Expand targeted introduction and move method figure to page two

manuscript/targeted/Makefile

@@ -2,11 +2,11 @@ LATEXMK ?= latexmk
 
 .PHONY: all clean figure
 
-all: figures/system_overview_onecolumn.pdf figures/task_overview.pdf
+all: figures/system_overview_onecolumn.pdf
 	mkdir -p build
 	$(LATEXMK) -pdf -interaction=nonstopmode -halt-on-error -outdir=build main.tex
 
-figure: figures/system_overview_onecolumn.pdf figures/task_overview.pdf
+figure: figures/system_overview_onecolumn.pdf
 
 figures/%.pdf: figures/%.tex
 	$(LATEXMK) -pdf -interaction=nonstopmode -halt-on-error -outdir=figures $<
@@ -14,4 +14,3 @@ figures/%.pdf: figures/%.tex
 clean:
 	$(LATEXMK) -C -outdir=build main.tex
 	$(LATEXMK) -c -outdir=figures figures/system_overview_onecolumn.tex
-	$(LATEXMK) -c -outdir=figures figures/task_overview.tex

manuscript/targeted/README.md

@@ -63,11 +63,13 @@ make
 ```
 
 The editable sources are `main.tex`, `tables_compact.tex`, `references.bib`,
-`figures/task_overview.tex`, and `figures/system_overview_onecolumn.tex`.
+and `figures/system_overview_onecolumn.tex`. The earlier
+`figures/task_overview.tex` is retained as unused source.
 Generated LaTeX files are written to `build/`.
 
-The preview targets four technical pages plus a reference-only fifth page. Both
+The preview targets four technical pages plus a reference-only fifth page.
-the task diagram (Fig. 1) and the system diagram (Fig. 2) occupy one column.
+The single-column method diagram (Fig. 1) has SWE on top and PTR below;
+the earlier standalone task figure is not included.
 The current PDF reserves seven numbered result tables. Table 1 spans two
 columns and reports 0.2--2.0-s mAP for EasyCom and the pending Ego4D transfer
 rows. Only three EasyCom models have archived complete horizon curves; other
@@ -77,7 +79,7 @@ Table 2A T/C matrix, and Table 2B chunk screen are now standalone Tables
 Pending cells are explicitly unmeasured. Active table layouts are in
 `tables_compact.tex`; the earlier full-precision tabulars
 remain disabled in `main.tex` for source-level auditing.
-Figure 3 is an H/Q case slot, not a selected or measured example. Its
+Figure 2 is an H/Q case slot, not a selected or measured example. Its
 cutoff-marked timelines must be inserted only after the slice protocol and
 case-selection rule are frozen. The single-column system figure is generated
 from figures/system_overview_onecolumn.tex; the earlier full-width source

manuscript/targeted/figures/system_overview_onecolumn.tex

@@ -1,5 +1,5 @@
 \documentclass[tikz,border=2pt]{standalone}
-\usetikzlibrary{arrows.meta,positioning}
+\usetikzlibrary{arrows.meta}
 \definecolor{navy}{HTML}{19324A}
 \definecolor{bluefill}{HTML}{EAF1F7}
 \definecolor{teal}{HTML}{087F78}
@@ -8,43 +8,64 @@
 \definecolor{orangefill}{HTML}{FFF0DF}
 \begin{document}
 \begin{tikzpicture}[
-  font=\sffamily\small,
+  font=\sffamily\footnotesize,
   >=Latex,
-  box/.style={draw=navy,fill=bluefill,rounded corners=1.5pt,
+  flow/.style={-{Latex[length=1.7mm]},draw=navy,line width=.7pt}]
-    align=center,minimum height=7mm,inner sep=2pt},
+
-  local/.style={box,draw=teal,fill=tealfill},
+\node[anchor=west,font=\sffamily\footnotesize\bfseries,text=navy]
-  flow/.style={-{Latex[length=1.6mm]},draw=navy,line width=.6pt}]
+  at (.05,5.45) {(a) Short-window encoder evidence (SWE)};
-\node[box,text width=20mm] (global) at (1.12,3.9)
+\node[anchor=east,font=\sffamily\scriptsize,text=navy]
-  {Observed AV\\8-s maximum};
+  at (8.25,5.45) {inputs $\leq t_n$};
-\node[box,text width=22mm] (thinker) at (4.13,3.9)
+
-  {Frozen Thinker\\readout $G$};
+\draw[draw=navy,fill=bluefill,rounded corners=2pt]
-\node[local,text width=20mm] (audio) at (1.12,2.9)
+  (.10,4.48) rectangle (3.80,5.18);
-  {Recent 1-s\\mixed audio};
+\node[align=center,text=navy] at (1.95,4.83)
-\node[local,text width=22mm] (aenc) at (4.13,2.9)
+  {Frozen Omni Thinker\\global AV context $G$};
-  {Frozen encoder\\local $A$};
+\draw[draw=teal,fill=tealfill,rounded corners=2pt]
-\node[local,dashed,text width=20mm] (video) at (1.12,1.9)
+  (.10,3.57) rectangle (3.80,4.27);
-  {Past person\\crops (optional)};
+\node[align=center,text=teal] at (1.95,3.92)
-\node[local,dashed,text width=22mm] (venc) at (4.13,1.9)
+  {Frozen audio encoder\\recent 1-s audio $A$};
-  {Frozen encoder\\pooled $V$};
