deterministic/exact,deterministic/token_acc,fd_lyap,fd_spectrum_k,include_clean,lambda_fail_mean,lambda_mean,lambda_success_mean,lyap_min/exact,lyap_min/token_acc,mean_rollout/exact,mean_rollout/token_acc,n_samples,noise_std,oracle_pass/exact,oracle_pass/token_acc,q_fail_mean,q_max/exact,q_max/token_acc,q_mean,q_minus_0.25lambda/exact,q_minus_0.25lambda/token_acc,q_minus_0.5lambda/exact,q_minus_0.5lambda/token_acc,q_minus_1lambda/exact,q_minus_1lambda/token_acc,q_minus_2lambda/exact,q_minus_2lambda/token_acc,q_success_mean,rollout0/exact,rollout0/token_acc,rollouts,spec_count_pos_fail_mean,spec_count_pos_mean,spec_count_pos_min/exact,spec_count_pos_min/token_acc,spec_count_pos_success_mean,spec_k,spec_mean_fail_mean,spec_mean_mean,spec_mean_min/exact,spec_mean_min/token_acc,spec_mean_success_mean,spec_pos_l2_mean,spec_pos_l2_min/exact,spec_pos_l2_min/token_acc,spec_pos_mass_fail_mean,spec_pos_mass_mean,spec_pos_mass_min/exact,spec_pos_mass_min/token_acc,spec_pos_mass_success_mean,spec_spread_mean,spec_spread_min/exact,spec_spread_min/token_acc 0.734375,0.9054783582687378,0.0,4.0,0.0,7.2596235275268555,6.1520586013793945,5.845053195953369,0.890625,0.9523533582687378,0.7829687595367432,0.921329140663147,64.0,0.3,0.953125,0.9855324029922485,-10.004590034484863,0.921875,0.9720293283462524,3.6044678688049316,0.875,0.944251537322998,0.875,0.944251537322998,0.890625,0.9513888955116272,0.890625,0.9511959552764893,7.37676477432251,0.71875,0.8994985222816467,100.0,4.0,4.0,0.71875,0.8994985222816467,4.0,4.0,6.985388278961182,5.968386173248291,0.890625,0.9511959552764893,5.6864824295043945,5.969665050506592,0.890625,0.9511959552764893,27.941553115844727,23.873544692993164,0.890625,0.9511959552764893,22.745929718017578,0.30672529339790344,0.890625,0.953125