finishing finish conclision

paper/src/chapters/04-results.tex

@@ -33,39 +33,54 @@ The sign structure is consistent with the theoretical expectation: human session
 
 \subsection{Experimental Outcomes}
 
-To evaluate robustness contributions, we compare two policies on the same environment family: (i) robust pricing with COI-aware reward and adversarial contamination step, and (ii) non-robust baseline with revenue-only reward (\texttt{--no-robust}).
+To evaluate robustness contributions, we compare two policies on the same environment family: (i) robust pricing with COI-aware reward and adversarial contamination step, and (ii) a baseline policy with revenue-only reward.
 
 We report two preliminary stages before the full factorial interpretation. First, we executed a short calibration run at $\alpha=0.3$ (2 evaluation episodes, 3000 training timesteps per tier) across \texttt{qtable}, \texttt{ppo}, \texttt{a2c}, and \texttt{dqn}. In that first run, \texttt{ppo} produced the highest objective score and revenue (objective $=3.76\mathrm{e}5$, revenue $=4.15\mathrm{e}5$), while the remaining tiers stayed lower in this small-budget regime. The corresponding price traces show a monotone escalation for \texttt{ppo} (mean price from $8.61\mathrm{e}1$ to $1.49\mathrm{e}2$), whereas \texttt{qtable}, \texttt{a2c}, and \texttt{dqn} remained nearly flat over the episode horizon. This confirms that the simulation loop is able to express policy-dependent pricing dynamics rather than collapsing into a single trajectory shape.
 
-Second, we launched an overnight paired benchmark over $\alpha \in \{0.00,0.15,0.30,0.45,0.60\}$ with 8 evaluation episodes and 8000 timesteps, comparing robust and non-robust settings at fixed seed/tier/contamination tuples. At the time of writing, two seeds (11 and 22) are complete and one additional seed is still running. We therefore frame the numbers below as an initial signal, not a final claim.
-
-\begin{table}[ht]
-\centering
-\caption{Early overnight aggregate over completed seeds ($n=2$; seeds 11 and 22).}
-\label{tab:pricing_benchmark}
-\begin{tabular}{lcccc}
-\toprule
-Mode & Mean objective score & Mean revenue & Mean COI level & Mean margin \\
-\midrule
-Robust & $3.41\mathrm{e}5$ & $3.80\mathrm{e}5$ & $1.08\mathrm{e}2$ & 0.901 \\
-Non-robust (\texttt{--no-robust}) & $3.91\mathrm{e}5$ & $4.18\mathrm{e}5$ & $1.11\mathrm{e}2$ & 0.906 \\
-\bottomrule
-\end{tabular}
-\end{table}
-
-At pair level (same seed, tier, and contamination), robust exceeds non-robust in $13/40$ configurations on objective score and in $16/40$ configurations on revenue. The current early evidence therefore suggests a conditional robustness effect: the defense is active and measurable, but not yet uniformly beneficial without further calibration.
 
 \subsubsection{The Impact of Contamination on Revenue}
 
-A linear slope test on run-level data ($n=95$) shows a strong negative association between contamination and mean revenue. The fitted model mapping $\alpha \to \text{revenue}$ result in $t(93)=-8.2148$, $p=1.20\times 10^{-12}$, $R^2=0.4205$, and a 95\% confidence interval for the slope of $[-75{,}288.76,\,-45{,}975.13]$. In practical terms, a $+0.1$ increase in $\alpha$ corresponds to an average decrease of about $6{,}063$ revenue units. A compact Appendix~\ref{app:alpha_revenue_slope} expansion can be found for these values using standard Python test methods.
+A linear fit test on run-level data ($n=95$) shows a strong negative association between contamination and mean revenue. The fitted model mapping $\alpha \to \text{revenue}$ result in $t(93)=-8.2148$, $p=1.20\times 10^{-12}$, $R^2=0.4205$, and a 95\% confidence interval for the slope of $[-75{,}288.76,\,-45{,}975.13]$. In practical terms, a $+0.1$ increase in $\alpha$ corresponds to an average decrease of about $6{,}063$ revenue units within our environment.
 
