% Author: Simon-Pierre Boucher — contact@spboucher.ai
% Generated by scripts/08_revision_tables.py — do not edit by hand.
\begin{table}[!htbp]
\centering
\caption{Incremental explanatory power of the 20 semantic similarities across extended specifications.}
\label{tab:spec_summary}
\small
\begin{adjustbox}{max width=\textwidth}
\begin{tabular}{lR{1.2cm}R{1.0cm}R{1.2cm}R{1.4cm}R{1.3cm}R{1.1cm}l}
\toprule
\textbf{Specification} & $\boldsymbol{n}$ & $\boldsymbol{R^2}$ & \textbf{Within} $\boldsymbol{R^2}$ & $\boldsymbol{\Delta R^2}$ \textbf{(sem.)} & \textbf{Block} $\boldsymbol{F}$ & \textbf{Sig.} & \textbf{Cov.} \\
\midrule
D: baseline (Table~\ref{tab:model_comparison}) & 17{,}087 & 0.512 & --- & 0.047 & 54.3 & 16/20 & HC3 \\
D, standard errors clustered by FSA & 17{,}087 & 0.512 & --- & 0.047 & 20.1 & 14/20 & cluster \\
D-L: D + language indicators & 17{,}087 & 0.518 & --- & 0.017 & 22.6 & 16/20 & HC3 \\
D-L, standard errors clustered by FSA & 17{,}087 & 0.518 & --- & 0.017 & 17.6 & 15/20 & cluster \\
D-L + FSA fixed effects & 17{,}087 & 0.667 & 0.458 & 0.020 & 31.4 & 18/20 & cluster \\
D-L + municipality fixed effects & 17{,}087 & 0.710 & 0.456 & 0.016 & 28.3 & 14/20 & cluster \\
D-L + FSA FE, unit-corrected lot area & 17{,}087 & 0.725 & 0.552 & 0.013 & 25.5 & 14/20 & cluster \\
D-L + FSA FE + floor area (subsample) & 6{,}228 & 0.773 & 0.588 & 0.011 & 12.3 & 10/20 & cluster \\
French listings only, D + FSA FE & 9{,}843 & 0.599 & 0.413 & 0.029 & 24.4 & 15/20 & cluster \\
English listings only, D + FSA FE & 6{,}779 & 0.690 & 0.500 & 0.024 & 23.8 & 15/20 & cluster \\
ML-D: multilingual encoder, as D & 17{,}087 & 0.522 & --- & 0.057 & 65.3 & 17/20 & HC3 \\
ML-D-L: multilingual encoder + language & 17{,}087 & 0.538 & --- & 0.038 & 54.0 & 16/20 & HC3 \\
ML-D-L + FSA fixed effects & 17{,}087 & 0.687 & 0.489 & 0.039 & 70.6 & 15/20 & cluster \\
ML-D-L + FSA FE, unit-corrected lot area & 17{,}087 & 0.741 & 0.578 & 0.028 & 52.0 & 13/20 & cluster \\
\bottomrule
\end{tabular}
\end{adjustbox}
\begin{minipage}{\textwidth}
\vspace{4pt}\footnotesize
\textit{Notes:} All specifications include the six structural variables and description length; ``D-L'' adds indicators for English and mixed-language listings; ``ML'' replaces the all-MiniLM-L6-v2 similarities by those computed with paraphrase-multilingual-MiniLM-L12-v2. Fixed effects are absorbed by within-group demeaning (415 forward sortation areas, FSA, or 1{,}061 municipalities); $R^2$ is then measured against the total variance of log price and ``Within $R^2$'' against the within-group variance. $\Delta R^2$ (sem.) is the gain in $R^2$ from adding the 20 similarities to the otherwise identical specification. Block $F$ is the robust Wald test (HC3 or clustered by FSA/municipality) that the 20 semantic coefficients are jointly zero; all $p < 0.001$. ``Sig.'' counts similarities individually significant at the 5\% level. The unit-corrected lot area converts the raw field to square metres (m$^2$, sq.\ ft., acres, hectares) and enters in logs with a missing-value indicator; the floor-area subsample is restricted to the 6{,}228 listings reporting interior floor area.
\end{minipage}
\end{table}