% Author: Simon-Pierre Boucher — contact@spboucher.ai
% Generated by scripts/08_revision_tables.py — do not edit by hand.
\begin{table}[!htbp]
\centering
\caption{Sensitivity of Model~D to the phrasing of the reference descriptions.}
\label{tab:reference_sensitivity}
\small
\begin{adjustbox}{max width=\textwidth}
\begin{tabular}{lR{1.6cm}R{1.1cm}R{1.4cm}R{1.3cm}R{1.7cm}R{1.6cm}R{1.1cm}}
\toprule
\textbf{Reference variant} & \textbf{Corr.\ of similarities} & $\boldsymbol{R^2}$ & $\boldsymbol{\Delta R^2}$ \textbf{(sem.)} & \textbf{Block} $\boldsymbol{F}$ & \textbf{Corr.\ of coefficients} & \textbf{Sign agreement} & \textbf{Sig.} \\
\midrule
Baseline (full references) & 1.000 & 0.5122 & 0.048 & 54.3 & 1.000 & 100\% & 16/20 \\
First half of each reference's phrases & 0.970 & 0.5185 & 0.054 & 63.5 & 0.625 & 81\% & 15/20 \\
Second half of each reference's phrases & 0.929 & 0.5080 & 0.043 & 52.6 & 0.024 & 62\% & 11/20 \\
Phrases in reverse order & 0.987 & 0.5066 & 0.042 & 51.6 & 0.805 & 88\% & 11/20 \\
\bottomrule
\end{tabular}
\end{adjustbox}
\begin{minipage}{\textwidth}
\vspace{4pt}\footnotesize
\textit{Notes:} Each reference text in Appendix Table~\ref{tab:reference_texts} is split into its comma-separated phrases and re-encoded with all-MiniLM-L6-v2 after the indicated perturbation; Model~D is then re-estimated with the 20 perturbed similarities. ``Corr.\ of similarities'' is the mean, over the 20 dimensions, of the correlation between perturbed and baseline similarity scores; ``Corr.\ of coefficients'' is the correlation between the 20 perturbed and baseline semantic coefficients; ``Sign agreement'' is the share of the 16 dimensions significant in the baseline whose coefficient keeps its sign; ``Sig.'' counts dimensions significant at 5\%. Block $F$ is the HC3 Wald test of the 20 semantic coefficients.
\end{minipage}
\end{table}