# w2sg-peritem-harder-llama analysis summary (run hypgen-20260708-213130-1-fu1); curve.csv ships alongside with per-dataset per-condition mean_acc/CI, mean_pgr/CI, train_label_gold; 3 seeds (0,1,2), full mode, RTX 5090 boolq_n_seeds: 3.000000 boolq_weak_acc: 0.806116 boolq_ceiling_acc: 0.888175 boolq_base_fewshot_student_acc_mean: 0.621713 boolq_base_fewshot_student_acc_ci_low: 0.621713 boolq_base_fewshot_student_acc_ci_high: 0.621713 boolq_base_fewshot_pgr_mean: -2.247205 boolq_base_fewshot_pgr_ci_low: -2.247205 boolq_base_fewshot_pgr_ci_high: -2.247205 boolq_base_fewshot_train_label_gold_accuracy_mean: nan boolq_gold_ceiling_student_acc_mean: 0.888175 boolq_gold_ceiling_student_acc_ci_low: 0.884098 boolq_gold_ceiling_student_acc_ci_high: 0.893272 boolq_gold_ceiling_pgr_mean: 1.000000 boolq_gold_ceiling_pgr_ci_low: 0.950311 boolq_gold_ceiling_pgr_ci_high: 1.062112 boolq_gold_ceiling_train_label_gold_accuracy_mean: 1.000000 boolq_real_weak_student_acc_mean: 0.832008 boolq_real_weak_student_acc_ci_low: 0.811009 boolq_real_weak_student_acc_ci_high: 0.849847 boolq_real_weak_pgr_mean: 0.315528 boolq_real_weak_pgr_ci_low: 0.059627 boolq_real_weak_pgr_ci_high: 0.532919 boolq_real_weak_train_label_gold_accuracy_mean: 0.796500 boolq_shuffled_weak_student_acc_mean: 0.621509 boolq_shuffled_weak_student_acc_ci_low: 0.621407 boolq_shuffled_weak_student_acc_ci_high: 0.621713 boolq_shuffled_weak_pgr_mean: -2.249689 boolq_shuffled_weak_pgr_ci_low: -2.250932 boolq_shuffled_weak_pgr_ci_high: -2.247205 boolq_shuffled_weak_train_label_gold_accuracy_mean: 0.528500 boolq_random_label_student_acc_mean: 0.564934 boolq_random_label_student_acc_ci_low: 0.478287 boolq_random_label_student_acc_ci_high: 0.621101 boolq_random_label_pgr_mean: -2.939130 boolq_random_label_pgr_ci_low: -3.995031 boolq_random_label_pgr_ci_high: -2.254658 boolq_random_label_train_label_gold_accuracy_mean: 0.505167 boolq_constant_majority_student_acc_mean: 0.621713 boolq_constant_majority_student_acc_ci_low: 0.621713 boolq_constant_majority_student_acc_ci_high: 0.621713 boolq_constant_majority_pgr_mean: -2.247205 boolq_constant_majority_pgr_ci_low: -2.247205 boolq_constant_majority_pgr_ci_high: -2.247205 boolq_constant_majority_train_label_gold_accuracy_mean: 0.626500 boolq_real_minus_shuffled_weak_acc_diff_mean: 0.210499 boolq_real_minus_shuffled_weak_acc_diff_ci_low: 0.189602 boolq_real_minus_shuffled_weak_acc_diff_ci_high: 0.228135 boolq_real_minus_shuffled_weak_acc_diff_perm_p: 0.250000 boolq_real_minus_random_label_acc_diff_mean: 0.267074 boolq_real_minus_random_label_acc_diff_ci_low: 0.189908 boolq_real_minus_random_label_acc_diff_ci_high: 0.371560 boolq_real_minus_random_label_acc_diff_perm_p: 0.250000 boolq_real_minus_constant_majority_acc_diff_mean: 0.210296 boolq_real_minus_constant_majority_acc_diff_ci_low: 0.189297 boolq_real_minus_constant_majority_acc_diff_ci_high: 0.228135 boolq_real_minus_constant_majority_acc_diff_perm_p: 0.250000 boolq_real_weak_pgr_mean: 0.315528 boolq_shuffled_weak_pgr_mean: -2.249689 boolq_real_minus_shuffled_pgr_mean: 2.565217 