diff --git a/.gitignore b/.gitignore
index 611e0bc1..9c5092f2 100644
--- a/.gitignore
+++ b/.gitignore
@@ -47,3 +47,7 @@ examples/training/single_table/data/**
 examples/training/single_table/results/**
 examples/training/multi_table/data/**
 examples/training/multi_table/results/**
+examples/synthesizing/single_table/data/**
+examples/synthesizing/single_table/results/**
+examples/synthesizing/multi_table/data/**
+examples/synthesizing/multi_table/results/**
diff --git a/examples/synthesizing/multi_table/README.md b/examples/synthesizing/multi_table/README.md
new file mode 100644
index 00000000..737b49ec
--- /dev/null
+++ b/examples/synthesizing/multi_table/README.md
@@ -0,0 +1,60 @@
+# Multi-Table Synthesizing Example
+
+This example will go over synthesizing data for a multi-table dataset from the ground
+up using the code in this toolkit.
+
+
+## Downloading data
+
+First, we need the data. Download it from this
+[Google Drive link](https://drive.google.com/file/d/1Ao222l4AJjG54-HDEGCWkIfzRbl9_IKa/view?usp=drive_link),
+extract the files and place them in a `/data` folder within this folder
+(`examples/synthesizing/multi_table`).
+
+> [!NOTE]
+> If you wish to change the data folder, you can do so by editing the `base_data_dir` attribute
+> of the [`config.yaml`](config.yaml) file.
+
+It will contain data for 8 tables: `account`, `card`, `client`, `disp`, `district`, `loan`, `order`,
+and `trans`. For each table there will be two files:
+- `{table_name}.csv`: The table's data.
+- `{table_name}_domain.json`: Metadata about the columns in the table's data, such as data types and sizes.
+
+Additionally, you will find one more file:
+- `dataset_meta.json`: Metadata about the relationship between the tables. It will describe which tables
+are associated with which other tables.
+
+
+## Kicking off synthesizing
+
+If there is a `/results` folder within this folder (`examples/synthesizing/multi_table`)
+from a previous training run, we will use that data to kick off synthesizing.
+For example, you can copy the results from another run (e.g. `examples.training.multi_table.run_training`)
+and paste them here and it will be picked up by this example.
+
+The [`config.yaml`](config.yaml) file contains the parameters for the synthesizing and also
+for training, in case there is a need to run that. Please take a look at them before kicking
+off the synthesizing process and edit them as necessary.
+
+To kick off synthesizing, simply run the command below from the project's root folder:
+
+```bash
+python -m examples.synthesizing.multi_table.run_synthesizing
+```
+
+## Results
+
+It will save the result files inside a `/results` folder within this folder
+(`examples/synthesizing/multi_table`).
+
+> [!NOTE]
+> If you wish to change the save folder, you can do so by editing the `results_dir` attribute
+> of the [`config.yaml`](config.yaml) file.
+
+In the `/results/before_matching/` folder, there will be a file called `synthetic_tables.pkl`,
+which is a pickle file containing the synthetic data before the matching process, in case
+it's needed.
+
+The `/results/multi_table_synthesizing` folder will contain the final synthesized
+data, organized per table, in the form of `.csv` files with the following naming pattern:
+`/results/multi_table_synthesizing/{table_name}/_final/{table_name}_synthetic.csv`.
diff --git a/examples/synthesizing/multi_table/config.yaml b/examples/synthesizing/multi_table/config.yaml
new file mode 100644
index 00000000..bbfcff30
--- /dev/null
+++ b/examples/synthesizing/multi_table/config.yaml
@@ -0,0 +1,49 @@
+# Training example configuration
+# Base data directory (can be overridden from command line)
+base_data_dir: examples/synthesizing/multi_table/data
+results_dir: examples/synthesizing/multi_table/results
+
+# diffusion_config, clustering_config, and classifier_config are only required
+# when training a new model from scratch
+diffusion_config:
+  d_layers: [512, 1024, 1024, 1024, 1024, 512]
+  dropout: 0.0
+  num_timesteps: 2000
+  model_type: mlp
+  iterations: 20000
+  batch_size: 4096
