\begin{table}[htbp]
\centering\footnotesize
\caption{Leakage audit}\label{tab:leakage}
\begin{threeparttable}
\begin{tabular}{p{4cm}p{11cm}}
\toprule
Item & Treatment \\
\midrule
Hedonic coefficients & WP22 stage 1 re-estimated at every vintage; Task A features never use coefficients \\
Geographic clustering / location cells & WP22 nested grid rebuilt from data $\le$ origin at every vintage; Task A uses raw coordinates \\
Normalisation & standardisation constants from training rows only; index levels enter as changes \\
Feature selection & fixed feature lists, no selection on test data \\
Imputation & WP22 conditional medians (no price information); indicators time-stable \\
Target encoding & none; one-hot with training categories \\
Spatial graph & DSGFN adjacency recomputed at each origin from centroids and the real-time history $\le$ origin \\
Hyper-parameter tuning & fixed a priori (Table~\ref{tab:hyper}) \\
Index revisions & predictors = vintage published for the origin; target = final series (revision component reported) \\
Partial last month & October 2026 excluded; last target September 2026 \\
\bottomrule
\end{tabular}
\end{threeparttable}
\end{table}