@ -336,10 +336,8 @@ EC is EasyCom; MiniCPM first needs readout/refresh/history audits.}
 \toprule
 Backbone & $\G$ & $\G+\A$ & $\Delta$ \\
 \midrule
-EC: Omni 3B & -- & -- & -- \\
-EC: Omni 7B & -- & -- & -- \\
-EC: MiniCPM-o 4.5 & -- & -- & -- \\
-Ego4D: Omni 3B & -- & -- & -- \\
+Omni 3B & -- & -- & -- \\
+Omni 7B & -- & -- & -- \\
 \bottomrule
 \end{tabular}
 \end{table}
@@ -508,14 +506,16 @@ shared GRU, while head capacity and training batch differ; raw boundary
 metrics and repeat seeds are unavailable. Thus the +0.66/+0.43-point
 difference does not isolate visual motion or floor behavior.
 
-The analysis-only audit in Table~\ref{tab:oracle} substitutes two seconds
+The lower block of Table~\ref{tab:visual} is an analysis-only audit that
+substitutes two seconds
 of transcript-derived, strictly past visible-person activity on the 5-Hz
-grid. It tests visibility alone, per-person histories, shuffled identities,
-a one-second delay, and OR-pooled activity. These privileged labels are
+grid. The displayed conditions test visibility alone, a one-second delay,
+and OR-pooled activity. These privileged labels are
 neither deployable visual features nor a performance upper bound.
-Aggregate visible
-activity improves over the audio baseline by 4.826 points at 0.2~s and 1.775
-mean-mAP points.  Visibility alone changes mean mAP by only +0.040, and
+The three-seed audio baseline is 81.87\% at 0.2~s and 65.18\% mean mAP;
+aggregate visible activity improves on it by 4.826 and 1.775 points,
+respectively.
+Visibility alone changes mean mAP by only +0.040, and
 one-second-delayed activity by +0.164.  Thus availability or extra parameters
 cannot explain the oracle gain.  Per-person activity exceeds shuffled identity
 by only 0.200 mean-mAP points and is itself 0.291 below the aggregate