+  lr: 0.0006
+  gaussian_loss_type: mse
+  weight_decay: 1e-05
+  scheduler: cosine
+  data_split_ratios: [0.99, 0.005, 0.005]
+
+clustering_config:
+  parent_scale: 1.0
+  num_clusters: 50
+  clustering_method: kmeans_and_gmm
+
+classifier_config:
+    d_layers: [128, 256, 512, 1024, 512, 256, 128]
+    lr: 0.0001
+    dim_t: 128
+    batch_size: 4096
+    iterations: 20000
+
+# Synthesizing configuration
+general_config:
+    data_dir: examples/synthesizing/multi_table/data
+    test_data_dir: examples/synthesizing/multi_table/data
+    exp_name: multi_table_synthesizing
+    workspace_dir: examples/synthesizing/multi_table/results
+    sample_prefix: ""
+
+sampling_config:
+    batch_size: 20000
+    classifier_scale: 1.0
+
+matching_config:
+    num_matching_clusters: 1
+    matching_batch_size: 1000
+    unique_matching: True
+    no_matching: False
diff --git a/examples/synthesizing/multi_table/run_synthesizing.py b/examples/synthesizing/multi_table/run_synthesizing.py
new file mode 100644
index 00000000..9d845e2e
--- /dev/null
+++ b/examples/synthesizing/multi_table/run_synthesizing.py
@@ -0,0 +1,88 @@
+import pickle
+from logging import INFO
+from pathlib import Path
+from typing import Any
+
+import hydra
+from omegaconf import DictConfig
+
+from examples.training.multi_table import run_training
+from midst_toolkit.common.config import GeneralConfig, MatchingConfig, SamplingConfig
+from midst_toolkit.common.logger import TOOLKIT_LOGGER, log
+from midst_toolkit.models.clavaddpm.data_loaders import load_tables
+from midst_toolkit.models.clavaddpm.enumerations import Relation
+from midst_toolkit.models.clavaddpm.synthesizer import clava_synthesizing
+
+
+# Preventing some excessive logging
+TOOLKIT_LOGGER.setLevel(INFO)
+
+
+@hydra.main(config_path=".", config_name="config", version_base=None)
+def main(config: DictConfig) -> None:
+    """
+    Run the synthesizing pipeline for a multi-table diffusion model.
+
+    It will load the config and then data from the `config.base_data_dir` folder,
+    train the model, synthesize the data and save the results in the
+    `config.results_dir` folder.
+
+    It will first look for a pre-trained model in the `config.results_dir` folder.
+    If it doesn't find one, it will train a new model from scratch.
+
+    Args:
+        config: Training and synthesizing configuration as an OmegaConf DictConfig object.
+    """
+    log(INFO, f"Checking for a pre-trained model in {config.results_dir}...")
+
+    _, relation_order, _ = load_tables(Path(config.base_data_dir))
+
+    model_file_paths: dict[Relation, dict[str, Any]] = {}
+    for relation in relation_order:
+        model_file_path = Path(config.results_dir) / "models" / f"{relation[0]}_{relation[1]}_ckpt.pkl"
+        model_file_paths[relation] = {
+            "file_path": model_file_path,
+            "exists": model_file_path.exists(),
+        }
+
+    clustering_results_file = Path(config.results_dir) / "cluster_ckpt.pkl"
+
+    if all(result["exists"] for result in model_file_paths.values()) and clustering_results_file.exists():
+        log(INFO, f"Found previous results in {config.results_dir}. Skipping training.")
+    else:
+        log(INFO, "Not all previous results found. Training a new model from scratch.")
+        log(INFO, f"Summary of results: {model_file_paths}")
+        log(INFO, f"Clustering results file: {clustering_results_file} exists? {clustering_results_file.exists()}")
+        run_training.main(config)
+
+    log(INFO, "Loading models...")
+
+    models = {}
+    for relation in relation_order:
+        with open(model_file_paths[relation]["file_path"], "rb") as f:
+            models[relation] = pickle.load(f)
+
+    with open(clustering_results_file, "rb") as f:
+        clustering_result = pickle.load(f)
+
+    tables = clustering_result["tables"]
+    all_group_lengths_prob_dicts = clustering_result["all_group_lengths_prob_dicts"]
+
+    log(INFO, "Synthesizing data...")
+
+    clava_synthesizing(
+        tables,
+        relation_order,
+        Path(config.results_dir),
