1arm,n_runs,n_tasks,n_evaluated,Y_task_weighted,Y_run_mean,correct_any_task_weighted,violation_rate,n_runs_with_violation,reproducible_rate,quality_mean,q_correctness,q_reporting,q_baseline,cost_mean_usd,cost_median_usd,cost_p90_usd,cost_total_usd,reviewer_usd_total,wall_median_s,wall_p90_s,n_timeout,n_budget_exhausted,n_sessions_mean,cost_per_success_usd2A,72,24,72,0.986111111111111,0.9861111111111112,0.986111111111111,0.0,0,1.0,0.9810847222222221,0.9816468253968255,0.9969135802469135,0.9722222222222222,0.24199995833333332,0.21324300000000002,0.41118730000000003,17.423997,0.0,67.75,103.11,0,0,1.0,0.245408408450704223B,72,24,72,1.0,1.0,1.0,0.0,0,1.0,0.9841319444444443,0.9895833333333334,0.991435185185185,0.9791666666666666,0.42211899999999997,0.3858505,0.6234624999999999,30.392567999999997,0.0,115.5,175.79,0,0,1.0,0.422118999999999974C,72,24,72,1.0,1.0,1.0,0.0,0,1.0,0.9854166666666667,0.9895833333333334,1.0,0.9791666666666666,0.45164937499999996,0.430682,0.6584917,32.518755,0.0,127.9,168.71,0,0,1.0,0.451649374999999965D,72,24,71,0.9722222222222222,0.9722222222222222,0.9722222222222222,0.013888888888888888,1,1.0,0.9845070422535213,0.9929577464788732,1.0,0.9859154929577465,0.6365128169014085,0.606481,0.908648,45.19241,11.455315,176.2,228.4,0,0,2.0,0.64560585714285726