SPB Git

spb/wp31_uqo

Public
1.3 KB · 21 lines latex
1\begin{table}[t]\centering\small2\caption{Pre-registered uncertainty analysis of dev-iid exact match (percentage points). ``t-CI'' is the 95\,\%3$t$-interval over independent adapter seeds of the per-seed paired difference; ``item CI range'' spans the4smallest lower and largest upper bound of the per-seed paired item bootstraps (10,000 resamples, 1,000 items).}5\label{tab:stats}6\begin{tabular}{lrrll}\toprule7Comparison & seeds & mean & t-CI over seeds & item CI range\\\midrule8prisme b1 vs b0 & 5 & +1.58 & [+1.21, +1.95] & [+0.30, +3.30]\\9prisme b2 vs b0 & 5 & +1.92 & [+1.60, +2.24] & [+0.10, +3.90]\\10prisme b8 vs b0 & 5 & +1.50 & [+0.94, +2.06] & [-1.10, +4.50]\\11gr b1 vs b0 & 5 & +2.14 & [+1.76, +2.52] & [+0.20, +4.10]\\12gr b2 vs b0 & 5 & +1.86 & [+1.37, +2.35] & [-0.30, +4.50]\\13gr b8 vs b0 & 5 & +2.34 & [+0.97, +3.71] & [-1.40, +6.20]\\14dense b1 vs b0 & 5 & +2.06 & [+1.75, +2.37] & [+0.50, +3.60]\\15dense b2 vs b0 & 5 & +2.00 & [+1.58, +2.42] & [+0.00, +3.90]\\16dense b8 vs b0 & 5 & +1.34 & [+0.68, +2.00] & [-1.40, +4.30]\\17prisme minus gr b1 & 5 & -0.56 & [-0.85, -0.27] & [-2.20, +0.90]\\18prisme minus gr b2 & 5 & +0.06 & [-0.53, +0.65] & [-2.20, +2.00]\\19prisme minus gr b8 & 5 & -0.84 & [-2.43, +0.75] & [-4.40, +2.50]\\20\bottomrule\end{tabular}\end{table}21
Files · a2c46f03643fdd75e8e87595931d35e18c590d57
Menu

Theme