update

webapp/services/report_builder.py

@@ -37,6 +37,9 @@ GROUPING_FIELDS = ("difficulty", "question_type", "language")
 # How many lowest-scoring samples to surface for manual review.
 LOWEST_SAMPLE_COUNT = 10
 
+# Metrics whose lower raw value means stronger performance.
+LOWER_IS_BETTER_METRICS = {"noise_sensitivity"}
+
 
 def _round_or_none(value: float | None) -> float | None:
     """Round a float to four places, mapping NaN/None to None for clean JSON."""
@@ -105,7 +108,7 @@ def _groupings(frame: pd.DataFrame, metrics: list[str]) -> dict[str, list[GroupS
 def _sample_mean(row: pd.Series, metrics: list[str]) -> float | None:
     """Average a single sample's available metric scores for ranking."""
     values = [
-        float(row[metric])
+        (1.0 - float(row[metric])) if metric in LOWER_IS_BETTER_METRICS else float(row[metric])
         for metric in metrics
         if metric in row and pd.notna(row[metric])
     ]