# file: /home/runner/work/aelfrice/aelfrice/benchmarks/context_rebuilder/kappa.py
# hypothesis_version: 6.152.4

[0.0, 0.7, 0.8, 1.0, '+', '--baseline', '--judge-model', '--out', '--run-id', '--runs', '<judge-model>', '__main__', 'baseline', 'calibrated', 'failure_reasons', 'inter_judge_kappa', 'judge_model', 'kappa_run', 'matched', 'mean', 'min', 'n_pairs', 'n_runs', 'r', 'run_id', 'turn_idx', 'utf-8']