+        models,
+        GeneralConfig(**config.general_config),
+        SamplingConfig(**config.sampling_config),
+        MatchingConfig(**config.matching_config),
+        all_group_lengths_prob_dicts,
+    )
+
+    log(INFO, "Data synthesized successfully.")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/examples/synthesizing/single_table/README.md b/examples/synthesizing/single_table/README.md
new file mode 100644
index 00000000..5f6f1f51
--- /dev/null
+++ b/examples/synthesizing/single_table/README.md
@@ -0,0 +1,58 @@
+# Single-Table Synthesizing Example
+
+This example will go over synthesizing data for a single-table dataset from the ground
+up using the code in this toolkit.
+
+
+## Downloading data
+
+First, we need the data. Download it from this
+[Google Drive link](https://drive.google.com/file/d/1J5qDuMHHg4dm9c3ISmb41tcTHSu1SVUC/view?usp=drive_link),
+extract the files and place them in a `/data` folder within this folder
+(`examples/synthesizing/single_table`).
+
+> [!NOTE]
+> If you wish to change the data folder, you can do so by editing the `base_data_dir` attribute
+> of the [`config.yaml`](config.yaml) file.
+
+Here is a description of the files that have been extracted:
+- `trans.csv`: The training data. It consists of information about bank transactions and it
+contains 20,000 data points.
+- `trans_domain.json`: Metadata about the columns in `trans.csv`, such as data types and sizes.
+- `dataset_meta.json`: Metadata about the relationship between the tables. Since this is a
+single-table example, it will only contain information about the `trans` table.
+
+
+## Kicking off synthesizing
+
+If there is a `/results` folder within this folder (`examples/synthesizing/single_table`)
+from a previous training run, we will use that data to kick off synthesizing.
+For example, you can copy the results from another run (e.g. `examples.training.single_table.run_training`)
+and paste them here and it will be picked up by this example.
+
+The [`config.yaml`](config.yaml) file contains the parameters for the synthesizing and also
+for training, in case there is a need to run that. Please take a look at them before kicking
+off the synthesizing process and edit them as necessary.
+
+To kick off synthesizing, simply run the command below from the project's root folder:
+
+```bash
+python -m examples.synthesizing.single_table.run_synthesizing
+```
+
+## Results
+
+It will save the result files inside a `/results` folder within this folder
+(`examples/synthesizing/single_table`).
+
+> [!NOTE]
+> If you wish to change the save folder, you can do so by editing the `results_dir` attribute
+> of the [`config.yaml`](config.yaml) file.
+
+In the `/results/before_matching/` folder, there will be a file called `synthetic_tables.pkl`,
+which is a pickle file containing the synthetic data before the matching process, in case
+it's needed.
+
+The `/results/single_table_synthesizing` folder will contain the final synthesized
+data, organized per table. In this single-table example, there is only going to be one
+synthesized table under `/results/single_table_synthesizing/trans/_final/trans_synthetic.csv`.
diff --git a/examples/synthesizing/single_table/config.yaml b/examples/synthesizing/single_table/config.yaml
new file mode 100644
index 00000000..b3cbb0e2
--- /dev/null
+++ b/examples/synthesizing/single_table/config.yaml
@@ -0,0 +1,36 @@
+# Training example configuration
+# Base data directory (can be overridden from command line)
+base_data_dir: examples/synthesizing/single_table/data
+results_dir: examples/synthesizing/single_table/results
+
+# diffusion_config is only required when training a new model from scratch
+diffusion_config:
+  d_layers: [512, 1024, 1024, 1024, 1024, 512]
+  dropout: 0.0
+  num_timesteps: 2000
+  model_type: mlp
+  iterations: 20000
+  batch_size: 4096
+  lr: 0.0006
+  gaussian_loss_type: mse
+  weight_decay: 1e-05
+  scheduler: cosine
+  data_split_ratios: [0.99, 0.005, 0.005]
+
+# Synthesizing configuration
+general_config:
