primary_qwen_increment: 0.006794389525559219
primary_qwen_ci_lo: -0.07086694077508525
primary_qwen_ci_hi: 0.09271309013501285
primary_qwen_p_one_sided: 0.4032596740325967
primary_qwen_n_treatment: 70
primary_qwen_n_control: 71
extension_qwen_increment: 0.03136056429600764
extension_qwen_ci_lo: -0.008761403530060767
extension_qwen_ci_hi: 0.07775887907114178
extension_qwen_holm_p_one_sided: 0.0527947205279472
extension_qwen_n_treatment: 364
extension_qwen_n_control: 346
manipulation_qwen_holm_significant_items: 0
manipulation_qwen_within_control_floor: 0.035
manipulation_qwen_floor_ci_lo: 0.0
manipulation_qwen_floor_ci_hi: 1.0
manipulation_qwen_minimum_holm_item_p: 0.23350489358658658
extension_llama_increment: 0.046674322076803665
extension_llama_ci_lo: -0.01826710785812408
extension_llama_ci_hi: 0.14227908306083967
extension_llama_holm_p_one_sided: 0.0527947205279472
extension_llama_n_treatment: 174
extension_llama_n_control: 157
manipulation_llama_holm_significant_items: 1
manipulation_llama_within_control_floor: 0.015
manipulation_llama_floor_ci_lo: 0.0
manipulation_llama_floor_ci_hi: 0.0
manipulation_llama_minimum_holm_item_p: 0.03458606795761232
parse_leg1_qwen_control_rate: 0.8875
parse_leg1_qwen_control_n: 71
parse_leg1_qwen_treatment_rate: 0.875
parse_leg1_qwen_treatment_n: 70
parse_leg2_llama_control_rate: 0.3925
parse_leg2_llama_control_n: 157
parse_leg2_llama_treatment_rate: 0.435
parse_leg2_llama_treatment_n: 174
parse_leg2_qwen_control_rate: 0.865
parse_leg2_qwen_control_n: 346
parse_leg2_qwen_treatment_rate: 0.91
parse_leg2_qwen_treatment_n: 364
posthoc_review_wave: 1
posthoc_item1_alpha_seq_per_family_one_sided: 0.025
posthoc_item1_information_fraction_qwen: 0.16568742655699178
posthoc_item1_looks_qwen: 2
posthoc_item1_looks_llama: 1
posthoc_item1_qwen_look1_z: 0.24491874392169385
posthoc_item1_qwen_look2_z: 1.8055228656991225
posthoc_item1_llama_look2_z: 1.9365962189435788
posthoc_item1_obf_alpha_spent_look1: 3.660517666759233e-08
posthoc_item1_obf_boundary_look1_z: 5.383108559915048
posthoc_item1_obf_boundary_look2_z: 1.9599642167296585
posthoc_item1_obf_nominal_alpha_look2: 0.0249999864296655
posthoc_item1_obf_qwen_crosses: 0
posthoc_item1_obf_llama_crosses: 0
posthoc_item1_pocock_alpha_spent_look1: 0.006263085832057279
posthoc_item1_pocock_boundary_look1_z: 2.4969638753314336
posthoc_item1_pocock_boundary_look2_z: 2.0589919417759157
posthoc_item1_pocock_nominal_alpha_look2: 0.019747505220649275
posthoc_item1_pocock_qwen_crosses: 0
posthoc_item1_pocock_llama_crosses: 0
posthoc_item1_holm_p_unchanged: 1
posthoc_item1_conclusion_changed: 0
posthoc_item2_qwen_intersection_increment: 0.020839475416451814
posthoc_item2_qwen_intersection_ci_lo: -0.02588913609777192
posthoc_item2_qwen_intersection_ci_hi: 0.06846486882487955
posthoc_item2_qwen_intersection_p_one_sided: 0.14328567143285673
posthoc_item2_qwen_intersection_n_per_arm: 315
posthoc_item2_qwen_intersection_draws_matched: 400
posthoc_item2_qwen_intersection_retention_rate: 0.7875
posthoc_item2_qwen_intersection_treatment_level: 0.8902797538373127
