{"blinding_authentication":"NOT_ESTABLISHED","classification_threshold":0.5,"cohorts":{"ALL":{"baseline":{"accuracy":0.6666666666666666,"accuracy_wilson_95":[0.2999933151383921,0.9032285888942196],"brier_hoeffding_95":[0.0,0.774442622077489],"brier_score":0.22,"calibration_deciles":[{"absolute_gap":null,"count":0,"lower_inclusive":0.0,"mean_probability":null,"observed_frequency":null,"upper":0.1,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.1,"mean_probability":null,"observed_frequency":null,"upper":0.2,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.2,"mean_probability":null,"observed_frequency":null,"upper":0.3,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.3,"mean_probability":null,"observed_frequency":null,"upper":0.4,"upper_inclusive":false},{"absolute_gap":0.4,"count":1,"lower_inclusive":0.4,"mean_probability":0.4,"observed_frequency":0.0,"upper":0.5,"upper_inclusive":false},{"absolute_gap":0.0,"count":4,"lower_inclusive":0.5,"mean_probability":0.5,"observed_frequency":0.5,"upper":0.6,"upper_inclusive":false},{"absolute_gap":0.4,"count":1,"lower_inclusive":0.6,"mean_probability":0.6,"observed_frequency":1.0,"upper":0.7,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.7,"mean_probability":null,"observed_frequency":null,"upper":0.8,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.8,"mean_probability":null,"observed_frequency":null,"upper":0.9,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.9,"mean_probability":null,"observed_frequency":null,"upper":1.0,"upper_inclusive":true}],"confusion":{"false_negative":0,"false_positive":2,"true_negative":1,"true_positive":3},"count":6,"expected_calibration_error":0.13333333333333333,"false_negative_rate":0.0,"false_negative_rate_wilson_95":[0.0,0.5614970317550454],"false_positive_rate":0.6666666666666666,"false_positive_rate_wilson_95":[0.20765960080204782,0.9385080552796038],"log_loss":0.6323733282952938,"log_loss_probability_floor":1e-15,"positive_predictive_value":0.6,"uncertainty_scope":"Conditional bounds assume independent sampling units; supplied group IDs do not prove independence."},"brier_skill_score":0.25757575757575757,"count":6,"proposed":{"accuracy":0.6666666666666666,"accuracy_wilson_95":[0.2999933151383921,0.9032285888942196],"brier_hoeffding_95":[0.0,0.7177759554108224],"brier_score":0.16333333333333333,"calibration_deciles":[{"absolute_gap":null,"count":0,"lower_inclusive":0.0,"mean_probability":null,"observed_frequency":null,"upper":0.1,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.1,"mean_probability":null,"observed_frequency":null,"upper":0.2,"upper_inclusive":false},{"absolute_gap":0.2,"count":1,"lower_inclusive":0.2,"mean_probability":0.2,"observed_frequency":0.0,"upper":0.3,"upper_inclusive":false},{"absolute_gap":0.3,"count":1,"lower_inclusive":0.3,"mean_probability":0.3,"observed_frequency":0.0,"upper":0.4,"upper_inclusive":false},{"absolute_gap":0.6,"count":1,"lower_inclusive":0.4,"mean_probability":0.4,"observed_frequency":1.0,"upper":0.5,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.5,"mean_probability":null,"observed_frequency":null,"upper":0.6,"upper_inclusive":false},{"absolute_gap":0.6,"count":1,"lower_inclusive":0.6,"mean_probability":0.6,"observed_frequency":0.0,"upper":0.7,"upper_inclusive":false},{"absolute_gap":0.30000000000000004,"count":1,"lower_inclusive":0.7,"mean_probability":0.7,"observed_frequency":1.0,"upper":0.8,"upper_inclusive":false},{"absolute_gap":0.19999999999999996,"count":1,"lower_inclusive":0.8,"mean_probability":0.8,"observed_frequency":1.0,"upper":0.9,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.9,"mean_probability":null,"observed_frequency":null,"upper":1.0,"upper_inclusive":true}],"confusion":{"false_negative":1,"false_positive":1,"true_negative":2,"true_positive":2},"count":6,"expected_calibration_error":0.36666666666666664,"false_negative_rate":0.3333333333333333,"false_negative_rate_wilson_95":[0.06149194472039632,0.7923403991979523],"false_positive_rate":0.3333333333333333,"false_positive_rate_wilson_95":[0.06149194472039632,0.7923403991979523],"log_loss":0.49870307570903244,"log_loss_probability_floor":1e-15,"positive_predictive_value":0.6666666666666666,"uncertainty_scope":"Conditional bounds assume independent sampling units; supplied group IDs do not prove independence."