+    data_dir: examples/synthesizing/single_table/data
+    test_data_dir: examples/synthesizing/single_table/data
+    exp_name: single_table_synthesizing
+    workspace_dir: examples/synthesizing/single_table/results
+    sample_prefix: ""
+
+sampling_config:
+    batch_size: 20000
+    classifier_scale: 1.0
+
+matching_config:
+    num_matching_clusters: 1
+    matching_batch_size: 1000
+    unique_matching: True
+    no_matching: False
diff --git a/examples/synthesizing/single_table/run_synthesizing.py b/examples/synthesizing/single_table/run_synthesizing.py
new file mode 100644
index 00000000..b9f6a649
--- /dev/null
+++ b/examples/synthesizing/single_table/run_synthesizing.py
@@ -0,0 +1,84 @@
+import pickle
+from logging import INFO
+from pathlib import Path
+from typing import Any
+
+import hydra
+from omegaconf import DictConfig
+
+from examples.training.single_table import run_training
+from midst_toolkit.common.config import GeneralConfig, MatchingConfig, SamplingConfig
+from midst_toolkit.common.logger import TOOLKIT_LOGGER, log
+from midst_toolkit.models.clavaddpm.data_loaders import load_tables
+from midst_toolkit.models.clavaddpm.enumerations import Relation
+from midst_toolkit.models.clavaddpm.synthesizer import clava_synthesizing
+
+
+# Preventing some excessive logging
+TOOLKIT_LOGGER.setLevel(INFO)
+
+
+@hydra.main(config_path=".", config_name="config", version_base=None)
+def main(config: DictConfig) -> None:
+    """
+    Run the synthesizing pipeline for a single-table diffusion model.
+
+    It will load the config and then data from the `config.base_data_dir` folder,
+    train the model, synthesize the data and save the results in the
+    `config.results_dir` folder.
+
+    It will first look for a pre-trained model in the `config.results_dir` folder.
+    If it doesn't find one, it will train a new model from scratch.
+
+    Args:
+        config: Training and synthesizing configuration as an OmegaConf DictConfig object.
+    """
+    log(INFO, f"Checking for a pre-trained model in {config.results_dir}...")
+
+    tables, relation_order, _ = load_tables(Path(config.base_data_dir))
+
+    assert len(relation_order) == 1 and relation_order[0][0] is None, (
+        "Relation order is not configured for single-table. "
+        "For multi-table synthesizing, please use the `examples.synthesizing.multi_table.run_synthesizing` example. "
+        f"Relation order: {relation_order}"
+    )
+
+    model_file_paths: dict[Relation, dict[str, Any]] = {}
+    for relation in relation_order:
+        model_file_path = Path(config.results_dir) / "models" / f"{relation[0]}_{relation[1]}_ckpt.pkl"
+        model_file_paths[relation] = {
+            "file_path": model_file_path,
+            "exists": model_file_path.exists(),
+        }
+
+    if all(result["exists"] for result in model_file_paths.values()):
+        log(INFO, f"Found previous results in {config.results_dir}. Skipping training.")
+    else:
+        log(INFO, "Not all previous results found. Training a new model from scratch.")
+        log(INFO, f"Summary of results: {model_file_paths}")
+        run_training.main(config)
+
+    log(INFO, "Loading models...")
+
+    models = {}
+    for relation in relation_order:
+        with open(model_file_paths[relation]["file_path"], "rb") as f:
+            models[relation] = pickle.load(f)
+
+    log(INFO, "Synthesizing data...")
+
+    clava_synthesizing(
+        tables,
+        relation_order,
+        Path(config.results_dir),
+        models,
+        GeneralConfig(**config.general_config),
+        SamplingConfig(**config.sampling_config),
+        MatchingConfig(**config.matching_config),
+    )
+
+    log(INFO, "Data synthesized successfully.")
+
+
+if __name__ == "__main__":
+    main()
diff --git a/examples/training/multi_table/README.md b/examples/training/multi_table/README.md
index 31791112..31e2584a 100644
--- a/examples/training/multi_table/README.md
+++ b/examples/training/multi_table/README.md
@@ -13,7 +13,7 @@ extract the files and place them in a `/data` folder in within this folder
 
