-def create_score_dictionary_from_metrics(weights: list[float], *metrics: list[float]) -> dict[int, int]:
-    """Combine multiple metrics into a single weighted score dictionary.
-
-    Each metric is a list of values (smaller = better).
-    The total score for each index is the weighted sum of its values
-    across all metrics:
-
-        score[index] = Σ (value * weight)
-
-    Args:
-        weights: A list of weights, one per metric. Larger weight = more influence.
-        *metrics: Lists of values (one list per metric, aligned by index).
-
-    Returns:
-        A dictionary mapping each index to its combined weighted score.
-
-    """
+def create_score_dictionary_from_metrics(weights: list[float], *metrics: list[float]) -> dict[int, float]:
+    """Combine multiple metrics into a single weighted score dictionary."""
     if len(weights) != len(metrics):
         raise ValueError("Number of weights must match number of metrics")
+    lengths = {len(m) for m in metrics}
+    if len(lengths) > 1:
+        raise ValueError("All metric lists must have the same length")
 
     combined: dict[int, float] = {}
-
     for weight, metric in zip(weights, metrics):
         for idx, value in enumerate(metric):
-            combined[idx] = combined.get(idx, 0) + value * weight
-
+            combined[idx] = combined.get(idx, 0.0) + value * weight
     return combined

 top_n_candidates = int((TOP_N_REFINEMENTS * len(runtimes_list)) + 0.5)
-top_indecies = sorted(score_dict, key=score_dict.get)[:top_n_candidates]
+if len(runtimes_list) > 0:
+    top_n_candidates = max(1, min(top_n_candidates, len(runtimes_list)))
+top_indices = sorted(score_dict, key=score_dict.get)[:top_n_candidates]
 
-for idx in top_indecies:
+for idx in top_indices:
     data = self.all_refinements_data[idx]
     future_refinements.append(self.refine_optimizations([data]))

-runtime_norm = normalize(runtimes_list)
-diffs_norm = normalize(diff_lens_list)
-# the lower the better
+if not runtimes_list or not diff_lens_list:
+    self.refinement_done = True
+    return self.get_next_candidate()
+
+runtime_norm = normalize(runtimes_list)  # lower is better
+diffs_norm = normalize(diff_lens_list)   # lower is better
 score_dict = create_score_dictionary_from_metrics(weights, runtime_norm, diffs_norm)