From e09ee1c4320cfff41036dbbfa6843e7dc50f4c90 Mon Sep 17 00:00:00 2001 From: Xin Wang Date: Thu, 24 Sep 2026 15:11:14 +0800 Subject: [PATCH] Rework targeted manuscript result tables --- manuscript/targeted/README.md | 37 ++++++--- manuscript/targeted/main.tex | 44 +++++++---- manuscript/targeted/tables_compact.tex | 100 +++++++++++++++++++++++++ 3 files changed, 155 insertions(+), 26 deletions(-) create mode 100644 manuscript/targeted/tables_compact.tex diff --git a/manuscript/targeted/README.md b/manuscript/targeted/README.md index 0554c58..3467bed 100644 --- a/manuscript/targeted/README.md +++ b/manuscript/targeted/README.md @@ -26,12 +26,19 @@ Omni models lack local perception or that PTR's independent gain is proven: The draft also reflects two seed-0 exploratory screens reported in `../main/main.tex`: no-box full-frame F3 (Table 1) and a global-only -chunk-construction comparison (Table 2, panel B). Neither supplies +chunk-construction comparison (Table 4). Neither supplies matched visual-motion evidence, endpoint gains, or the pending T/C factorial. The result directories cited by the main draft for F3 and its G+A recheck are absent from this checkout, so their underlying logs have not been independently audited here. +The Results section also reports the archived 2026-08-24 sparse Thinker-LoRA +diagnostic as a separate historical screen. Its strict causal-valid mean mAP +declined under the recorded LoRA recipes, but the legacy feature/head contract +is not matched to the current G+A matrix, and the remote raw metrics and +checkpoints are unavailable here. It is not a Table 1 model ranking or proof +that LoRA cannot help this task. + No semantic ENTRY/YIELD, addressee, online-detector, or real-time-throughput claim is made. The deployable matrix is explicitly single-seed and exploratory. EasyCom has archived screening scores. The Ego4D manifest and extraction / @@ -51,17 +58,21 @@ cd manuscript/targeted make ``` -The editable sources are `main.tex`, `references.bib`, +The editable sources are `main.tex`, `tables_compact.tex`, `references.bib`, `figures/task_overview.tex`, and `figures/system_overview_onecolumn.tex`. Generated LaTeX files are written to `build/`. -The preview is four technical pages plus a reference-only fifth page. Both +The preview targets four technical pages plus a reference-only fifth page. Both the task diagram (Fig. 1) and the system diagram (Fig. 2) occupy one column. -The current PDF reserves five numbered result tables: measured deployable -and oracle screens share Table 1; L controls extend its first panel. The -unmeasured T/C matrix and a separate measured chunk screen share Table 2; -B (including an Ego4D transfer slot), H, and S occupy Tables 3--5. Pending -cells are explicitly unmeasured. +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 +intermediate cells remain unavailable. The old Table 1B oracle audit, +Table 2A T/C matrix, and Table 2B chunk screen are now standalone Tables +2--4. B (including an Ego4D transfer slot), H, and S occupy Tables 5--7. +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 cutoff-marked timelines must be inserted only after the slice protocol and case-selection rule are frozen. The single-column system figure is generated @@ -74,10 +85,12 @@ The build uses the repository's ICASSP 2027 LaTeX assets in ## Evidence sources -- `results/easycom_encoder_only_1s_4ep_2026-08-28/` -- `results/easycom_egospeak_three_level_eval_2026-09-16/` -- `results/easycom_omni_floor_screen_2026-09-16/` -- `results/easycom_oracle_pooled_wearer_audit_2026-09-10/` +- `../../results/easycom_encoder_only_1s_4ep_2026-08-28/` +- `../../results/easycom_egospeak_three_level_eval_2026-09-16/` +- `../../results/easycom_omni_floor_screen_2026-09-16/` +- `../../results/easycom_oracle_pooled_wearer_audit_2026-09-10/` +- `../../results/easycom_sparse_supervision_vs_lora_2026-08-24/` +- `../../results/easycom_omni_lora_sparse_epoch2_2026-08-24/` The manuscript does not use superseded opportunity-conditioned ENTRY/INT numbers. See `REVIEWER_REPORT.md` for the internal review loop and the remaining diff --git a/manuscript/targeted/main.tex b/manuscript/targeted/main.tex index 840412b..7e04b3b 100644 --- a/manuscript/targeted/main.tex +++ b/manuscript/targeted/main.tex @@ -182,6 +182,9 @@ second, and (v) one OR-pooled aggregate-visible history. These conditions never expose future activity, but their speech labels make them privileged diagnostics, not deployable features or upper bounds. +\input{tables_compact} +% Historical full-precision table layouts retained as source audit only. +\iffalse \begin{table*}[t] \caption{Measured EasyCom screens (\%). Panel A: deployable models; Panel B: three-seed privileged past-activity audit, which is not deployable. Mean is @@ -270,6 +273,7 @@ Completed blocks + observed tail & 70.85 & 59.17 & -- \\ \end{tabular} \end{table*} +\fi \begin{table}[t] \caption{Pending paired $\G\rightarrow\G+\A$ transfer (unmeasured). EC is EasyCom; MiniCPM first needs readout/refresh/history audits.