 > [!NOTE]
 > If you wish to change the data folder, you can do so by editing the `base_data_dir` attribute
-> of the [`config.yaml`](config.yaml) file.
+> of the (`config.yaml`)[config.yaml] file.
 
 It will contain data for 8 tables: `account`, `card`, `client`, `disp`, `district`, `loan`, `order`,
 and `trans`. For each table there will be two files:
@@ -44,7 +44,7 @@ The result files will be saved inside a `/results` folder within this folder
 
 > [!NOTE]
 > If you wish to change the save folder, you can do so by editing the `results_dir` attribute
-> of the [`config.yaml`](config.yaml) file.
+> of the (`config.yaml`)[config.yaml] file.
 
 One of the results file is `/results/cluster_ckpt.pkl`, which will contain the results
 of the clustering step.
diff --git a/examples/training/single_table/README.md b/examples/training/single_table/README.md
index ac6fa12b..683e7431 100644
--- a/examples/training/single_table/README.md
+++ b/examples/training/single_table/README.md
@@ -13,7 +13,7 @@ extract the files and place them in a `/data` folder in within this folder
 
 > [!NOTE]
 > If you wish to change the data folder, you can do so by editing the `base_data_dir` attribute
-> of the [`config.yaml`](config.yaml) file.
+> of the (`config.yaml`)[config.yaml] file.
 
 Here is a description of the files that have been extracted:
 - `trans.csv`: The training data. It consists of information about bank transactions and it
@@ -42,7 +42,7 @@ The result files will be saved inside a `/results` folder within this folder
 
 > [!NOTE]
 > If you wish to change the save folder, you can do so by editing the `results_dir` attribute
-> of the [`config.yaml`](config.yaml) file.
+> of the (`config.yaml`)[config.yaml] file.
 
 In the `/results/models/` folder, there will be a file called `None_trans_ckpt.pkl`,
 which is a pickle file containing the training results. You can load it using Python's
diff --git a/examples/training/single_table/config.yaml b/examples/training/single_table/config.yaml
index 7fc54556..719be647 100644
--- a/examples/training/single_table/config.yaml
+++ b/examples/training/single_table/config.yaml
@@ -8,7 +8,7 @@ diffusion_config:
   dropout: 0.0
   num_timesteps: 2000
   model_type: mlp
-  iterations: 200000
+  iterations: 20000
   batch_size: 4096
   lr: 0.0006
   gaussian_loss_type: mse
diff --git a/src/midst_toolkit/attacks/ensemble/shadow_model_utils.py b/src/midst_toolkit/attacks/ensemble/shadow_model_utils.py
index 1678a3cd..f1693c8e 100644
--- a/src/midst_toolkit/attacks/ensemble/shadow_model_utils.py
+++ b/src/midst_toolkit/attacks/ensemble/shadow_model_utils.py
@@ -142,11 +142,11 @@ def train_tabddpm_and_synthesize(
             tables,
             relation_order,
             save_dir,
-            all_group_lengths_prob_dicts,
             models,
             configs.general,
             configs.sampling,
             configs.matching,
+            all_group_lengths_prob_dicts,
             sample_scale=sample_scale,
         )
 
