base_pass_at_1: 0.29 base_pass_at_1_ci95_high: 0.35 base_pass_at_1_ci95_low: 0.225 base_solved_cost_ci95_high: 50 base_solved_cost_ci95_low: 25.86206897 base_solved_cost_p: 0 base_solved_cost_points: 37.93103448 base_solved_n: 58 base_solved_retention: 0.6206896552 delta_beats_permuted_ci_separated: 0 delta_beats_random_ci_separated: 1 delta_minus_permuted_ci95_high: 0.165 delta_minus_permuted_ci95_low: -0.01 delta_minus_permuted_p: 0.091 delta_minus_permuted_pass_at_1: 0.08 delta_minus_random_ci95_high: 0.265125 delta_minus_random_ci95_low: 0.1 delta_minus_random_p: 0 delta_minus_random_pass_at_1: 0.185 delta_pass_at_1: 0.44 delta_pass_at_1_ci95_high: 0.51 delta_pass_at_1_ci95_low: 0.375 heldout_manip_cosine_applied_shift_to_heldout_post_minus_base: 0.2934749722 heldout_manip_distance_fraction_reduced: 0.04256332174 heldout_manip_n_items: 32 mean_new_tokens_base: 351.87 mean_new_tokens_delta: 546.255 mean_new_tokens_permuted: 370.44 mean_new_tokens_random: 407.98 mean_new_tokens_sibling: 929.775 n_items: 200 permuted_pass_at_1: 0.36 permuted_pass_at_1_ci95_high: 0.43 permuted_pass_at_1_ci95_low: 0.295 random_pass_at_1: 0.255 random_pass_at_1_ci95_high: 0.315 random_pass_at_1_ci95_low: 0.195 recovery_fraction: 0.3614457831 recovery_fraction_ci95_high: 0.5287525355 recovery_fraction_ci95_low: 0.170448501 recovery_fraction_denominator_sibling_minus_base: 0.415 recovery_fraction_meets_50pct_by_ci: 0 recovery_fraction_numerator_delta_minus_base: 0.15 recovery_fraction_p: 0.109 sibling_pass_at_1: 0.705 sibling_pass_at_1_ci95_high: 0.77 sibling_pass_at_1_ci95_low: 0.644875