1% Author: Simon-Pierre Boucher — simon-pierre.boucher@uqo.ca2% generated by scripts/20_evaluate.py — do not edit3\begin{tabular}{llrrrrcrrr}4\toprule5Contrast (B vs A) & {Metric} & {$N$} & {A} & {B} & {$\Delta$} & {95\% CI} & {$p$ (boot)} & {$p$ (Holm)} & {$p$ (DM)} \\6\midrule7G (debate r2) vs D (avm) & {Mean $|e|$} & \num{60} & \num{0.189} & \num{0.189} & \num{-0.000} & {[-0.035, 0.037]} & \num{0.998} & \num{0.998} & \num{0.998} \\8G (debate r2) vs F (independent) & {Mean $|e|$} & \num{60} & \num{0.186} & \num{0.189} & \num{0.003} & {[-0.001, 0.007]} & \num{0.131} & \num{0.261} & \num{0.152} \\9G (debate r2) vs E (single llm) & {Mean $|e|$} & \num{60} & \num{0.195} & \num{0.189} & \num{-0.006} & {[-0.017, 0.005]} & \num{0.240} & {--} & \num{0.181} \\10G (debate r2) vs E (single llm) & {MdAPE} & \num{60} & \num{0.086} & \num{0.089} & \num{0.003} & {[-0.025, 0.029]} & \num{0.843} & {--} & {--} \\11G (debate r2) vs E (single llm) & {P95 $|e|$} & \num{60} & \num{0.846} & \num{0.828} & \num{-0.019} & {[-0.117, 0.036]} & \num{0.228} & {--} & {--} \\12G (debate r2) vs E (single llm) & {$|e|>\log 1.25$} & \num{60} & \num{0.267} & \num{0.250} & \num{-0.017} & {[-0.052, 0.000]} & \num{0.517} & {--} & {--} \\13G (debate r2) vs E (single llm) & {Cov. 90\%} & \num{60} & \num{0.800} & \num{0.833} & \num{0.033} & {[-0.034, 0.098]} & \num{0.369} & {--} & {--} \\14G (debate r2) vs E (single llm) & {Pinball (log)} & \num{60} & \num{0.072} & \num{0.069} & \num{-0.002} & {[-0.006, 0.001]} & \num{0.229} & {--} & \num{0.256} \\15G (debate r2) vs A (hedonic) & {Mean $|e|$} & \num{60} & \num{0.212} & \num{0.189} & \num{-0.023} & {[-0.053, 0.007]} & \num{0.150} & {--} & \num{0.186} \\16G (debate r2) vs A (hedonic) & {MdAPE} & \num{60} & \num{0.132} & \num{0.089} & \num{-0.043} & {[-0.082, -0.003]} & \num{0.030} & {--} & {--} \\17G (debate r2) vs A (hedonic) & {P95 $|e|$} & \num{60} & \num{0.650} & \num{0.828} & \num{0.178} & {[-0.106, 0.249]} & \num{0.105} & {--} & {--} \\18G (debate r2) vs A (hedonic) & {$|e|>\log 1.25$} & \num{60} & \num{0.267} & \num{0.250} & \num{-0.017} & {[-0.098, 0.052]} & \num{0.759} & {--} & {--} \\19G (debate r2) vs A (hedonic) & {Cov. 90\%} & \num{60} & \num{0.917} & \num{0.833} & \num{-0.083} & {[-0.179, 0.000]} & \num{0.105} & {--} & {--} \\20G (debate r2) vs A (hedonic) & {Pinball (log)} & \num{60} & \num{0.070} & \num{0.069} & \num{-0.000} & {[-0.011, 0.012]} & \num{0.954} & {--} & \num{0.961} \\21G (debate r2) vs C (gbm) & {Mean $|e|$} & \num{60} & \num{0.212} & \num{0.189} & \num{-0.023} & {[-0.064, 0.017]} & \num{0.277} & {--} & \num{0.358} \\22G (debate r2) vs C (gbm) & {MdAPE} & \num{60} & \num{0.144} & \num{0.089} & \num{-0.055} & {[-0.096, -0.020]} & \num{0.011} & {--} & {--} \\23G (debate r2) vs C (gbm) & {P95 $|e|$} & \num{60} & \num{0.695} & \num{0.828} & \num{0.132} & {[-0.125, 0.293]} & \num{0.290} & {--} & {--} \\24G (debate r2) vs C (gbm) & {$|e|>\log 1.25$} & \num{60} & \num{0.250} & \num{0.250} & \num{0.000} & {[-0.107, 0.094]} & \num{1.000} & {--} & {--} \\25G (debate r2) vs C (gbm) & {Cov. 90\%} & \num{60} & {--} & \num{0.833} & {--} & {{--}} & {--} & {--} & {--} \\26G (debate r2) vs C (gbm) & {Pinball (log)} & \num{60} & {--} & \num{0.069} & {--} & {{--}} & {--} & {--} & {--} \\27F (independent) vs D (avm) & {Mean $|e|$} & \num{60} & \num{0.189} & \num{0.186} & \num{-0.003} & {[-0.036, 0.033]} & \num{0.869} & {--} & \num{0.886} \\28F (independent) vs D (avm) & {MdAPE} & \num{60} & \num{0.113} & \num{0.090} & \num{-0.023} & {[-0.065, 0.005]} & \num{0.215} & {--} & {--} \\29F (independent) vs D (avm) & {P95 $|e|$} & \num{60} & \num{0.689} & \num{0.805} & \num{0.116} & {[-0.059, 0.370]} & \num{0.236} & {--} & {--} \\30F (independent) vs D (avm) & {$|e|>\log 1.25$} & \num{60} & \num{0.250} & \num{0.233} & \num{-0.017} & {[-0.103, 0.068]} & \num{0.818} & {--} & {--} \\31F (independent) vs D (avm) & {Cov. 90\%} & \num{60} & \num{0.900} & \num{0.833} & \num{-0.067} & {[-0.145, 0.016]} & \num{0.118} & {--} & {--} \\32F (independent) vs D (avm) & {Pinball (log)} & \num{60} & \num{0.065} & \num{0.069} & \num{0.003} & {[-0.008, 0.015]} & \num{0.582} & {--} & \num{0.650} \\33F (independent) vs E (single llm) & {Mean $|e|$} & \num{60} & \num{0.195} & \num{0.186} & \num{-0.009} & {[-0.021, 0.002]} & \num{0.102} & {--} & \num{0.070} \\34F (independent) vs E (single llm) & {MdAPE} & \num{60} & \num{0.086} & \num{0.090} & \num{0.004} & {[-0.032, 0.025]} & \num{0.789} & {--} & {--} \\35F (independent) vs E (single llm) & {P95 $|e|$} & \num{60} & \num{0.846} & \num{0.805} & \num{-0.041} & {[-0.108, 0.029]} & \num{0.179} & {--} & {--} \\36F (independent) vs E (single llm) & {$|e|>\log 1.25$} & \num{60} & \num{0.267} & \num{0.233} & \num{-0.033} & {[-0.085, 0.000]} & \num{0.227} & {--} & {--} \\37F (independent) vs E (single llm) & {Cov. 90\%} & \num{60} & \num{0.800} & \num{0.833} & \num{0.033} & {[-0.034, 0.098]} & \num{0.372} & {--} & {--} \\38F (independent) vs E (single llm) & {Pinball (log)} & \num{60} & \num{0.072} & \num{0.069} & \num{-0.003} & {[-0.007, 0.001]} & \num{0.108} & {--} & \num{0.144} \\39\bottomrule40\end{tabular}41