@@ -235,11 +235,11 @@ def fine_tune_tabddpm_and_synthesize(
             new_tables,
             relation_order,
             save_dir,
-            all_group_lengths_prob_dicts,
             new_models,
             configs.general,
             configs.sampling,
             configs.matching,
+            all_group_lengths_prob_dicts,
             sample_scale=sample_scale,
         )
 
diff --git a/src/midst_toolkit/models/clavaddpm/clustering.py b/src/midst_toolkit/models/clavaddpm/clustering.py
index 1299d85b..b841ec6d 100644
--- a/src/midst_toolkit/models/clavaddpm/clustering.py
+++ b/src/midst_toolkit/models/clavaddpm/clustering.py
@@ -59,6 +59,8 @@ def clava_clustering(
             "tables": tables,
             "all_group_lengths_prob_dicts": all_group_lengths_prob_dicts,
         }
+
+        save_dir.mkdir(parents=True, exist_ok=True)
         with open(save_dir / "cluster_ckpt.pkl", "wb") as f:
             pickle.dump(cluster_ckpt, f)
 
diff --git a/src/midst_toolkit/models/clavaddpm/data_loaders.py b/src/midst_toolkit/models/clavaddpm/data_loaders.py
index 008e0d6c..2cb10746 100644
--- a/src/midst_toolkit/models/clavaddpm/data_loaders.py
+++ b/src/midst_toolkit/models/clavaddpm/data_loaders.py
@@ -96,7 +96,7 @@ def load_tables(
     with open(data_dir / "dataset_meta.json", "r") as f:
         dataset_meta = json.load(f)
 
-    relation_order = dataset_meta["relation_order"]
+    relation_order = [tuple(relation) for relation in dataset_meta["relation_order"]]
 
     tables = {}
 
diff --git a/src/midst_toolkit/models/clavaddpm/synthesizer.py b/src/midst_toolkit/models/clavaddpm/synthesizer.py
index 2204ec52..44741bcd 100644
--- a/src/midst_toolkit/models/clavaddpm/synthesizer.py
+++ b/src/midst_toolkit/models/clavaddpm/synthesizer.py
@@ -17,7 +17,7 @@
 from midst_toolkit.common.config import GeneralConfig, MatchingConfig, SamplingConfig
 from midst_toolkit.common.enumerations import DataSplit
 from midst_toolkit.common.logger import log
-from midst_toolkit.models.clavaddpm.data_loaders import Tables
+from midst_toolkit.models.clavaddpm.data_loaders import NO_PARENT_COLUMN_NAME, Tables
 from midst_toolkit.models.clavaddpm.dataset import Dataset, TableMetadata, Transformations
 from midst_toolkit.models.clavaddpm.enumerations import (
     CategoricalEncoding,
@@ -626,9 +626,9 @@ def sample_from_dict(probabilities: dict[int, float]) -> int:
     Returns:
         The sampled key.
     """
-    assert sum(probabilities.values()) == 1.0, "The sum of all probabilities must be 1.0."
+    assert np.isclose(sum(probabilities.values()), 1), "The sum of all probabilities must be 1."
 
