Add wide evaluation table and qualitative placeholder

manuscript/main/main.tex

@@ -339,9 +339,12 @@ non-wearer release. It resolves positively when the wearer enters, or
 negatively when the same non-wearer resumes or a different non-wearer takes the
 next floor. From the first causal 5-Hz state that observes the release, the
 entry score is the maximum projected wearer probability before that competing
-resolution, capped at 2.0~s. Positive entries without a reviewer-selected
-release are reported as unanchored and excluded from this matched-opportunity
-analysis; they remain available to the separate raw-onset analysis.
+resolution, capped at 2.0~s. A selected-release positive is excluded if another
+non-wearer onset occurs before or exactly at the wearer entry, or if wearer
+activity already occurred after the selected release. Positive entries without
+a reviewer-selected release are reported as unanchored and excluded from this
+matched-opportunity analysis; they remain available to the separate raw-onset
+analysis.
 
 An INT opportunity begins when a non-wearer starts while the wearer holds the
 floor. It resolves positively when the reviewed behavior is an INT-yield, and
@@ -352,8 +355,9 @@ strictly at the competing non-wearer offset. All prediction values are read
 diagonally from one causal source row of the target-aligned forecast tensor.
 No input after the observed action outcome is used. For current INT-positive
 annotations, which do not select a competing onset explicitly, the
-implementation uses the latest supplied non-wearer interval crossing the
-wearer offset and surfaces cases with multiple eligible intervals for audit.
+implementation evaluates only a unique supplied non-wearer interval crossing
+the wearer offset; cases with multiple eligible intervals are excluded and
+counted for audit rather than assigned an arbitrary onset.
 
 The headline entry hard negatives are same-speaker mid-turn pauses and other-
 to-other transfers. Wearer backchannels are not pooled into headline false-
@@ -394,42 +398,57 @@ latency claim.
 
 \subsection{Main Comparison}
 
-Table~\ref{tab:main} compares the proposed causal local audiovisual adapter
-with an EgoSpeak reproduction, the frozen Qwen2.5-Omni-3B global state $G$,
-matched PEFT, $G$ plus recent local audio, and a parameter- and history-matched
-temporal local branch. Qwen2.5-Omni-7B is included only as a capacity-scaling
-control. All methods use the same split, causal inputs, targets, and evaluation
-protocol. Event thresholds are selected on training-side calibration data and
-frozen before test evaluation. \todo{Freeze all baseline implementations and
-verify identical targets, causal validity, and evaluation.}
+Table~\ref{tab:main} places the released EgoSpeak checkpoint beside the
+currently available Omni screening runs and reserves a row for the final causal
+local audiovisual model. Historical unmatched runs are identified explicitly
+and cannot support confirmatory attribution. The final comparison will use the
+same split, causal inputs, targets, training/selection protocol, and three
+random seeds; event thresholds will be selected on training-side calibration
+data and frozen before test evaluation. \todo{Freeze all baseline
+implementations and verify identical targets, causal validity, and evaluation.}
 
-\begin{table}[t]
-\caption{Confirmatory EasyCom results. Entry and INT false-positive rates use
-the opportunity-conditioned activity score at matched recall $R=0.8$; E/I AP
-is the corresponding opportunity AP. Event results will be populated only
-after protocol-v2 reruns and human adjudication.}
+\begin{table*}[t]
+\caption{EasyCom Sessions~1--3 dense future-activity and raw-boundary
+screening. All values are percentages. ``Avg.'' averages dense mAP over the ten
+horizons; On/Off are mean raw wearer onset/offset AP and are timing diagnostics,
+not semantic ENTRY/INT scores. $\dagger$ denotes historical seed-0 runs with an
+unmatched training/selection protocol; $\ddagger$ denotes a three-seed screen.
+Missing horizon curves and the final matched comparison will be filled after
+the matched dense/boundary reruns.}
 \label{tab:main}
 \centering
-\small
-\resizebox{\columnwidth}{!}{%
-\begin{tabular}{lccccc}
+\scriptsize
+\setlength{\tabcolsep}{2.6pt}
+\resizebox{\textwidth}{!}{%
+\begin{tabular}{@{}lccccccccccccc@{}}
 \hline
-Method & 0.2-s mAP $\uparrow$ & Mean mAP $\uparrow$
-& Entry FPR@$R=.8$ $\downarrow$ & INT FPR@$R=.8$ $\downarrow$ & E/I AP $\uparrow$\\
+& \multicolumn{10}{c}{Dense mAP at prediction horizon (s) $\uparrow$}
+& & \multicolumn{2}{c}{Raw boundary AP $\uparrow$}\\
+\cline{2-11}\cline{13-14}
+Method & .2 & .4 & .6 & .8 & 1.0 & 1.2 & 1.4 & 1.6 & 1.8 & 2.0
+& Avg. & On & Off\\
 \hline
-EgoSpeak MiniROADA A+V      & 74.12 & 61.16 & \todo{--} & \todo{--} & \todo{--/--}\\
-Omni-3B frozen $G$          & \todo{--} & \todo{--} & \todo{--} & \todo{--} & \todo{--/--}\\
-Omni-3B matched PEFT        & \todo{--} & \todo{--} & \todo{--} & \todo{--} & \todo{--/--}\\
-$G+$local audio             & \todo{--} & \todo{--} & \todo{--} & \todo{--} & \todo{--/--}\\
-$G+$matched temporal local  & \todo{--} & \todo{--} & \todo{--} & \todo{--} & \todo{--/--}\\
-$G+$causal local AV (ours)  & \todo{--} & \todo{--} & \todo{--} & \todo{--} & \todo{--/--}\\
-Omni-7B scaling control     & \todo{--} & \todo{--} & \todo{--} & \todo{--} & \todo{--/--}\\
+EgoSpeak MiniROADA A+V
+  & 74.20 & 68.35 & 64.31 & 61.13 & 59.77 & 58.81 & 57.50 & 57.09 & 55.95 & 54.82
+  & 61.19 & 24.49 & 38.02\\
+Omni $G{+}A^{\dagger}$
+  & 81.72 & -- & -- & -- & -- & -- & -- & -- & -- & --
+  & 65.11 & 25.96 & 45.25\\
+Omni $G{+}A{+}$pooled-$V^{\dagger}$
+  & 82.03 & -- & -- & -- & -- & -- & -- & -- & -- & --
+  & 65.40 & 26.02 & 45.37\\
+Current-frame F1$^{\ddagger}$
+  & $81.78{\pm}0.16$ & -- & -- & -- & -- & -- & -- & -- & -- & --
+  & $64.95{\pm}0.09$ & -- & --\\
+$G+$causal local AV (ours)
+  & -- & -- & -- & -- & -- & -- & -- & -- & -- & --
+  & -- & -- & --\\
 \hline
 \end{tabular}}
-\end{table}
+\end{table*}
 