},"record_ids":["fixture-01","fixture-02","fixture-03","fixture-04","fixture-05","fixture-06"],"skill_status":"DESCRIPTIVE_SAMPLE_COMPARISON"},"DEVELOPMENT":{"baseline":{"accuracy":0.5,"accuracy_wilson_95":[0.09453120573423074,0.9054687942657693],"brier_hoeffding_95":[0.0,1.0],"brier_score":0.25,"calibration_deciles":[{"absolute_gap":null,"count":0,"lower_inclusive":0.0,"mean_probability":null,"observed_frequency":null,"upper":0.1,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.1,"mean_probability":null,"observed_frequency":null,"upper":0.2,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.2,"mean_probability":null,"observed_frequency":null,"upper":0.3,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.3,"mean_probability":null,"observed_frequency":null,"upper":0.4,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.4,"mean_probability":null,"observed_frequency":null,"upper":0.5,"upper_inclusive":false},{"absolute_gap":0.0,"count":2,"lower_inclusive":0.5,"mean_probability":0.5,"observed_frequency":0.5,"upper":0.6,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.6,"mean_probability":null,"observed_frequency":null,"upper":0.7,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.7,"mean_probability":null,"observed_frequency":null,"upper":0.8,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.8,"mean_probability":null,"observed_frequency":null,"upper":0.9,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.9,"mean_probability":null,"observed_frequency":null,"upper":1.0,"upper_inclusive":true}],"confusion":{"false_negative":0,"false_positive":1,"true_negative":0,"true_positive":1},"count":2,"expected_calibration_error":0.0,"false_negative_rate":0.0,"false_negative_rate_wilson_95":[0.0,0.7934506856227626],"false_positive_rate":1.0,"false_positive_rate_wilson_95":[0.20654931437723745,1.0],"log_loss":0.6931471805599453,"log_loss_probability_floor":1e-15,"positive_predictive_value":0.5,"uncertainty_scope":"Conditional bounds assume independent sampling units; supplied group IDs do not prove independence."},"brier_skill_score":0.8400000000000001,"count":2,"proposed":{"accuracy":1.0,"accuracy_wilson_95":[0.3423802275066532,1.0],"brier_hoeffding_95":[0.0,1.0],"brier_score":0.039999999999999994,"calibration_deciles":[{"absolute_gap":null,"count":0,"lower_inclusive":0.0,"mean_probability":null,"observed_frequency":null,"upper":0.1,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.1,"mean_probability":null,"observed_frequency":null,"upper":0.2,"upper_inclusive":false},{"absolute_gap":0.2,"count":1,"lower_inclusive":0.2,"mean_probability":0.2,"observed_frequency":0.0,"upper":0.3,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.3,"mean_probability":null,"observed_frequency":null,"upper":0.4,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.4,"mean_probability":null,"observed_frequency":null,"upper":0.5,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.5,"mean_probability":null,"observed_frequency":null,"upper":0.6,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.6,"mean_probability":null,"observed_frequency":null,"upper":0.7,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.7,"mean_probability":null,"observed_frequency":null,"upper":0.8,"upper_inclusive":false},{"absolute_gap":0.19999999999999996,"count":1,"lower_inclusive":0.8,"mean_probability":0.8,"observed_frequency":1.0,"upper":0.9,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.9,"mean_probability":null,"observed_frequency":null,"upper":1.0,"upper_inclusive":true}],"confusion":{"false_negative":0,"false_positive":0,"true_negative":1,"true_positive":1},"count":2,"expected_calibration_error":0.19999999999999998,"false_negative_rate":0.0,"false_negative_rate_wilson_95":[0.0,0.7934506856227626],"false_positive_rate":0.0,"false_positive_rate_wilson_95":[0.0,0.7934506856227626],"log_loss":0.2231435513142097,"log_loss_probability_floor":1e-15,"positive_predictive_value":1.0,"uncertainty_scope":"Conditional bounds assume independent sampling units; supplied group IDs do not prove independence."},"record_ids":["fixture-01","fixture-02"],"skill_status":"DESCRIPTIVE_SAMPLE_COMPARISON"},"HOLDOUT":{"baseline":{"accuracy":0.75,"accuracy_wilson_95":[0.300641842582402,0.9544127391902995],"brier_hoeffding_95":[0.0,0.8840507578703098],"brier_score":0.20500000000000002,"calibration_deciles":[{"absolute_gap":null,"count":0,"lower_inclusive":0.0,"mean_probability":null,"observed_frequency":null,"upper":0.1,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.1,"mean_probability":null,"observed_frequency":null,"upper":0.2,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.2,"mean_probability":null,"observed_frequency":null,"upper":0.3,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.3,"mean_probability":null,"observed_frequency":null,"upper":0.4,"upper_inclusive":false},{"absolute_gap":0.4,"count":1,"lower_inclusive":0.4,"mean_probability":0.4,"observed_frequency":0.0,"upper":0.5,"upper_inclusive":false},{"absolute_gap":0.0,"count":2,"lower_inclusive":0.5,"mean_probability":0.5,"observed_frequency":0.5,"upper":0.6,"upper_inclusive":false},{"absolute_gap":0.4,"count":1,"lower_inclusive":0.6,"mean_probability":0.6,"observed_frequency":1.0,"upper":0.7,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