feat: Add training data transparency flags with HF Hub verification

src/models/service.py

@@ -661,14 +661,39 @@ def _create_model_card_section(self, metadata: Dict[str, Any]) -> Dict[str, Any]
                 props.append({"name": "genai:aibom:modelcard:quantizationFileType", "value": str(q_dict["file_type"])})
             taxonomy_mapped_keys.append("quantization")
 
+        # Training Data Completeness Check
+        has_training_data = self._verify_datasets_available(metadata)
+        props.append({"name": "genai:aibom:trainingDataAvailable", "value": "true" if has_training_data else "false"})
+
+        # Add status note about dataset verification
+        if has_training_data:
+            props.append({
+                "name": "genai:aibom:trainingDataStatus",
+                "value": "Training datasets verified: Dataset(s) exist and are accessible on Hugging Face Hub."
+            })
+        else:
+            # Dataset referenced but not found/verified
+            if "datasets" in metadata and metadata.get("datasets"):
+                props.append({
+                    "name": "genai:aibom:trainingDataWarning", 
+                    "value": "Training datasets were referenced but could not be verified on Hugging Face Hub. Dataset may not exist, be disabled, or be inaccessible."
+                })
+            else:
+                # No dataset info at all
+                props.append({
+                    "name": "genai:aibom:trainingDataWarning", 
+                    "value": "Training data information is missing or not documented. This limits transparency and auditability of the model."
+                })
+
         # Basic Fields we've already mapped to structured homes
         mapped_fields = [
             "primaryPurpose", "typeOfModel", "suppliedBy", "intendedUse",
             "technicalLimitations", "ethicalConsiderations", "datasets", "eval_results",
             "pipeline_tag", "name", "author", "license", "description",
             "commit", "bomFormat", "specVersion", "version", "licenses",
             "external_references", "tags", "library_name", "paper", "downloadLocation",
-            "gguf_filename", "gguf_license", "model_type", "architectures"
+            "gguf_filename", "gguf_license", "model_type", "architectures",
+            "trainingDataAvailable", "trainingDataWarning"
         ] + taxonomy_mapped_keys
 
         for k, v in metadata.items():
@@ -719,3 +744,28 @@ def _infer_io_formats(self, task: str) -> tuple:
             return (["csv", "json"], ["string", "number"])
 
         return ([], [])
+
+    def _verify_datasets_available(self, metadata: Dict[str, Any]) -> bool:
+        """Verify if training datasets exist on Hugging Face Hub."""
+        datasets = metadata.get("datasets")
+        if not datasets:
+            return False
+
+        # Normalize to list
+        if isinstance(datasets, str):
+            datasets = [datasets]
+        elif isinstance(datasets, dict):
+            datasets = [datasets.get("name", "")]
+
+        # Filter out empty/placeholder values
+        valid = [d for d in datasets if isinstance(d, str) and d.strip() and d.lower() != "unknown"]
+
+        return any(self._verify_dataset_exists_on_hf(d) for d in valid) if valid else False
+
+    def _verify_dataset_exists_on_hf(self, dataset_id: str) -> bool:
+        """Check if dataset exists and is accessible on HF Hub."""
+        try:
+            info = self.hf_api.dataset_info(repo_id=dataset_id)
+            return info is not None and not getattr(info, 'disabled', False)
+        except Exception:
+            return False

tests/test_service.py

@@ -119,5 +119,108 @@ def test_generate_purl_no_namespace(self):
         purl = self.service._generate_purl("model", "1.0")
         self.assertEqual(purl, "pkg:huggingface/model@1.0")
 