+\draw[draw=teal,fill=tealfill,dashed,rounded corners=2pt]
-\node[box,text width=18mm] (head) at (7.05,2.9)
+  (.10,2.48) rectangle (3.80,3.43);
-  {Validities +\\trained head};
+\node[align=center,text=teal] at (1.95,2.955)
-\draw[flow] (global) -- (thinker);
+  {Frozen visual encoder\\recent person-crop clues $V$};
-\draw[flow,draw=teal] (audio) -- (aenc);
+
-\draw[flow,draw=teal,dashed] (video) -- (venc);
+\draw[draw=navy,line width=.7pt] (3.80,4.83) -- (4.38,4.83)
-\draw[flow] (thinker.east) -- ++(.18,0) |- (head.north);
+  -- (4.38,2.955) -- (3.80,2.955);
-\draw[flow,draw=teal] (aenc) -- (head);
+\draw[draw=teal,line width=.7pt] (3.80,3.92) -- (4.38,3.92);
-\draw[flow,draw=teal,dashed] (venc.east) -- ++(.18,0) |- (head.south);
+\draw[flow] (4.38,3.92) -- (4.85,3.92);
-\node[box,text width=32mm] (out) at (5.7,.88)
+\draw[draw=navy,fill=bluefill,rounded corners=2pt]
-  {$10\times3$ future activity\\0.2--2.0-s horizons};
+  (4.95,3.57) rectangle (6.40,4.27);
-\draw[flow] (head.south) -- (out.north);
+\node[align=center,text=navy] at (5.675,3.92) {Fusion\\head};
-\draw[draw=navy,line width=.5pt] (0,.12) -- (8.25,.12);
+\draw[flow] (6.40,3.92) -- (6.78,3.92);
-\node[anchor=west,text=navy] at (0,-.28) {Completed blocks};
+\draw[draw=orange,fill=orangefill,rounded corners=2pt]
-\foreach \x in {0,1.04,2.08} {
+  (6.88,3.57) rectangle (8.30,4.27);
-  \draw[draw=navy,fill=bluefill] (\x,-.93) rectangle ++(.96,.35);
+\node[align=center,text=orange] at (7.59,3.92)
+  {Future\\activity};
+
+\draw[draw=navy!35,line width=.5pt] (.05,2.34) -- (8.30,2.34);
+\node[anchor=west,font=\sffamily\footnotesize\bfseries,text=navy]
+  at (.05,2.07) {(b) Partial-tail refresh (PTR)};
+
+\node[font=\sffamily\scriptsize,text=navy] at (1.58,1.70)
+  {reused completed blocks};
+\node[font=\sffamily\scriptsize,text=orange] at (4.08,1.70)
+  {observed at $t_n$};
+\foreach \x in {.15,1.15,2.15} {
+  \draw[draw=navy,fill=bluefill,rounded corners=1pt]
+    (\x,1.08) rectangle ++(.88,.46);
+  \node[text=navy] at (\x+.44,1.31) {2 s};
 }
-\draw[draw=orange,fill=orangefill] (3.12,-.93) rectangle ++(.96,.35);
+\draw[draw=orange,fill=orangefill,rounded corners=1pt]
-\node[anchor=west,text=orange] at (4.25,-.76) {Observed tail};
+  (3.20,1.08) rectangle (4.95,1.54);
-\node[anchor=west,text=navy] at (0,-1.33)
+\node[text=orange] at (4.075,1.31) {partial tail};
-  {Reuse completed payloads; query a temporary tail at $t_n$.};
+\draw[flow] (4.95,1.31) -- (5.41,1.31);
+\draw[draw=navy,fill=bluefill,rounded corners=2pt]
+  (5.51,.96) rectangle (8.30,1.66);
+\node[align=center,text=navy] at (6.905,1.31)
+  {Temporary Thinker\\readout $G_t$};
+\node[anchor=west,font=\sffamily\scriptsize,text=navy]
+  at (.15,.53) {Only completed blocks enter persistent history; the tail is not committed.};
+
 \end{tikzpicture}
 \end{document}

manuscript/targeted/main.tex

@@ -57,7 +57,14 @@ streaming, voice activity projection, conversational agents
 An egocentric conversational agent must decide \emph{when} to speak even
 though its camera wearer is usually invisible.  It hears a mixed conversation
 and sees other participants, but must anticipate its own speech from the
-observed stream before a turn boundary is known (Fig.~\ref{fig:task}).
+observed stream before a turn boundary is known (Fig.~\ref{fig:overview}).
+This decision differs from recognizing who is speaking now: the relevant
+evidence may be a brief pause, overlap, or response by someone in view, while
+the target is the wearer's \emph{future} activity.  It also differs from
+predicting a semantic end of turn or selecting an addressee.  We therefore
+study a deliberately narrower and measurable question: at each 200-ms
+cutoff, how well can a causal observer forecast background, wearer, and
+aggregate-other activity over the next 0.2--2.0~s?
 Anticipatory turn-taking has developed rapidly: VAP, audiovisual and triadic
 extensions, backchannel prediction, online end-of-turn detection, and event
 benchmarks address increasingly realistic timing decisions
@@ -65,16 +72,10 @@ benchmarks address increasingly realistic timing decisions
 lin2025backchannel,lee2024eot,qi2026muvap,jiang2026turnbench}.
 Their input viewpoints and target decisions, however, are not interchangeable
 with forecasting the future activity of an unseen wearer.