.7,"mean_probability":null,"observed_frequency":null,"upper":0.8,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.8,"mean_probability":null,"observed_frequency":null,"upper":0.9,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.9,"mean_probability":null,"observed_frequency":null,"upper":1.0,"upper_inclusive":true}],"confusion":{"false_negative":0,"false_positive":1,"true_negative":1,"true_positive":2},"count":4,"expected_calibration_error":0.2,"false_negative_rate":0.0,"false_negative_rate_wilson_95":[0.0,0.6576197724933468],"false_positive_rate":0.5,"false_positive_rate_wilson_95":[0.09453120573423074,0.9054687942657693],"log_loss":0.601986402162968,"log_loss_probability_floor":1e-15,"positive_predictive_value":0.6666666666666666,"uncertainty_scope":"Conditional bounds assume independent sampling units; supplied group IDs do not prove independence."},"brier_skill_score":-0.09756097560975596,"count":4,"proposed":{"accuracy":0.5,"accuracy_wilson_95":[0.15003898915214958,0.8499610108478504],"brier_hoeffding_95":[0.0,0.9040507578703098],"brier_score":0.225,"calibration_deciles":[{"absolute_gap":null,"count":0,"lower_inclusive":0.0,"mean_probability":null,"observed_frequency":null,"upper":0.1,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.1,"mean_probability":null,"observed_frequency":null,"upper":0.2,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.2,"mean_probability":null,"observed_frequency":null,"upper":0.3,"upper_inclusive":false},{"absolute_gap":0.3,"count":1,"lower_inclusive":0.3,"mean_probability":0.3,"observed_frequency":0.0,"upper":0.4,"upper_inclusive":false},{"absolute_gap":0.6,"count":1,"lower_inclusive":0.4,"mean_probability":0.4,"observed_frequency":1.0,"upper":0.5,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.5,"mean_probability":null,"observed_frequency":null,"upper":0.6,"upper_inclusive":false},{"absolute_gap":0.6,"count":1,"lower_inclusive":0.6,"mean_probability":0.6,"observed_frequency":0.0,"upper":0.7,"upper_inclusive":false},{"absolute_gap":0.30000000000000004,"count":1,"lower_inclusive":0.7,"mean_probability":0.7,"observed_frequency":1.0,"upper":0.8,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.8,"mean_probability":null,"observed_frequency":null,"upper":0.9,"upper_inclusive":false},{"absolute_gap":null,"count":0,"lower_inclusive":0.9,"mean_probability":null,"observed_frequency":null,"upper":1.0,"upper_inclusive":true}],"confusion":{"false_negative":1,"false_positive":1,"true_negative":1,"true_positive":1},"count":4,"expected_calibration_error":0.45,"false_negative_rate":0.5,"false_negative_rate_wilson_95":[0.09453120573423074,0.9054687942657693],"false_positive_rate":0.5,"false_positive_rate_wilson_95":[0.09453120573423074,0.9054687942657693],"log_loss":0.6364828379064438,"log_loss_probability_floor":1e-15,"positive_predictive_value":0.5,"uncertainty_scope":"Conditional bounds assume independent sampling units; supplied group IDs do not prove independence."},"record_ids":["fixture-03","fixture-04","fixture-05","fixture-06"],"skill_status":"DESCRIPTIVE_SAMPLE_COMPARISON"}},"commitment_scope":"Retain these commitments through an independently trusted channel before label release; self-contained matching hashes alone do not prove chronology or blinding.","dataset_id":"synthetic-schema-exercise-v1","field_accuracy":"NOT_ESTABLISHED","ground_truth_authentication":"NOT_ESTABLISHED","holdout_evaluation_status":"DESCRIPTIVE_METRICS_COMPUTED","independent_human_review":"NOT_PERFORMED","label_commitment_blake2b_256":"76ea0838eaf449993799907e02af095638671f31374b4d05b682fd021e39248f","limitations":["Commitments and consistent supplied timestamps do not independently authenticate collection, chronology, labels or actual blinding.","Custodian and label provenance remain supplied assertions until an independent reviewer corroborates them.","Metrics describe the supplied records; neither synthetic nor unauthenticated observations establish field accuracy or a legal conclusion.","Confidence bounds assume independent sampling units; distinct supplied group IDs cannot establish actual statistical independence.","ECE and Brier skill are descriptive sample metrics, not guarantees for new matters or individual clients."],"prediction_commitment_blake2b_256":"6911388869871d78d34e2efd2fddb489bcf378296d0bb2dfd9d0af9875e3b1e0","provenance":{"custodian":"Synthetic fixture generator","description":"Six fabricated numerical cases illustrate the schema and scoring arithmetic, not product accuracy.","label_source":"Explicit producer-authored example labels; no real matters","status":"SUPPLIED_UNAUTHENTICATED"},"schema":"subrosa-validation-report-v1","source_kind":"SYNTHETIC","status":"SYNTHETIC_ONLY","supplied_timestamp_check":"CONSISTENT","task":"PROSPECTIVE_FORECAST"}