+    @patch("src.models.service.calculate_completeness_score")
+    @patch("src.models.service.EnhancedExtractor")
+    def test_training_data_flag_with_datasets(self, mock_extractor_cls, mock_score):
+        """Test that trainingDataAvailable flag is set to true when datasets are present"""
+        # Setup
+        mock_extractor = mock_extractor_cls.return_value
+        metadata_with_data = {
+            "name": "test-model",
+            "datasets": ["dataset1", "dataset2"],
+            "commit": "123456"
+        }
+        mock_extractor.extract_metadata.return_value = metadata_with_data
+        mock_extractor.extraction_results = {}
+        mock_score.return_value = {"total_score": 50}
+
+        self.service.hf_api.model_info.return_value = MagicMock(sha="123456")
+
+        # Mock dataset verification
+        with patch.object(self.service, '_verify_dataset_exists_on_hf', return_value=True):
+            # Action
+            aibom = self.service.generate_aibom("owner/model")
+
+        # Verify
+        model_card = aibom["components"][0].get("modelCard", {})
+        properties = model_card.get("properties", [])
+
+        # Find the trainingDataAvailable property
+        training_flag = next((p for p in properties if p["name"] == "genai:aibom:trainingDataAvailable"), None)
+        self.assertIsNotNone(training_flag)
+        self.assertEqual(training_flag["value"], "true")
+
+        # Verify no warning
+        warning = next((p for p in properties if p["name"] == "genai:aibom:trainingDataWarning"), None)
+        self.assertIsNone(warning)
+
+    @patch("src.models.service.calculate_completeness_score")
+    @patch("src.models.service.EnhancedExtractor")
+    def test_training_data_flag_without_datasets(self, mock_extractor_cls, mock_score):
+        """Test that trainingDataAvailable flag is set to false and warning is added when datasets are missing"""
+        # Setup
+        mock_extractor = mock_extractor_cls.return_value
+        metadata_no_data = {
+            "name": "test-model",
+            "commit": "123456"
+            # No datasets key
+        }
+        mock_extractor.extract_metadata.return_value = metadata_no_data
+        mock_extractor.extraction_results = {}
+        mock_score.return_value = {"total_score": 50}
+
+        self.service.hf_api.model_info.return_value = MagicMock(sha="123456")
+
+        # Action
+        aibom = self.service.generate_aibom("owner/model")
+
+        # Verify
+        model_card = aibom["components"][0].get("modelCard", {})
+        properties = model_card.get("properties", [])
+
+        # Find the trainingDataAvailable property
+        training_flag = next((p for p in properties if p["name"] == "genai:aibom:trainingDataAvailable"), None)
+        self.assertIsNotNone(training_flag)
+        self.assertEqual(training_flag["value"], "false")
+
+        # Verify warning is present
+        warning = next((p for p in properties if p["name"] == "genai:aibom:trainingDataWarning"), None)
+        self.assertIsNotNone(warning)
+        self.assertIn("Training data information is missing", warning["value"])
+
+    def test_verify_datasets_available_with_valid_datasets(self):
+        """Test dataset verification with valid datasets"""
+        # Mock the HF API call
+        with patch.object(self.service, '_verify_dataset_exists_on_hf', return_value=True):
+            # List of valid datasets
+            metadata = {"datasets": ["dataset1", "dataset2"]}
+            self.assertTrue(self.service._verify_datasets_available(metadata))
+
+            # Single string dataset
+            metadata = {"datasets": "valid_dataset"}
+            self.assertTrue(self.service._verify_datasets_available(metadata))
+
+            # Dict format with name
+            metadata = {"datasets": {"name": "my_dataset", "url": "https://example.com"}}
+            self.assertTrue(self.service._verify_datasets_available(metadata))
+
+    def test_verify_datasets_available_with_empty_datasets(self):
+        """Test dataset verification with empty or invalid datasets"""
+        # Empty list
+        metadata = {"datasets": []}
+        self.assertFalse(self.service._verify_datasets_available(metadata))
+
+        # List with empty strings
+        metadata = {"datasets": ["", "  ", ""]}
+        self.assertFalse(self.service._verify_datasets_available(metadata))
+
+        # Unknown placeholder
+        metadata = {"datasets": ["unknown"]}
+        self.assertFalse(self.service._verify_datasets_available(metadata))
+
+        # No datasets key
+        metadata = {"name": "test-model"}
+        self.assertFalse(self.service._verify_datasets_available(metadata))
+
 if __name__ == '__main__':
     unittest.main()