posthoc_item2_qwen_intersection_control_level: 0.8694402784208609
posthoc_item2_qwen_intersection_residual_component: 0.00018460583620209803
posthoc_item2_qwen_intersection_surrogate_component: 0.020654869580249646
posthoc_item2_llama_intersection_increment: 0.032545956458999825
posthoc_item2_llama_intersection_ci_lo: -0.1760870026737792
posthoc_item2_llama_intersection_ci_hi: 0.2467744727183472
posthoc_item2_llama_intersection_p_one_sided: 0.2542745725427457
posthoc_item2_llama_intersection_n_per_arm: 67
posthoc_item2_llama_intersection_draws_matched: 400
posthoc_item2_llama_intersection_retention_rate: 0.1675
posthoc_item2_llama_intersection_treatment_level: 0.8702302528389484
posthoc_item2_llama_intersection_control_level: 0.8376842963799486
posthoc_item2_llama_intersection_residual_component: 0.0015138121963361173
posthoc_item2_llama_intersection_surrogate_component: 0.031032144262663763
posthoc_item2_qwen_intersection_holm_p_one_sided: 0.28657134286571345
posthoc_item2_llama_intersection_holm_p_one_sided: 0.28657134286571345
posthoc_item2_qwen_compliance_gap_leg2: 0.04500000000000004
posthoc_item2_qwen_compliance_gap_leg2_exceeds_0p05: 0
posthoc_item2_llama_compliance_gap_leg2: 0.04249999999999998
posthoc_item2_llama_compliance_gap_leg2_exceeds_0p05: 0
posthoc_item2_qwen_compliance_gap_leg1: -0.012499999999999956
posthoc_item2_qwen_treatment_fail_invalid_label: 35
posthoc_item2_qwen_treatment_fail_duplicate_label: 1
posthoc_item2_qwen_treatment_fail_json_decode_error: 0
posthoc_item2_qwen_treatment_fail_truncation: 0
posthoc_item2_qwen_treatment_fail_refusal: 0
posthoc_item2_qwen_control_fail_invalid_label: 48
posthoc_item2_qwen_control_fail_duplicate_label: 2
posthoc_item2_qwen_control_fail_json_decode_error: 4
posthoc_item2_qwen_control_fail_truncation: 0
posthoc_item2_qwen_control_fail_refusal: 0
posthoc_item2_llama_treatment_fail_invalid_label: 204
posthoc_item2_llama_treatment_fail_duplicate_label: 21
posthoc_item2_llama_treatment_fail_json_decode_error: 1
posthoc_item2_llama_treatment_fail_truncation: 0
posthoc_item2_llama_treatment_fail_refusal: 0
posthoc_item2_llama_control_fail_invalid_label: 224
posthoc_item2_llama_control_fail_duplicate_label: 14
posthoc_item2_llama_control_fail_json_decode_error: 5
posthoc_item2_llama_control_fail_truncation: 0
posthoc_item2_llama_control_fail_refusal: 0
posthoc_item2_conclusion_changed: 0
posthoc_item3_index_qwen_increment: -0.22727426640180814
posthoc_item3_index_qwen_ci_lo: -0.34559658297078427
posthoc_item3_index_qwen_ci_hi: -0.10818694391545236
posthoc_item3_index_qwen_p_one_sided_prereg_direction: 0.9999000099990001
posthoc_item3_index_qwen_p_two_sided: 0.00039996000399960006
posthoc_item3_index_qwen_treatment_level: 1.2629687323008925
posthoc_item3_index_qwen_control_level: 1.4902429987027006
posthoc_item3_index_qwen_ci_excludes_zero: 1
posthoc_item3_decomp_qwen_surrogate_component: 0.02782621289707654
posthoc_item3_decomp_qwen_surrogate_ci_lo: -0.011051180326545127
posthoc_item3_decomp_qwen_surrogate_ci_hi: 0.07458841743720086
posthoc_item3_decomp_qwen_surrogate_p_one_sided: 0.0402959704029597
