docs(manuscript): record F3 and microchunk screens

manuscript/main/README.md

@@ -34,6 +34,13 @@ remain records of their dates. The new scoped decision is
   unmeasured placeholders, not zero or mixed-protocol confirmatory numbers.
   Historical main-table screens are identified explicitly. Already inspected
   official-test runs remain exploratory despite additional seed repetitions.
+- The main table now includes an exploratory F3 seed-0 no-box full-frame screen
+  and the re-evaluated G+A dense horizon curve, both under
+  `causal_valid_only`. F3's 0.2-s/ten-horizon mAP is 82.38/65.54 versus
+  G+A's 81.72/65.11. This is not a matched visual-motion claim: F2, matched
+  capacity/history controls, boundary evaluation, and repeat seeds are still
+  missing. Source records: [F3](../../results/easycom_fullframe_qwen_av/f3_seed0/README.md)
+  and [G+A](../../results/easycom_omni_audio_recheck_2026-09-24/official_test/README.md).
 - Backbone transfer adds paired G/GA controls for Qwen2.5-Omni 3B/7B and
   MiniCPM-o 4.5, fixing the same local audio sidecar. Compact table deltas are
   pending and require readout/refresh/history audits; MiniCPM is not yet

manuscript/main/main.tex

@@ -261,18 +261,21 @@ detection latency claim.
 \subsection{Main Comparison}
 
 Table~\ref{tab:main} retains exploratory references and reserves the locked
-comparison. Historical runs have unmatched training/selection protocols;
-the three-seed F1 screen establishes stability, not matched superiority.
+comparison. The G+A and F3 seed-0 rows use the same official test split and
+\texttt{causal\_valid\_only} dense protocol, but their head capacity, visual
+history, and training batch differ. The three-seed F1 screen establishes
+stability, not matched superiority.
 \todo{Fill the locked rows with three-seed mean and sample standard deviation.}
 
 \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.}
+not semantic ENTRY/INT scores. $\dagger$ denotes exploratory seed-0 runs
+without a complete matched capacity/history comparison; $\ddagger$ denotes a
+three-seed screen. F3 uses a two-frame causal full-frame token history without
+person boxes. Dashes indicate unmeasured values; locked rows await the final
+matched dense/boundary reruns.}
 \label{tab:main}
 \centering
 \scriptsize
@@ -290,11 +293,14 @@ 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 & -- & -- & -- & -- & -- & -- & -- & -- & --
+  & 81.72 & 75.92 & 70.38 & 66.46 & 63.81 & 61.37 & 60.00 & 58.32 & 56.95 & 56.16
   & 65.11 & 25.96 & 45.25\\
 Omni $G{+}A{+}$pooled-$V^{\dagger}$
   & 82.03 & -- & -- & -- & -- & -- & -- & -- & -- & --
   & 65.40 & 26.02 & 45.37\\
+No-box full-frame F3$^{\dagger}$
+  & 82.38 & 76.42 & 70.78 & 66.35 & 63.93 & 61.87 & 60.41 & 59.11 & 57.61 & 56.53
+  & 65.54 & -- & --\\
 Current-frame F1$^{\ddagger}$
   & $81.78{\pm}0.16$ & -- & -- & -- & -- & -- & -- & -- & -- & --
   & $64.95{\pm}0.09$ & -- & --\\
@@ -328,6 +334,16 @@ global-only head as a capacity control. These branches expose different
 history ranges, so the comparison is not a pure Thinker-versus-encoder test.
 Past-delayed local inputs provide separate fixed-checkpoint sensitivity
 tests, not substitutes for retrained modality-removal controls.
+In a seed-0 exploratory screen, no-box full-frame F3 uses two strictly causal
+2-FPS spatial-token observations per grid position and a shared GRU. On
+Sessions~1--3, its 0.2-s mAP is 82.38\% and ten-horizon mean mAP is 65.54\%,
+versus 81.72\% and 65.11\% for the existing $G+A$ head (differences of
++0.66 and +0.43 points). This comparison shares the global states, recent
+Qwen audio source, test split, and dense evaluation protocol, but adds visual
+input and temporal parameters and uses a different training batch. It does
+not isolate visual motion or establish wearer floor-control improvement;
+F2, capacity/history-matched controls, boundary metrics, and repeat seeds
+remain outstanding.
 \todo{Insert audio and visual marginal deltas in wearer, onset, and offset
 AP; retain negative findings even if overall mAP increases.}
 
@@ -345,6 +361,7 @@ 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
 are used. This tests whether the two paths are complementary or redundant.
+The global-only chunk screen below is separate from this matched factorial.
 
 \begin{table}[t]
 \caption{Planned controls. M/W: mean mAP/wearer AP; On/Off: mean endpoint
@@ -377,6 +394,21 @@ MiniCPM-o 4.5 & -- & -- & -- & --\\
 \end{tabular}
 \end{table}
 
+\textbf{Exploratory 200-ms chunk screen.}
+With frozen Qwen2.5-Omni-3B global features, 8-s memory, and 2-FPS video, we
+trained separate seed-0 heads for ten epochs on Sessions 4--12 and evaluated
+Sessions 1--3 under the causal-valid protocol. A native 2-s completed-block
+hold, non-native 200-ms
+payload commits, and completed blocks with an observed partial tail obtain
+59.62/67.05/70.85\% mAP at the 0.2-s horizon, respectively; their
+ten-horizon mean mAPs are 55.19/57.84/59.17\%. The microchunk advantage
+over hold remains after excluding the first nine startup decisions per
+session, but requires 95,453 versus 9,539 processor calls over all 12
+sessions. This previously inspected, single-seed test-set screen measures
+dense activity forecasting, not floor events or native 200-ms streaming.
+Freshness and chunk construction both change, and the older partial-tail
+feature bank is not a fully matched extraction-version control.
+
 The planned 4/8/16-s context-cap comparison keeps local evidence at 1~s
 and reports actual history spans and block phases. Each cap requires its
 own extracted states and matched training; a fixed-checkpoint context