Python 52.4%
TeX 47.6%
1% Auto-generated2\begin{table}[htbp]3 \centering4 \begin{threeparttable}5 \caption{Machine-Generated Feature Summary}6 \label{tab:ai_summary}7 \begin{tabular}{@{}lc@{\hskip 1.2cm}lc@{}}8 \toprule9 Text (LLM) & Share & Vision (façade) & Mean / share \\10 \midrule11 Recently renovated & 26\% & Condition score (1--10) & 7.4 \\12 Renovated kitchen & 17\% & Curb appeal (1--10) & 7.2 \\13 Hardwood floor & 16\% & Luxury cue & 43\% \\14 Quartz/granite counter & 7\% & Garage visible & 46\% \\15 New construction & 14\% & Brick façade & 47\% \\16 Income property & 12\% & Waterfront setting & 7\% \\17 Water view & 24\% & Exterior shot detected & 96\% \\18 \bottomrule19 \end{tabular}20 \begin{tablenotes}[flushleft]21 \footnotesize22 \item \textit{Notes:} Prevalence of selected machine-generated attributes across23 the 19{,}123 cleaned listings. Text attributes are extracted from the24 description by \texttt{gpt-4o-mini}; vision attributes from the façade photograph by25 \texttt{claude-haiku-4-5}. Scores are 1--10 means; the remainder are shares.26 \end{tablenotes}27 \end{threeparttable}28\end{table}29