-
+The distinction matters when comparing systems: a correct current-speaker
-\begin{figure}[H]
+label or an utterance-final response can conceal errors in the first few
-\centering
+hundred milliseconds, precisely where a wearable agent must decide whether
-\includegraphics[width=\columnwidth]{figures/task_overview.pdf}
+to wait or begin speaking.
-\caption{Task, not an observed event example.  At each 5-Hz decision cutoff,
-only the past audio--video prefix is input; ten future activity states are
-targets.  ENTRY-like and YIELD-like refer to wearer activity transitions,
-not semantic floor ownership.}
-\label{fig:task}
-\end{figure}
 
 \textbf{Egocentric audiovisual conversation.}
 EgoSpeak is the closest wearer-centered predecessor: it extracts audio and
@@ -90,6 +91,13 @@ prediction in noise \cite{oconnorrussell2025noise}.  These studies make a
 broad ``first audiovisual turn-taking'' claim untenable.  What remains
 less examined is how a single causal first-person stream should expose
 recent audio--visual evidence to forecast the invisible wearer's activity.
+EgoSpeak establishes that compact audio and video representations can be
+fused for this task, but it does not answer whether a large integrated Omni
+representation makes those cutoff-local cues readily available to a small
+forecasting head.  Conversely, work on active speakers or addressees need
+not solve wearer anticipation: the visible interlocutor and the predicted
+speaker occupy different roles.  This leaves an architectural question,
+rather than a claim that audiovisual evidence itself is new.
 
 \textbf{Streaming Omni and temporal access.}
 Omni systems integrate modalities and support streaming interaction
@@ -106,21 +114,31 @@ recent modality features outside the Thinker state, while \emph{partial-tail
 refresh} (PTR) queries the observed prefix of the incomplete current block.
 SWE denotes temporal locality, not shallow encoder layers; the argument
 concerns this pipeline, not an intrinsic deficit of every Omni model.
+These interventions target different bottlenecks.  SWE asks whether recent
+encoder evidence improves prediction when the global state is held fixed;
+PTR asks whether the same integrated backbone benefits from a fresher readout
+without admitting future media.  A gain from one does not establish a gain
+from the other.  In particular, the effect of PTR requires a matched
+completed-only comparison at the same context cap, rather than comparison
+with a longer or shorter history.
 
-Our contributions are a causal SWE/PTR interface for 5-Hz wearer activity
+This framing yields three concrete contributions.  First, we formulate a
-anticipation; an EasyCom analysis separating global, recent-audio,
+causal, 5-Hz wearer-activity forecast and specify SWE and PTR as separable
-pooled-visual, and privileged visible-activity information; and a specified
+ways to expose local evidence to a frozen Omni model.  Second, on EasyCom we
-EasyCom--Ego4D evaluation with horizon, endpoint, and hard-slice diagnostics.
+compare global, recent-audio, and pooled-visual features, then use privileged
-Only EasyCom screening scores are currently available: matched PTR effects,
+past visible activity only as an information audit, not a deployable input.
-Ego4D transfer, and event-level behavior remain open tests.
+Third, we specify cross-dataset, endpoint, and hard-slice tests.  EasyCom
+screening is the only measured evidence; matched PTR, Ego4D transfer, and
+event behavior remain open.
 
 \begin{figure}[t]
 \centering
 \includegraphics[width=\columnwidth]{figures/system_overview_onecolumn.pdf}
-\caption{Two cutoff-aligned interfaces.  SWE supplies recent encoder-side
+\caption{Method overview at cutoff $t_n$. Top: SWE joins frozen Omni context
-audio and optional pooled person-crop vision to a frozen-Omni head.  PTR
+with recent audio and optional pooled person-crop evidence in the forecasting
-temporarily queries the observed current-block prefix while reusing completed
+head. Bottom: PTR reuses completed 2-s blocks and temporarily queries only
-2-s payloads.  Privileged past-activity labels are not model inputs.}
+the observed current-block tail at each 200-ms cutoff. The tail is not
+committed to persistent history.}
 \label{fig:overview}
 \end{figure}