 \textbf{Dense forecasting.}
-The EgoSpeak baseline reaches 74.12\% 0.2-s mAP and 61.16\% mean mAP; its raw
+The EgoSpeak baseline reaches 74.20\% 0.2-s mAP and 61.19\% mean mAP; its raw
 wearer-onset/offset mean APs are 24.49/38.02\%. Opportunity-conditioned values
 remain pending a protocol-v2 rerun and human review; continuous wearer-score
 plots do not alone establish semantic floor-yield selectivity.
@@ -459,6 +478,34 @@ beyond additional temporal capacity}.
 \todo{If this difference is not statistically supported, state instead that
 the local temporal branch accounts for most of the gain.}
 
+\subsection{Qualitative Floor-Event Analysis}
+
+We will compare EgoSpeak with the final matched model on human-confirmed
+examples selected by pre-declared event subtype rather than post-hoc score
+extremes. Each case will align participant-resolved activity, minimal transcript
+context, the opportunity anchor and competing-risk censor, and the two models'
+causally emitted wearer forecasts. The comparison will include a genuine wearer
+entry, an other-to-other false-entry opportunity, and an INT-yield paired with a
+non-takeover overlap; a shared failure case will be retained when space permits.
+
+\begin{figure*}[t]
+\centering
+\fbox{\parbox[c][0.115\textheight][c]{0.965\textwidth}{
+\centering
+\textbf{Qualitative comparison placeholder}\\[0.7em]
+\begin{tabular}{ccc}
+Case A: wearer entry & Case B: other$\rightarrow$other HN
+& Case C: INT-yield / failed takeover\\
+participant timeline + transcript & opportunity anchor + censor
+& EgoSpeak vs. proposed forecast\\
+\end{tabular}
+}}
+\caption{Planned qualitative floor-event comparison. Final panels will use
+human-confirmed protocol-v2 cases and show the same causal source time for both
+models; the figure is a layout placeholder and contains no result claim.}
+\label{fig:qualitative_floor_events}
+\end{figure*}
+
 \subsection{Information Opportunity}
 
 Before designing the deployable adapter, we measured whether local floor
@@ -569,7 +616,7 @@ future-media intervention test. Report within-backbone 5-Hz versus 1-Hz
 deltas plus cache/no-cache throughput and memory; do not interpret unmatched
 Qwen--MiniCPM raw scores as a pure backbone effect.}
 
-\subsection{Limitations and Qualitative Analysis}
+\subsection{Limitations}
 
 The results support \todo{precise supported claim}, but several limitations
 remain.
@@ -579,10 +626,9 @@ tracking assumption}.
 Third, \todo{failure condition: occlusion, overlapping speakers, rapid floor
 exchange, etc.} remains challenging.
 
-\todo{Add one compact, pre-selected qualitative timeline only if space permits:
-one multi-other false-entry improvement paired with one preserved real wearer
-onset or one failure. Examples illustrate aggregate rates and never establish
-the claim by themselves.}
+\todo{Replace Fig.~\ref{fig:qualitative_floor_events} with compact, pre-selected
+human-confirmed timelines. Examples illustrate aggregate rates and never
+establish the claim by themselves.}
 
 \section{Conclusion}
 \label{sec:conclusion}