Refactor load_dataset to include split parameter in populate.py

src/populate.py

@@ -13,7 +13,7 @@ def get_leaderboard_df(results_repo):
     subsets = get_dataset_config_names(results_repo)
     subset_dfs = {}
     for subset in subsets:
-        subset_data = load_dataset(results_repo, subset)
+        subset_data = load_dataset(results_repo, subset, split="test")
         subset_df = subset_data.to_pandas()
         subset_df = subset_df.sort_values(by="Total", ascending=False)
         subset_df = subset_df.round(2)  # Round all numeric columns to two decimal places