posthoc_item3_decomp_qwen_residual_component: 0.003534351398931136
posthoc_item3_decomp_qwen_residual_ci_lo: 0.003232760482838731
posthoc_item3_decomp_qwen_residual_ci_hi: 0.003976129426203242
posthoc_item3_decomp_qwen_residual_analytic_prediction: 0.0034749433014519687
posthoc_item3_decomp_qwen_components_sum: 0.03136056429600768
posthoc_item3_disjoint_qwen_increment: 0.03735733067244173
posthoc_item3_disjoint_qwen_ci_lo: -0.19729397326237635
posthoc_item3_disjoint_qwen_ci_hi: 0.2474773210986412
posthoc_item3_disjoint_qwen_n_matchings: 200
posthoc_item3_disjoint_qwen_p_one_sided: 0.3331666833316668
posthoc_item3_disjoint_qwen_agrees_with_ustat: 1
posthoc_item3_k7_qwen_control_absolute_overlap: 0.863064750823062
posthoc_item3_k7_qwen_treatment_absolute_overlap: 0.8944253151190696
posthoc_item3_k7_qwen_ceiling_fired: 0
posthoc_item3_k7_qwen_control_minus_uniform_floor: 0.06306475082306195
posthoc_item3_k7_qwen_control_jackknife_se: 0.013284521404111233
posthoc_item3_k7_qwen_control_ci_lo: 0.8370275673191525
posthoc_item3_k7_qwen_control_ci_hi: 0.8891019343269715
posthoc_item3_k7_qwen_control_p_at_or_below_uniform_floor: 1.0310792901702115e-06
posthoc_item3_index_llama_increment: 0.04967471094588172
posthoc_item3_index_llama_ci_lo: -0.06774086048772496
posthoc_item3_index_llama_ci_hi: 0.19719466148566328
posthoc_item3_index_llama_p_one_sided_prereg_direction: 0.2263773622637736
posthoc_item3_index_llama_p_two_sided: 0.4527547245275472
posthoc_item3_index_llama_treatment_level: 1.0780170929989554
posthoc_item3_index_llama_control_level: 1.0283423820530737
posthoc_item3_index_llama_ci_excludes_zero: 0
posthoc_item3_decomp_llama_surrogate_component: 0.03269848115554286
posthoc_item3_decomp_llama_surrogate_ci_lo: -0.02942742184592399
posthoc_item3_decomp_llama_surrogate_ci_hi: 0.1269700350201948
posthoc_item3_decomp_llama_surrogate_p_one_sided: 0.030096990300969902
posthoc_item3_decomp_llama_residual_component: 0.013975840921260793
posthoc_item3_decomp_llama_residual_ci_lo: 0.01304264225082577
posthoc_item3_decomp_llama_residual_ci_hi: 0.015966407413687874
posthoc_item3_decomp_llama_residual_analytic_prediction: 0.01348626973463908
posthoc_item3_decomp_llama_components_sum: 0.04667432207680365
posthoc_item3_disjoint_llama_increment: 0.05265146410737809
posthoc_item3_disjoint_llama_ci_lo: -0.3380630391114262
posthoc_item3_disjoint_llama_ci_hi: 0.41564341731545995
posthoc_item3_disjoint_llama_n_matchings: 200
posthoc_item3_disjoint_llama_p_one_sided: 0.34296570342965704
posthoc_item3_disjoint_llama_agrees_with_ustat: 1
posthoc_item3_k7_llama_control_absolute_overlap: 0.8191613412553109
posthoc_item3_k7_llama_treatment_absolute_overlap: 0.8658356633321146
posthoc_item3_k7_llama_ceiling_fired: 0
posthoc_item3_k7_llama_control_minus_uniform_floor: 0.019161341255310882
posthoc_item3_k7_llama_control_jackknife_se: 0.020212917753282312
posthoc_item3_k7_llama_control_ci_lo: 0.7795447504364074
posthoc_item3_k7_llama_control_ci_hi: 0.8587779320742145
posthoc_item3_k7_llama_control_p_at_or_below_uniform_floor: 0.1715710838156902
posthoc_item3_k7_ceiling_threshold: 6.0
