diff --git a/services/ml_training_data/src/ml_training_data/sap_parity_probe.py b/services/ml_training_data/src/ml_training_data/sap_parity_probe.py
index 6a331f82..35e6dcfa 100644
--- a/services/ml_training_data/src/ml_training_data/sap_parity_probe.py
+++ b/services/ml_training_data/src/ml_training_data/sap_parity_probe.py
@@ -37,7 +37,11 @@ _ZIP_KEYS = ("certificates-2025.json.zip", "certificates-2026.json.zip")
 
 def _sample_certs(n: int, seed: int) -> dict[str, int]:
     df = pd.read_parquet(_PARQUET, columns=["certificate_number", "sap_score"])
-    df = df[df["sap_score"].between(20, 95)]
+    # Wide range so the sample includes full-SAP new-builds (sap_score 90+)
+    # and the deepest-tail heritage/anomaly certs (sap_score ≤ 20). Earlier
+    # `between(20, 95)` excluded the populations where the calculator's
+    # biggest spec gaps tend to live.
+    df = df[df["sap_score"].between(5, 99)]
     s = df.sample(n, random_state=seed)
     return dict(zip(s["certificate_number"], s["sap_score"].astype(int)))