test: falsify oral B protocol boundaries

1 files changed, 76 insertions, 71 deletions

diff --git a/experiments/analyze_bci_td_confirmation.py b/experiments/analyze_bci_td_confirmation.py
index 8697e38..689f3a7 100755
--- a/experiments/analyze_bci_td_confirmation.py
+++ b/experiments/analyze_bci_td_confirmation.py
@@ -70,6 +70,81 @@ def summarize(values):
     }
 
 
+def r2_checks(metrics, clustered, all_role_cosines, all_signs):
+    """Apply the frozen R2 gate to task-clustered summary statistics."""
+    learning_checks = {
+        "mean_intact_final_at_least_0p70":
+            metrics["intact_final"]["mean"] >= 0.70,
+        "every_task_mean_final_at_least_0p60":
+            min(clustered["intact_final"]) >= 0.60,
+        "intact_final_lower_bound_at_least_0p60":
+            metrics["intact_final"]["one_sided_95pct_lower"] >= 0.60,
+        "mean_learning_gain_at_least_0p10":
+            metrics["intact_gain"]["mean"] >= 0.10,
+        "learning_gain_lower_bound_at_least_0p05":
+            metrics["intact_gain"]["one_sided_95pct_lower"] >= 0.05,
+        "mean_fixed_gap_at_least_0p20":
+            metrics["fixed_final_gap"]["mean"] >= 0.20,
+        "fixed_gap_lower_bound_at_least_0p10":
+            metrics["fixed_final_gap"]["one_sided_95pct_lower"] >= 0.10,
+        "mean_oracle_deficit_at_most_0p10":
+            metrics["oracle_final_deficit"]["mean"] <= 0.10,
+        "oracle_deficit_upper_bound_at_most_0p20":
+            metrics["oracle_final_deficit"]["one_sided_95pct_upper"] <= 0.20,
+        "plasticity_lesion_half_margin_lower_bound_nonnegative":
+            metrics["plasticity_half_margin"]["one_sided_95pct_lower"] >= 0.0,
+        "mean_role_cosine_at_least_0p80":
+            metrics["role_cosine"]["mean"] >= 0.80,
+        "every_role_cosine_at_least_0p70": min(all_role_cosines) >= 0.70,
+    }
+    innovation_checks = {
+        "mean_residual_soma_corr_at_most_0p10":
+            metrics["residual_soma_corr"]["mean"] <= 0.10,
+        "residual_soma_corr_upper_bound_at_most_0p12":
+            metrics["residual_soma_corr"]["one_sided_95pct_upper"] <= 0.12,
+        "mean_raw_residual_corr_gap_at_least_0p20":
+            metrics["raw_residual_corr_gap"]["mean"] >= 0.20,
+        "raw_residual_corr_gap_lower_bound_at_least_0p15":
+            metrics["raw_residual_corr_gap"]["one_sided_95pct_lower"] >= 0.15,
+        "mean_surrounding_event_accuracy_at_least_0p55":
+            metrics["surrounding_event_accuracy"]["mean"] >= 0.55,
+        "surrounding_event_accuracy_lower_bound_at_least_0p52":
+            metrics["surrounding_event_accuracy"]["one_sided_95pct_lower"] >= 0.52,
+        "mean_decoder_distance_corr_at_least_0p10":
+            metrics["decoder_distance_corr"]["mean"] >= 0.10,
+        "decoder_distance_corr_lower_bound_at_least_0p02":
+            metrics["decoder_distance_corr"]["one_sided_95pct_lower"] >= 0.02,
+    }
+    vectorization_checks = {
+        "mean_residual_outcome_accuracy_at_least_0p57":
+            metrics["residual_outcome_accuracy"]["mean"] >= 0.57,
+        "residual_outcome_accuracy_lower_bound_at_least_0p53":
+            metrics["residual_outcome_accuracy"]["one_sided_95pct_lower"] >= 0.53,
+        "mean_residual_soma_outcome_gap_at_least_0p03":
+            metrics["residual_soma_outcome_gap"]["mean"] >= 0.03,
+        "residual_soma_outcome_gap_lower_bound_nonnegative":
+            metrics["residual_soma_outcome_gap"]["one_sided_95pct_lower"] >= 0.0,
+        "positive_sign_inversion_in_at_least_25_of_30":
+            sum(value > 0 for value in all_signs) >= 25,
+        "positive_sign_inversion_in_every_task_cluster":
+            min(clustered["sign_inversion"]) > 0.0,
+        "mean_velocity_advantage_at_least_0p05":
+            metrics["velocity_advantage"]["mean"] >= 0.05,
+        "velocity_advantage_lower_bound_nonnegative":
+            metrics["velocity_advantage"]["one_sided_95pct_lower"] >= 0.0,
+        "mean_longitudinal_prediction_at_least_0p30":
+            metrics["longitudinal_prediction"]["mean"] >= 0.30,
+        "longitudinal_prediction_lower_bound_at_least_0p10":
+            metrics["longitudinal_prediction"]["one_sided_95pct_lower"] >= 0.10,
+    }
+    return {
+        "all_records_finite_paired_and_cost_audited": True,
+        "learning_and_plasticity": learning_checks,
+        "innovation_identification_and_network_prediction": innovation_checks,
+        "outcome_and_causal_role_vectorization": vectorization_checks,
