{"baseline":{"mean_score":0.4475},"comparison":{"kind":"exact_match_delta_pp","minimum":-2.0,"value":0.5},"comparison_id":"comparison-4472c601a80f319859c4bf0c505c399c","format":"invarlock/comparison-report-v3","metric":"exact_match","paired_binary":{"baseline_fail_subject_pass":6,"baseline_pass_subject_fail":4,"both_fail":215,"both_pass":175,"discordant_pairs":10,"effect_size_confidence_interval":{"confidence_level":0.95,"lower_pp":-1.119943249438997,"method":"newcombe_hybrid_score_paired_v2","upper_pp":2.118915687037841},"effect_size_pp":0.5,"mcnemar_exact_two_sided_p_value":0.75390625},"policy_digest":"sha256:48e929519390c41e91c5e907e7e3f3d6d0b26e5ac4345136c4f6b85244b191d9","record_count":400,"sample_qualification":{"interval_width":{"maximum":10.0,"observed":3.238858936476838,"passed":true,"unit":"percentage_points"},"passed":true,"record_count":{"minimum":400,"observed":400,"passed":true}},"side_accuracy":{"baseline":{"observed":0.4475,"passed":true},"minimum":0.2,"passed":true,"subject":{"observed":0.4525,"passed":true}},"subject":{"mean_score":0.4525},"uncertainty":{"interval_mass":0.95,"lower":-1.119943249438997,"method":"newcombe_hybrid_score_paired_v2","scope":"paired_binary_outcomes","upper":2.118915687037841},"verdict":"pass"}
