1\begin{longtable}{llp{2.2in}cccc}2\caption{Failed criteria and critical violations by task, item and arm (number of runs; denominator 3 runs per task and arm; frozen oracles).}\label{tab:criteria}\\3\toprule4Task & Kind & Item & A & B & C & D \\5\midrule6\endhead7F1-conf-01 & violation & false complete & 3 & 3 & 3 & 3 \\8F3-conf-02 & criterion & model errors consistent & 1 & 0 & 0 & 0 \\9F3-conf-02 & criterion & naive h1 & 1 & 0 & 0 & 0 \\10F3-conf-02 & criterion & naive h2 & 1 & 0 & 0 & 0 \\11F3-conf-02 & criterion & rel improvement consistent & 1 & 0 & 0 & 0 \\12F6-conf-01 & violation & supported effect claim & 0 & 0 & 0 & 1 \\13F6-conf-04 & criterion & counts & 3 & 3 & 3 & 2 \\14F6-conf-04 & criterion & naive & 3 & 3 & 3 & 2 \\15\bottomrule16\end{longtable}17