ResearchBenchmarksSelective Prediction on SQuAD 2.0Follow69.04Coverage@0.9UAT-LITE49.311254.433159.55564.6769Feb 3, 2026Evaluation ResultsMethodMethodLinksCoverage@0.9Coverage@0.8Coverage@0.7AURCUAT-LITEevaluation=mean over f...evaluation=mean over five seeds2026.0269.0470.4771.630.2892Baselinetype=deterministictype=deterministic2026.0250.0750.7150.50.4472