} @@ -467,7 +471,7 @@ 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. -Table~\ref{tab:main}, panel B, locates the missing information. Aggregate visible +Table~\ref{tab:oracle} locates the missing information. 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 one-second-delayed activity by +0.164. Thus availability or extra parameters @@ -495,16 +499,31 @@ behavioral improvement is asserted by this placeholder.} \subsection{Chunk Timing and Cross-Dataset Limits} -Table~\ref{tab:stream_context}, panel B, reports a separate global-only +Table~\ref{tab:chunk} reports a separate global-only chunk-construction screen. Non-native 200-ms commits exceed native 2-s hold at 0.2~s (67.05 versus 59.62\% mAP), but use 95,453 rather than 9,539 processor calls over 12 sessions. Completed blocks plus observed tail reach 70.85\%; that older bank is not extraction-matched. Freshness and chunk construction vary together, so this is motivation for, not evidence of, an -isolated PTR benefit or real-time throughput. Panel A reserves the matched -tail $\times$ audio and context-cap tests. Tables~\ref{tab:backbone}-- +isolated PTR benefit or real-time throughput. Table~\ref{tab:stream_context} +reserves the matched tail $\times$ audio and context-cap tests. +Tables~\ref{tab:backbone}-- \ref{tab:efficiency} reserve backbone, hard-slice, and cost analyses; the cutoff-marked H/Q case in Fig.~\ref{fig:hq_cases} remains unmeasured. +\textbf{Historical LoRA diagnostic.} +A single-run EasyCom 8-s/2-FPS screen used sparse training anchors (1~Hz, +plus 5~Hz near transitions) and dense 5-Hz evaluation. Within that legacy +pipeline, strict mean mAP was 58.17\% for a frozen dense-cache control, +57.21\% for frozen sparse training, and 56.21\% for a separate three-epoch +Thinker-LoRA run initialized from a trained frozen head. An epoch-1 LoRA +weights-only continuation fell to 54.21\% after optimizer/scheduler reset. +Sparse frozen training is 0.96 points below the dense control; the separate +LoRA run is another 1.01 below sparse frozen, but the epoch budgets differ. +Sparse-train/dense-test mismatch and the optimizer reset are possible, not +isolated, explanations. +Missing remote raw metrics, matched seeds, and feature equivalence make this +a negative recipe diagnostic, not a Table~\ref{tab:main} $\G+\A$ comparison +or proof that LoRA is inherently harmful. Ego4D has no archived test metrics in this checkout, so transfer cannot yet be claimed. The oracle uses privileged labels, provided boxes omit online detection, and aggregate others cannot establish addressee or semantic floor @@ -512,16 +531,13 @@ ownership. \subsection{Decision Rules and Reproducibility} -Comparisons require identical physical cutoffs and future targets. New runs -must archive source timestamps, common valid-pair counts, seeds, per-session -AP, trainable counts, revisions, checkpoints, and predictions; correlated -frames are not independent replicates. The matched matrix keeps a fixed -four-epoch recipe, with selection rules frozen on training-side evidence. -Sessions~1--3 have already been inspected, so repeat seeds remain exploratory. -Raw endpoint AP is not one-event-one-vote ENTRY/YIELD: response windows must -be censored at the next other onset and yield windows at the next other -offset. Until that evaluator passes a real-timeline audit, we report dense -forecasting and endpoint anticipation only. +Matched comparisons require identical cutoffs and targets; archive source +timestamps, valid-pair counts, seeds, per-session AP, trainable counts, and +checkpoint/processor revisions. The fixed recipe and selection rules use +training-side evidence only. Already inspected test sessions make repeat +seeds exploratory. Raw endpoint AP is not one-event-one-vote ENTRY/YIELD: +response windows must end at the next other onset, and yield