update

app.py

@@ -327,14 +327,20 @@ def completed(session_id):
             logger.info(f"ground_truth_key: {ground_truth_key}")
 
             if ground_truth_key in ground_truth:
-                model_prediction = ground_truth[ground_truth_key]['answer'].upper()
+                # TODO: Important Note ->
+                # Using model prediction as we are doing forward simulation
+                # Please use ground_truth[ground_truth_key]['answer'].upper() if running verification task
+                model_prediction = ground_truth[ground_truth_key]['prediction'].upper()
                 if user_prediction.upper() == model_prediction:
-                    correct_predictions += 1
-
-                if user_prediction.upper() == "TRUE":
+                    # correct_predictions += 1
                     true_predictions += 1
-                elif user_prediction.upper() == "FALSE":
+                else:
                     false_predictions += 1
+
+                # if user_prediction.upper() == "TRUE":
+                #     true_predictions += 1
+                # elif user_prediction.upper() == "FALSE":
+                #     false_predictions += 1
             else:
                 logger.warning(f"Missing key in ground truth: {ground_truth_key}")