{"baseline":{"mean_score":0.53},"comparison":{"kind":"exact_match_delta_pp","minimum":-2.0,"value":1.7500000000000002},"comparison_id":"comparison-50b66963c275e4c1fffa0dde426e1d8c","format":"invarlock/comparison-report-v3","metric":"exact_match","paired_binary":{"baseline_fail_subject_pass":17,"baseline_pass_subject_fail":10,"both_fail":171,"both_pass":202,"discordant_pairs":27,"effect_size_confidence_interval":{"confidence_level":0.95,"lower_pp":-0.8298925545805376,"method":"newcombe_hybrid_score_paired_v2","upper_pp":4.3217785714311985},"effect_size_pp":1.7500000000000002,"mcnemar_exact_two_sided_p_value":0.24778856337070465},"policy_digest":"sha256:48e929519390c41e91c5e907e7e3f3d6d0b26e5ac4345136c4f6b85244b191d9","record_count":400,"sample_qualification":{"interval_width":{"maximum":10.0,"observed":5.1516711260117365,"passed":true,"unit":"percentage_points"},"passed":true,"record_count":{"minimum":400,"observed":400,"passed":true}},"side_accuracy":{"baseline":{"observed":0.53,"passed":true},"minimum":0.2,"passed":true,"subject":{"observed":0.5475,"passed":true}},"subject":{"mean_score":0.5475},"uncertainty":{"interval_mass":0.95,"lower":-0.8298925545805376,"method":"newcombe_hybrid_score_paired_v2","scope":"paired_binary_outcomes","upper":4.3217785714311985},"verdict":"pass"}