windows at the +next other offset. Behavioral claims await a real-timeline evaluator audit. \section{Conclusion} diff --git a/manuscript/targeted/tables_compact.tex b/manuscript/targeted/tables_compact.tex new file mode 100644 index 0000000..03f13f3 --- /dev/null +++ b/manuscript/targeted/tables_compact.tex @@ -0,0 +1,100 @@ +% Active result tables. A dash denotes an unreported or unmeasured value. +\begin{table*}[t] +\caption{Dense future-activity mAP (\%) by prediction horizon. EasyCom +scores use Sessions~1--3; the complete ten-horizon curves are reported for +EgoSpeak, $\G+\A$, and F3. Other archived screens provide only 0.2-s and +ten-horizon mean scores, so intermediate cells are not interpolated. +Ego4D transfer is pending. Mean averages all ten horizons, including where +the individual values are unavailable. F3 and the fusion rows are exploratory +seed-0 runs; F1 reports a three-seed mean. These rows are not all +capacity- or training-matched.} +\label{tab:main} +\centering\ninept +\renewcommand{\arraystretch}{0.91} +\begin{tabular*}{\textwidth}{@{\extracolsep{\fill}}lccccccccccc@{}} +\toprule +& \multicolumn{10}{c}{Prediction horizon (s)} & \\ +\cmidrule(lr){2-11} +Dataset / model & .2 & .4 & .6 & .8 & 1.0 & 1.2 & 1.4 & 1.6 & 1.8 & 2.0 & Mean \\ +\midrule +\multicolumn{12}{@{}l}{\emph{EasyCom (measured)}} \\ +EgoSpeak A+V & 74.20 & 68.35 & 64.31 & 61.13 & 59.77 & 58.81 & 57.50 & 57.09 & 55.95 & 54.82 & 61.19 \\ +Recent $\A$ & 79.69 & -- & -- & -- & -- & -- & -- & -- & -- & -- & 60.51 \\ +Omni $\G$ & 73.45 & -- & -- & -- & -- & -- & -- & -- & -- & -- & 60.85 \\ +$\G+\A$ & 81.72 & 75.92 & 70.38 & 66.46 & 63.81 & 61.37 & 60.00 & 58.32 & 56.95 & 56.16 & 65.11 \\ +$\G+\A+$pooled-$\V$ & 82.03 & -- & -- & -- & -- & -- & -- & -- & -- & -- & 65.40 \\ +Full-frame F3 & 82.38 & 76.42 & 70.78 & 66.35 & 63.93 & 61.87 & 60.41 & 59.11 & 57.61 & 56.53 & 65.54 \\ +Person-set F1 & 81.78 & -- & -- & -- & -- & -- & -- & -- & -- & -- & 64.95 \\ +\midrule +\multicolumn{12}{@{}l}{\emph{Ego4D (transfer pending)}} \\ +Omni $\G$ & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\ +$\G+\A$ & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- & -- \\ +\bottomrule +\end{tabular*} +\end{table*} + +\begin{table}[t] +\caption{EasyCom privileged past-activity audit (\%). Three-seed mean +$\pm$ sample SD. The extra activity cues are not deployable inputs; W is +wearer AP at 0.2~s.} +\label{tab:oracle} +\centering\ninept +\renewcommand{\arraystretch}{0.92} +\setlength{\tabcolsep}{3pt} +\begin{tabular}{@{}lccc@{}} +\toprule +Extra condition & mAP$_{.2}$ & W$_{.2}$ & Mean \\ +\midrule +Audio baseline & $81.87{\pm}.05$ & $85.26{\pm}.11$ & $65.18{\pm}.06$ \\ +Visibility only & $81.95{\pm}.10$ & $85.20{\pm}.14$ & $65.22{\pm}.05$ \\ +Delayed 1 s & $81.95{\pm}.09$ & $85.27{\pm}.14$ & $65.34{\pm}.05$ \\ +Shuffled IDs & $85.92{\pm}.09$ & $85.58{\pm}.25$ & $66.46{\pm}.09$ \\ +Per-person & $86.27{\pm}.18$ & $85.61{\pm}.22$ & $66.66{\pm}.14$ \\ +Visible OR & $\mathbf{86.70{\pm}.09}$ & $\mathbf{85.84{\pm}.15}$ & $\mathbf{66.95{\pm}.02}$ \\ +\bottomrule +\end{tabular} +\end{table} + +\begin{table}[t] +\caption{Pending matched timing/context tests. Each cell will compare +$\G$ with $\G+\A$ on common cutoffs; $\Delta$ is paired mean-mAP gain. +PTR uses completed blocks plus the observed tail. Dashes are unmeasured.} +\label{tab:stream_context} +\centering\ninept +\renewcommand{\arraystretch}{0.92} +\setlength{\tabcolsep}{3pt} +\begin{tabular}{@{}llcc@{}} +\toprule +Group & Refresh / cap & $\G/\G+\A$ & $\Delta$ \\ +\midrule +T & Completed hold, 8 s & --/-- & -- \\ +T & PTR, 8 s & --/-- & -- \\ +\midrule +C & PTR, 2 s & --/-- & -- \\ +C & PTR, 4 s & --/-- & -- \\ +C & PTR, 6 s & --/-- & -- \\ +C & PTR, 8 s & --/-- & -- \\ +C & PTR, 10 s & --/-- & -- \\ +C & PTR, 12 s & --/-- & -- \\ +\bottomrule +\end{tabular} +\end{table} + +\begin{table}[t] +\caption{Separate seed-0 global-only chunk screen (\%): 10 epochs, 8-s cap, +2-FPS video. PTR is not extraction-matched to the other rows. Calls are +processor invocations across 12 sessions, not latency.} +\label{tab:chunk} +\centering\ninept +\renewcommand{\arraystretch}{0.95} +\setlength{\tabcolsep}{3pt} +\begin{tabular}{@{}lccc@{}} +\toprule +Global construction & mAP$_{.2}$ & Mean & Calls \\ +\midrule +Native 2-s hold & 59.62 & 55.19 & 9,539 \\ +200-ms commits & 67.05 & 57.84 & 95,453 \\ +PTR & 70.85 & 59.17 & -- \\ +\bottomrule +\end{tabular} +\end{table}