boolq_real_minus_shuffled_pgr_ci_low: 2.310559 boolq_real_minus_shuffled_pgr_ci_high: 2.780124 boolq_real_minus_shuffled_pgr_perm_p: 0.250000 sst2_n_seeds: 3.000000 sst2_weak_acc: 0.941514 sst2_ceiling_acc: 0.954893 sst2_base_fewshot_student_acc_mean: 0.952982 sst2_base_fewshot_student_acc_ci_low: 0.952982 sst2_base_fewshot_student_acc_ci_high: 0.952982 sst2_base_fewshot_pgr_mean: 0.857143 sst2_base_fewshot_pgr_ci_low: 0.857143 sst2_base_fewshot_pgr_ci_high: 0.857143 sst2_base_fewshot_train_label_gold_accuracy_mean: nan sst2_gold_ceiling_student_acc_mean: 0.954893 sst2_gold_ceiling_student_acc_ci_low: 0.944954 sst2_gold_ceiling_student_acc_ci_high: 0.959862 sst2_gold_ceiling_pgr_mean: 1.000000 sst2_gold_ceiling_pgr_ci_low: 0.257143 sst2_gold_ceiling_pgr_ci_high: 1.371429 sst2_gold_ceiling_train_label_gold_accuracy_mean: 1.000000 sst2_real_weak_student_acc_mean: 0.939602 sst2_real_weak_student_acc_ci_low: 0.936927 sst2_real_weak_student_acc_ci_high: 0.943807 sst2_real_weak_pgr_mean: -0.142857 sst2_real_weak_pgr_ci_low: -0.342857 sst2_real_weak_pgr_ci_high: 0.171429 sst2_real_weak_train_label_gold_accuracy_mean: 0.935000 sst2_shuffled_weak_student_acc_mean: 0.531346 sst2_shuffled_weak_student_acc_ci_low: 0.509174 sst2_shuffled_weak_student_acc_ci_high: 0.571101 sst2_shuffled_weak_pgr_mean: -30.657143 sst2_shuffled_weak_pgr_ci_low: -32.314286 sst2_shuffled_weak_pgr_ci_high: -27.685714 sst2_shuffled_weak_train_label_gold_accuracy_mean: 0.497667 sst2_random_label_student_acc_mean: 0.509939 sst2_random_label_student_acc_ci_low: 0.496560 sst2_random_label_student_acc_ci_high: 0.524083 sst2_random_label_pgr_mean: -32.257143 sst2_random_label_pgr_ci_low: -33.257143 sst2_random_label_pgr_ci_high: -31.200000 sst2_random_label_train_label_gold_accuracy_mean: 0.498000 sst2_constant_majority_student_acc_mean: 0.509174 sst2_constant_majority_student_acc_ci_low: 0.509174 sst2_constant_majority_student_acc_ci_high: 0.509174 sst2_constant_majority_pgr_mean: -32.314286 sst2_constant_majority_pgr_ci_low: -32.314286 sst2_constant_majority_pgr_ci_high: -32.314286 sst2_constant_majority_train_label_gold_accuracy_mean: 0.563000 sst2_real_minus_shuffled_weak_acc_diff_mean: 0.408257 sst2_real_minus_shuffled_weak_acc_diff_ci_low: 0.365826 sst2_real_minus_shuffled_weak_acc_diff_ci_high: 0.430046 sst2_real_minus_shuffled_weak_acc_diff_perm_p: 0.250000 sst2_real_minus_random_label_acc_diff_mean: 0.429664 sst2_real_minus_random_label_acc_diff_ci_low: 0.413991 sst2_real_minus_random_label_acc_diff_ci_high: 0.447248 sst2_real_minus_random_label_acc_diff_perm_p: 0.250000 sst2_real_minus_constant_majority_acc_diff_mean: 0.430428 sst2_real_minus_constant_majority_acc_diff_ci_low: 0.427752 sst2_real_minus_constant_majority_acc_diff_ci_high: 0.434633 sst2_real_minus_constant_majority_acc_diff_perm_p: 0.250000 sst2_real_weak_pgr_mean: -0.142857 sst2_shuffled_weak_pgr_mean: -30.657143 sst2_real_minus_shuffled_pgr_mean: 30.514286 sst2_real_minus_shuffled_pgr_ci_low: 27.342857 sst2_real_minus_shuffled_pgr_ci_high: 32.142857 sst2_real_minus_shuffled_pgr_perm_p: 0.250000