AbstractIntegratedModule 1.0.5__tar.gz → 1.0.6__tar.gz

{abstractintegratedmodule-1.0.5 → abstractintegratedmodule-1.0.6}/AbstractIntegratedModule.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: AbstractIntegratedModule
-Version: 1.0.5
+Version: 1.0.6
 Summary: Integrated Pipeline with Specialized Non-LLM AI Agent Framework for ARM64 architecture
 Author: Micro-Novelty
 Author-email: Micro-Novelty <hernikpuspita5@gmail.com>

{abstractintegratedmodule-1.0.5 → abstractintegratedmodule-1.0.6}/AbstractIntegratedModule.py

@@ -1868,7 +1868,7 @@ class MLP:
                                standard_low_error_mean + standard_pred_quality)
 
         if np.isnan(performance_score) or np.isinf(performance_score):
-            performance_score = 0.5
+            performance_score = 0.15
 
         return performance_score
 
@@ -2296,7 +2296,7 @@ class LSTMNetwork:
 
         diff = preds - targets
         loss = (1.0 - AMR) * np.mean(diff ** 2)
-        dloss = diff / (min_T * min_F)   # FIX 3 — normalize by full element count
+        dloss = diff / (min_T * min_F)   # normalized by full element count
         return loss, dloss
 
     # backward method for the network to calculate proper weights with cell backward
@@ -5123,7 +5123,7 @@ class ModelStorage:
             repaired = {}
             for key, value in data.items():
 
-                # dynamic corruption check instead of hardcoded 133
+                # dynamic corruption check 
                 if isinstance(value, list):
                     arr = np.asarray(value)
                     if arr.ndim > 2:
@@ -5137,7 +5137,7 @@ class ModelStorage:
                             f'{arr.shape}, expected {num_classes} — removing')
                         continue
 
-                # None values — skip silently
+                # None values — skipped silently
                 if value is None:
                     continue
 
@@ -17007,8 +17007,15 @@ class PipelinePredictionManager:
                     trans_confidence = results[0].get('trans_confidence', 1e-8)
                     confidence = (confidence + trans_confidence / 2) + 1e-5
                     print(f'[=] Calibrating confidence around: {confidence:.1%} Due to disagreement between Transformer and MLP.')
+                    
+                if isinstance(chosen_label, str) and chosen_label.startswith("unknown") or float(confidence) < self.pipeline.confidence_threshold:
+                    if chosen_label is None or chosen_label.startswith('unknown'):
+                        chosen_label = 'Unknown'
+                        confidence = 1.0 - confidence  #Invert confidence for unknown class
+                        print(f"\n[⚠️] Final prediction is {chosen_label} with uncertain confidence: {confidence:.1%}. Consider more consistent data for the model to learn from.")
+                    else:
+                        print(f"\n[🎯] Predicted label: {chosen_label} || With Certain Confidence: {confidence:.1%}")
 
-                print(f"\n[🎯] Predicted label: {chosen_label} || With Certain Confidence: {confidence:.1%}")
                 payload = {
                     'X_samples': X,
                     'input_ids': input_ids