posthoc_item3_k7_uniform_floor: 0.8
posthoc_item3_index_qwen_leg1_increment: -0.21942087306447378
posthoc_item3_index_qwen_leg1_ci_lo: -0.41866007640043157
posthoc_item3_index_qwen_leg1_ci_hi: -0.008641996908990075
posthoc_item3_index_qwen_leg1_treatment_level: 1.196273291925466
posthoc_item3_index_qwen_leg1_control_level: 1.4156941649899397
posthoc_item3_index_qwen_leg1_p_two_sided: 0.063993600639936
posthoc_item3_crossfamily_cells_generated: 0
posthoc_item3_counterpart_belief_only_cells_generated: 0
posthoc_item3_conclusion_changed: 1
posthoc_item4_leg2_prereg_attempts_per_cell: 400
posthoc_item4_design_power_completions_per_cell: 240
posthoc_item4_leg2_qwen_treatment_prereg_attempts: 400
posthoc_item4_leg2_qwen_treatment_generated: 400
posthoc_item4_leg2_qwen_treatment_recorded_attempts: 400
posthoc_item4_leg2_qwen_treatment_parsed: 364
posthoc_item4_leg2_qwen_treatment_parse_loss: 36
posthoc_item4_leg2_qwen_treatment_generation_shortfall: 0
posthoc_item4_leg2_qwen_treatment_vs_power_target: 124
posthoc_item4_leg2_qwen_control_prereg_attempts: 400
posthoc_item4_leg2_qwen_control_generated: 400
posthoc_item4_leg2_qwen_control_recorded_attempts: 400
posthoc_item4_leg2_qwen_control_parsed: 346
posthoc_item4_leg2_qwen_control_parse_loss: 54
posthoc_item4_leg2_qwen_control_generation_shortfall: 0
posthoc_item4_leg2_qwen_control_vs_power_target: 106
posthoc_item4_leg2_llama_treatment_prereg_attempts: 400
posthoc_item4_leg2_llama_treatment_generated: 400
posthoc_item4_leg2_llama_treatment_recorded_attempts: 400
posthoc_item4_leg2_llama_treatment_parsed: 174
posthoc_item4_leg2_llama_treatment_parse_loss: 226
posthoc_item4_leg2_llama_treatment_generation_shortfall: 0
posthoc_item4_leg2_llama_treatment_vs_power_target: -66
posthoc_item4_leg2_llama_control_prereg_attempts: 400
posthoc_item4_leg2_llama_control_generated: 400
posthoc_item4_leg2_llama_control_recorded_attempts: 400
posthoc_item4_leg2_llama_control_parsed: 157
posthoc_item4_leg2_llama_control_parse_loss: 243
posthoc_item4_leg2_llama_control_generation_shortfall: 0
posthoc_item4_leg2_llama_control_vs_power_target: -83
posthoc_item4_leg2_generation_shortfall_total: 0
posthoc_item4_shortfall_is_parse_loss_only: 1
posthoc_item4_conclusion_changed: 0
posthoc_poscontrol_criterion_qualifying_items: 15
posthoc_poscontrol_holm_significant_items: 21
posthoc_poscontrol_min_effect_threshold: 4
posthoc_poscontrol_within_control_floor_mean: 0.035
posthoc_poscontrol_floor_ci_lo: 0.0
posthoc_poscontrol_floor_ci_hi: 1.0
posthoc_poscontrol_instrument_validation_pass: 1
posthoc_poscontrol_attempted: 400
posthoc_poscontrol_parsed: 267
posthoc_poscontrol_parse_rate: 0.6675
posthoc_poscontrol_existing_control_attempted: 400
posthoc_poscontrol_existing_control_parsed: 346
posthoc_poscontrol_existing_control_parse_rate: 0.865
posthoc_poscontrol_total_parsed_n: 613
posthoc_poscontrol_qualifying_selections: 1046
posthoc_poscontrol_total_selections: 2136
posthoc_poscontrol_criterion_selection_fraction: 0.4897003745318352
posthoc_poscontrol_chance_selection_fraction: 0.1875
posthoc_poscontrol_minimum_holm_item_p: 6.698631697015424e-11