{"baseline":{"mean_score":0.63},"comparison":{"kind":"exact_match_delta_pp","minimum":-2.0,"value":1.5},"comparison_id":"comparison-f22a4c52f0172fb7c17e33a37f46a75d","format":"invarlock/comparison-report-v3","metric":"exact_match","paired_binary":{"baseline_fail_subject_pass":13,"baseline_pass_subject_fail":7,"both_fail":135,"both_pass":245,"discordant_pairs":20,"effect_size_confidence_interval":{"confidence_level":0.95,"lower_pp":-0.7440266824329054,"method":"newcombe_hybrid_score_paired_v2","upper_pp":3.7463947748609603},"effect_size_pp":1.5,"mcnemar_exact_two_sided_p_value":0.26317596435546875},"policy_digest":"sha256:48e929519390c41e91c5e907e7e3f3d6d0b26e5ac4345136c4f6b85244b191d9","record_count":400,"sample_qualification":{"interval_width":{"maximum":10.0,"observed":4.490421457293865,"passed":true,"unit":"percentage_points"},"passed":true,"record_count":{"minimum":400,"observed":400,"passed":true}},"side_accuracy":{"baseline":{"observed":0.63,"passed":true},"minimum":0.2,"passed":true,"subject":{"observed":0.645,"passed":true}},"subject":{"mean_score":0.645},"uncertainty":{"interval_mass":0.95,"lower":-0.7440266824329054,"method":"newcombe_hybrid_score_paired_v2","scope":"paired_binary_outcomes","upper":3.7463947748609603},"verdict":"pass"}