-    # Generate a random number between 0 and 1
+    # Generate a random number between [0, 1)
     random_number = random.random()
 
     # Initialize cumulative sum and the selected key
@@ -711,11 +711,11 @@ def clava_synthesizing(
     tables: Tables,
     relation_order: RelationOrder,
     save_dir: Path,
-    all_group_lengths_prob_dicts: GroupLengthsProbDicts,
     models: dict[Relation, ModelArtifacts],
     general_config: GeneralConfig,
     sampling_config: SamplingConfig,
     matching_config: MatchingConfig,
+    all_group_lengths_prob_dicts: GroupLengthsProbDicts | None = None,
     sample_scale: float = 1.0,
 ) -> tuple[dict[str, pd.DataFrame], float, float]:
     """
@@ -726,12 +726,13 @@ def clava_synthesizing(
         tables: Tables containing dataframes and clustering information.
         relation_order: List of parent-child table relationships.
         save_dir: Directory to save intermediate and final results.
-        all_group_lengths_prob_dicts: Dictionary containing group length probabilities for each
-            parent-child relationship.
         models: Trained models for each parent-child relationship.
         general_config: General configuration settings.
         sampling_config: Configuration settings for sampling.
         matching_config: Configuration settings for matching.
+        all_group_lengths_prob_dicts: Dictionary containing group length probabilities for each
+            parent-child relationship. Optional for single-table synthesizing, required for
+            multi-table synthesizing. Defaults to None.
         sample_scale: Scale factor for the number of samples to generate
             based on the train data size. Defaults to 1.0.
 
@@ -754,6 +755,10 @@ def clava_synthesizing(
         log(INFO, "Sample size: {}".format(int(sample_scale * len(df_without_id))))
 
         if parent is None:
+            # Adding the no parent placeholder column in case it doesn't have it
+            if NO_PARENT_COLUMN_NAME not in df_without_id.columns:
+                df_without_id[NO_PARENT_COLUMN_NAME] = list(range(len(df_without_id)))
+
             # synthesize data for single table or tables with no parent
             synthesized_df, table_keys = _synthesize_single_table(
                 child,
@@ -762,7 +767,12 @@ def clava_synthesizing(
                 sample_scale,
                 sampling_config.batch_size,
             )
+
         else:
+            assert all_group_lengths_prob_dicts is not None, (
+                "all_group_lengths_prob_dicts is required for multi-table synthesizing."
+            )
+
             # Finding previously synthesized data and training results for the parent
             parent_synthetic_data = None
             parent_training_results = None
diff --git a/tests/integration/models/clavaddpm/test_model.py b/tests/integration/models/clavaddpm/test_model.py
index 4bb3b965..43689ff0 100644
--- a/tests/integration/models/clavaddpm/test_model.py
+++ b/tests/integration/models/clavaddpm/test_model.py
@@ -122,7 +122,7 @@ def test_load_single_table():
         },
     )
 
-    assert relation_order == [[None, "trans"]]
+    assert relation_order == [(None, "trans")]
     assert dataset_meta["relation_order"] == [[None, "trans"]]
     assert dataset_meta["tables"] == {"trans": {"children": [], "parents": []}}
 
@@ -225,7 +225,7 @@ def test_load_tables():
         },
     )
 
-    assert relation_order == [[None, "account"], ["account", "trans"]]
+    assert relation_order == [(None, "account"), ("account", "trans")]
     assert dataset_meta["relation_order"] == [[None, "account"], ["account", "trans"]]
     assert dataset_meta["tables"] == {
         "account": {"children": ["trans"], "parents": []},
diff --git a/tests/integration/models/clavaddpm/test_synthesizer.py b/tests/integration/models/clavaddpm/test_synthesizer.py
index 267160df..ae88477e 100644
--- a/tests/integration/models/clavaddpm/test_synthesizer.py
+++ b/tests/integration/models/clavaddpm/test_synthesizer.py
@@ -92,11 +92,11 @@ def test_clava_synthesize_multi_table(tmp_path: Path):
         tables,
         relation_order,
         tmp_path,
-        all_group_lengths_prob_dicts,
         models[1],
         synthesizing_config,
         SAMPLING_CONFIG,
         MATCHING_CONFIG,
+        all_group_lengths_prob_dicts,
     )
 
     # Assert