summaryrefslogtreecommitdiff
path: root/ptrm_gbs768_base_vs_multi4_k100_d64_sigma03_Lonly_n1000_seed0.summary.csv
blob: 8afa74e205279aaf9ce7f2ed7443b00681a26934 (plain)
1
2
base/K_for_oracle_pass_0.9,base/K_for_oracle_pass_0.95,base/K_for_oracle_pass_0.975,base/K_for_oracle_pass_0.99,base/K_for_q_max_exact_0.9,base/K_for_q_max_exact_0.95,base/K_for_q_max_exact_0.975,base/K_for_q_max_exact_0.99,base/all_correct_frac,base/correct_count_det_fail_mean,base/correct_count_det_success_mean,base/correct_count_ge_10_frac,base/correct_count_ge_1_frac,base/correct_count_ge_25_frac,base/correct_count_ge_50_frac,base/correct_count_ge_5_frac,base/correct_count_ge_75_frac,base/correct_count_ge_90_frac,base/correct_count_mean,base/correct_count_median,base/correct_count_q10,base/correct_count_q25,base/correct_count_q75,base/correct_count_q90,base/det_exact,base/mean_rollout_exact,base/oracle_det_fail_frac,base/oracle_det_success_frac,base/oracle_pass,base/q_max_det_fail_frac,base/q_max_det_success_frac,base/q_max_exact,base/zero_correct_frac,base_file,base_nonzero_test_zero_frac,base_zero_test_nonzero_frac,both_oracle_success_test_more_frac,delta_correct_count_mean,delta_correct_count_median,delta_correct_count_q10,delta_correct_count_q25,delta_correct_count_q75,delta_correct_count_q90,multi4/K_for_oracle_pass_0.9,multi4/K_for_oracle_pass_0.95,multi4/K_for_oracle_pass_0.975,multi4/K_for_oracle_pass_0.99,multi4/K_for_q_max_exact_0.9,multi4/K_for_q_max_exact_0.95,multi4/K_for_q_max_exact_0.975,multi4/K_for_q_max_exact_0.99,multi4/all_correct_frac,multi4/correct_count_det_fail_mean,multi4/correct_count_det_success_mean,multi4/correct_count_ge_10_frac,multi4/correct_count_ge_1_frac,multi4/correct_count_ge_25_frac,multi4/correct_count_ge_50_frac,multi4/correct_count_ge_5_frac,multi4/correct_count_ge_75_frac,multi4/correct_count_ge_90_frac,multi4/correct_count_mean,multi4/correct_count_median,multi4/correct_count_q10,multi4/correct_count_q25,multi4/correct_count_q75,multi4/correct_count_q90,multi4/det_exact,multi4/mean_rollout_exact,multi4/oracle_det_fail_frac,multi4/oracle_det_success_frac,multi4/oracle_pass,multi4/q_max_det_fail_frac,multi4/q_max_det_success_frac,multi4/q_max_exact,multi4/zero_correct_frac,n_samples,oracle_base_only_frac,oracle_both_fail_frac,oracle_both_success_frac,oracle_test_only_frac,q_max_base_only_frac,q_max_both_fail_frac,q_max_both_success_frac,q_max_test_only_frac,rollouts,test_equal_correct_frac,test_fewer_correct_frac,test_file,test_more_correct_frac
1.0,2.0,6.0,nan,1.0,2.0,6.0,nan,0.85,54.380531311035156,99.2593002319336,0.976,0.985,0.961,0.949,0.981,0.924,0.905,94.18800354003906,100.0,91.0,100.0,100.0,100.0,0.887,0.94188,0.8672566371681416,1.0,0.985,0.8584070796460177,1.0,0.984,0.015,research/flossing/ptrm_official_gbs768_base58590_k100_d64_sigma03_Lonly_n1000_seed0.npz,0.001,0.004,0.107,1.2289999723434448,0.0,0.0,0.0,0.0,1.0,1.0,1.0,10.0,nan,1.0,1.0,10.0,nan,0.889,53.08988952636719,99.55213928222656,0.974,0.988,0.964,0.956,0.979,0.947,0.935,95.41699981689453,100.0,99.0,100.0,100.0,100.0,0.911,0.95417,0.8651685393258427,1.0,0.988,0.8651685393258427,1.0,0.988,0.012,1000.0,0.001,0.011,0.984,0.004,0.001,0.011,0.983,0.005,100.0,0.831,0.058,research/flossing/ptrm_official_gbs768_multi4_35805_k100_d64_sigma03_Lonly_n1000_seed0.npz,0.111