+    }
+
+
 def validate(row, path, eta, digests):
     require(row.get("schema_version") == 1, f"{path}: schema")
     args = row.get("args", {})
@@ -260,77 +335,7 @@ def main():
                         for row in records.values()]
     all_signs = [getters["sign_inversion"](row)
                  for row in records.values()]
-    learning_checks = {
-        "mean_intact_final_at_least_0p70":
-            metrics["intact_final"]["mean"] >= 0.70,
-        "every_task_mean_final_at_least_0p60":
-            min(clustered["intact_final"]) >= 0.60,
-        "intact_final_lower_bound_at_least_0p60":
-            metrics["intact_final"]["one_sided_95pct_lower"] >= 0.60,
-        "mean_learning_gain_at_least_0p10":
-            metrics["intact_gain"]["mean"] >= 0.10,
-        "learning_gain_lower_bound_at_least_0p05":
-            metrics["intact_gain"]["one_sided_95pct_lower"] >= 0.05,
-        "mean_fixed_gap_at_least_0p20":
-            metrics["fixed_final_gap"]["mean"] >= 0.20,
-        "fixed_gap_lower_bound_at_least_0p10":
-            metrics["fixed_final_gap"]["one_sided_95pct_lower"] >= 0.10,
-        "mean_oracle_deficit_at_most_0p10":
-            metrics["oracle_final_deficit"]["mean"] <= 0.10,
-        "oracle_deficit_upper_bound_at_most_0p20":
-            metrics["oracle_final_deficit"]["one_sided_95pct_upper"] <= 0.20,
-        "plasticity_lesion_half_margin_lower_bound_nonnegative":
-            metrics["plasticity_half_margin"]["one_sided_95pct_lower"] >= 0.0,
-        "mean_role_cosine_at_least_0p80":
-            metrics["role_cosine"]["mean"] >= 0.80,
-        "every_role_cosine_at_least_0p70": min(all_role_cosines) >= 0.70,
-    }
-    innovation_checks = {
-        "mean_residual_soma_corr_at_most_0p10":
-            metrics["residual_soma_corr"]["mean"] <= 0.10,
-        "residual_soma_corr_upper_bound_at_most_0p12":
-            metrics["residual_soma_corr"]["one_sided_95pct_upper"] <= 0.12,
-        "mean_raw_residual_corr_gap_at_least_0p20":
-            metrics["raw_residual_corr_gap"]["mean"] >= 0.20,
-        "raw_residual_corr_gap_lower_bound_at_least_0p15":
-            metrics["raw_residual_corr_gap"]["one_sided_95pct_lower"] >= 0.15,
-        "mean_surrounding_event_accuracy_at_least_0p55":
-            metrics["surrounding_event_accuracy"]["mean"] >= 0.55,
-        "surrounding_event_accuracy_lower_bound_at_least_0p52":
-            metrics["surrounding_event_accuracy"]["one_sided_95pct_lower"] >= 0.52,
-        "mean_decoder_distance_corr_at_least_0p10":
-            metrics["decoder_distance_corr"]["mean"] >= 0.10,
-        "decoder_distance_corr_lower_bound_at_least_0p02":
-            metrics["decoder_distance_corr"]["one_sided_95pct_lower"] >= 0.02,
-    }
-    vectorization_checks = {
-        "mean_residual_outcome_accuracy_at_least_0p57":
-            metrics["residual_outcome_accuracy"]["mean"] >= 0.57,
-        "residual_outcome_accuracy_lower_bound_at_least_0p53":
-            metrics["residual_outcome_accuracy"]["one_sided_95pct_lower"] >= 0.53,
-        "mean_residual_soma_outcome_gap_at_least_0p03":
-            metrics["residual_soma_outcome_gap"]["mean"] >= 0.03,
-        "residual_soma_outcome_gap_lower_bound_nonnegative":
-            metrics["residual_soma_outcome_gap"]["one_sided_95pct_lower"] >= 0.0,
-        "positive_sign_inversion_in_at_least_25_of_30":
-            sum(value > 0 for value in all_signs) >= 25,
-        "positive_sign_inversion_in_every_task_cluster":
-            min(clustered["sign_inversion"]) > 0.0,
-        "mean_velocity_advantage_at_least_0p05":
-            metrics["velocity_advantage"]["mean"] >= 0.05,
-        "velocity_advantage_lower_bound_nonnegative":
-            metrics["velocity_advantage"]["one_sided_95pct_lower"] >= 0.0,
-        "mean_longitudinal_prediction_at_least_0p30":
-            metrics["longitudinal_prediction"]["mean"] >= 0.30,
-        "longitudinal_prediction_lower_bound_at_least_0p10":
-            metrics["longitudinal_prediction"]["one_sided_95pct_lower"] >= 0.10,
-    }
-    checks = {
-        "all_records_finite_paired_and_cost_audited": True,
-        "learning_and_plasticity": learning_checks,
-        "innovation_identification_and_network_prediction": innovation_checks,
-        "outcome_and_causal_role_vectorization": vectorization_checks,
-    }
+    checks = r2_checks(metrics, clustered, all_role_cosines, all_signs)
     passed = all(
         value
         for category, values in checks.items()