arc_weak_acc: 0.5080 arc_hard_acc: 0.5180 arc_soft_acc: 0.2560 arc_ceiling_acc: 0.5530 arc_delta_soft_minus_hard: -0.2620 arc_pgr_hard: 0.2222 arc_pgr_soft: -5.6000 mmlu_weak_acc: 0.4020 mmlu_hard_acc: 0.2410 mmlu_soft_acc: 0.2590 mmlu_ceiling_acc: 0.6030 mmlu_delta_soft_minus_hard: 0.0180 mmlu_pgr_hard: -0.8010 mmlu_pgr_soft: -0.7114 pooled_weak_acc: 0.4550 pooled_hard_acc: 0.3795 pooled_soft_acc: 0.2575 pooled_ceiling_acc: 0.5780 pooled_delta_soft_minus_hard: -0.1220 ms_weak_acc: 0.5038 ms_hard_mean: 0.3980 ms_hard_std: 0.1605 ms_soft_mean: 0.4303 ms_soft_std: 0.1544 ms_delta_mean: 0.0323 ms_delta_std: 0.2726 ms_paired_t: 0.2645 ms_delta_ci_lo: -0.3063 ms_delta_ci_hi: 0.3708 ms_students_below_weak_frac: 0.6000 ms_seeds_delta_positive: 3.0000 ms_seeds_delta_negative: 2.0000 manip_auc_pooled: 0.6596 manip_auc_arc: 0.6814 manip_auc_mmlu: 0.6121