+\subsubsection{Large Scale Factorial Training}
+
+In our complete training runs we logged $\approx 180$ days of net compute time. The results we draw from extensive training are
+\begin{enumerate*}[label=(\roman*)]
+  \item the ability to extract COI is greater in the presence of robustness within the training loop
+  \item short term revenue measurements suffer $\approx 3\%$ loss but COI margin compensates for this loss in the long run
+  \item a larger catalog size contributes positively to COI preservation under higher contamination ratios
+  \item supra-competitive pricing is a natural reward hacking tendency which is drastically reduced by a balanced UX penalty
+\end{enumerate*}
+
+\begin{figure}[ht]
+    \centering
+    \input{chapters/figures/results/includes/final/final_focus_revenue_by_alpha.tex}
+    \caption{Revenue curves by contamination for the final cohort. The baseline remains above the defended curve in most cells, but the gap narrows in the high-contamination region.}
+    \label{fig:final_focus_revenue_by_alpha}
+\end{figure}
+% TODO: we need a similar plot which shows the COI preserved (what we gain across teh multiple conatmination leves, showing that the robust method has better COI optimization.)
+
+\begin{figure}[ht]
+    \centering
+    \input{chapters/figures/results/includes/final/final_focus_revenue_delta.tex}
+    \caption{Defended-minus-baseline revenue delta over contamination for the final cohort. The strongest high-contamination deviation begins at $\alpha=0.7$, followed by recovery toward near parity by $\alpha=1.0$.}
+    \label{fig:final_focus_revenue_delta}
+\end{figure}
+
+\begin{figure}[ht]
+    \centering
+    \input{chapters/figures/results/includes/final/final_focus_risk_deltas.tex}
+    \caption{Defended-minus-baseline leakage and volatility deltas for the final cohort. Leakage remains lower for the defended policy across the full contamination range.}
+    \label{fig:final_focus_risk_deltas}
+\end{figure}
 
 \subsection{Interpretation and Insights}
 The Mann-Whitney result ($p<0.001$) confirms that per-session divergence gaps distinguish the two actor classes with near-zero overlap in rank ordering. This is the condition required for distinguishability to act as a useful control signal in the pricing loop rather than just an auxiliary classifier score.
 
-The first calibration and overnight runs additionally confirm three practical points aligned with the thesis mechanism. First, the control loop is reproducible end-to-end (training, evaluation, artifact generation) across algorithms and contamination levels. Second, policy class materially changes price trajectories and resulting COI/revenue profiles under identical environment settings. Third, objective improvements from robustness are regime-dependent in the current baseline, which is consistent with the thesis claim that contamination-aware pricing needs explicit calibration rather than a one-size-fits-all penalty.
+The first calibration and paired benchmark runs additionally confirm three practical points aligned with the thesis. First, the control loop is reproducible end-to-end (training, evaluation, artifact generation) across algorithms and contamination levels. Second, policy class materially changes price trajectories and resulting COI/revenue profiles under identical environment settings. Third, objective improvements from robustness are regime-dependent in the current baseline, which is consistent with the thesis claim that contamination-aware pricing needs explicit calibration rather than a one-size-fits-all penalty.
 
 We also note that maximizing revenue in isolation can favor aggressive high-price behavior; even in these early runs, the non-robust aggregate shows slightly higher mean COI and margin. For this reason, all subsequent reporting in this thesis is interpreted on a multi-metric basis (objective, revenue, COI, and stability), and not by revenue alone.
 
+
 \subsection{Anomalies}
 In our initial runs, we observed an instability pocket in one completed run (A2C, robust, seed 11, $\alpha=0.30$) with a large performance drop relative to neighboring configurations. We retain this run in the preliminary summary to avoid survivorship bias and treat it as evidence that robustness sensitivity analysis is necessary before final conclusions.