diff --git a/.github/workflows/publish.yml b/.github/workflows/publish.yml
new file mode 100644
index 0000000..a75da4f
--- /dev/null
+++ b/.github/workflows/publish.yml
@@ -0,0 +1,27 @@
+name: pypi
+
+on:
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: '3.8'
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install setuptools wheel twine
+    - name: Build and publish
+      env:
+        TWINE_USERNAME: __token__
+        TWINE_PASSWORD: ${{ secrets.PUNCC_TO_PYPI }}
+      run: |
+        python setup.py sdist bdist_wheel
+        twine upload dist/*
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index b0e8292..298dce5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -13,7 +13,7 @@
 # Virtual environment
 puncc-dev-env/
 puncc-user-env/
-.venv
+.venv/
 
 # Local demo files
 **demo/
diff --git a/README.md b/README.md
index 358e983..7015b21 100644
--- a/README.md
+++ b/README.md
@@ -50,7 +50,7 @@ Documentation is available [**online**](https://deel-ai.github.io/puncc/index.ht
 You can directly install the library using pip:
 
 ```bash
-pip install git+https://github.com/deel-ai/puncc
+pip install puncc
 ```
 
 <!--
diff --git a/deel/puncc/api/README.md b/deel/puncc/api/README.md
deleted file mode 100644
index 341cb44..0000000
--- a/deel/puncc/api/README.md
+++ /dev/null
@@ -1,291 +0,0 @@
-# Architecture Overview
-
-*Puncc* enables a turnkey solution and a fully customized approach to conformal prediction. It is as simple as calling the conformal prediction procedures in `deel.puncc.regression` or `deel.puncc.classification`.
-
-The currently implemented conformal regression procedures are the following:
-* `deel.puncc.regression.SplitCP`: Split Conformal Prediction
-* `deel.puncc.regression.LocallyAdaptiveCP`: Locally Adaptive Conformal Prediction
-* `deel.puncc.regression.CQR`: Conformalized Quantile Regression
-* `deel.puncc.regression.CvPlus`: CV + (cross-validation)
-* `deel.puncc.regression.EnbPI`: Ensemble Batch Prediction Intervals method
-* `deel.puncc.regression.aEnbPI`: locally adaptive Ensemble Batch Prediction Intervals method
-
-The currently implemented conformal classification procedures are the following:
-* `deel.puncc.classification.APS`: Adaptive Prediction Sets.
-* `deel.puncc.classification.RAPS`: Regularized Adaptive Prediction Sets. APS is a special case where regularization term is nulled ($\lambda = 0$).
-
-Each of these procedures conformalize point-based or interval-based models that are wrapped in a predictor and passed as argument to the constructor. Wrapping the models in a predictor (`deel.puncc.api.prediction`) enables to work with several ML/DL libraries and data structures.
-
-The **API** offers more flexibility into defining conformal prediction procedures. Let's say we want to fit/calibrate a neural-network interval-estimator with a cross-validation plan; or that we want to experiment different user-defined nonconformity scores. In such cases and others, the user can fully construct their approaches using the proposed **Predictor-Calibrator-Splitter** paradigm. It boils down to assembling into `puncc.api.conformalization.ConformalPredictor`:
-1) a predictor
-2) A calibrator defining a nonconformity score and a procedure to construct/calibrate the prediction sets
-3) A splitter defining the strategy of data assignement into fitting and calibration sets
-
-<figure style="text-align:center">
-    <img src="../../../docs/assets/puncc_architecture.png"/>
-</figure>
-
-## ConformalPredictor
-
-`deel.puncc.api.conformalization.ConformalPredictor` is the canvas of conformal prediction procedures.
-An object instance is constructed by, as we will explain later, a **predictor**, a **calibrator** and a **splitter**:
-
-```python
-# Imports
-from sklearn import linear_model
-from deel.puncc.api.conformalization import ConformalPredictor
-from deel.puncc.api.prediction import BasePredictor
-from deel.puncc.api.calibration import BaseCalibrator
-from deel.puncc.api.splitting import KFoldSplitter
-
-# Regression linear model
-model = linear_model.LinearRegression()
-
-# Definition of a predictor (This will be explained later)
-my_predictor = BasePredictor(model) # Predictor
-
-# Definition of a calibrator, built for a given nonconformity scores and a
-# procedure to build the prediction sets
-
-## Definition of a custom nonconformity scores function.
-## Alternatively, several ready-to-use nonconf scores are provided in
-## the module deel.puncc.nonconformity_scores (more on this later)
-def my_ncf(y_pred, y_true):
-    return np.abs(y_pred-y_true)
-
-## Definition of a custom function to build prediction sets.
-## Alternatively, several ready-to-use procedure are provided in
-## the module deel.puncc.prediction_sets (more on this later)
-def my_psf(y_pred, nonconf_scores_quantile):
-    y_lower = y_pred - nonconf_scores_quantile
-    y_upper = y_pred + nonconf_scores_quantile
-    return y_lower, y_upper
-
-## Calibrator construction
-my_calibrator = BaseCalibrator(nonconf_score_func=my_ncf,
-                                pred_set_func=my_psf) # Calibrator
-
-# Definition of a K-fold splitter that produces 20 folds of fit/calibration
-kfold_splitter = KFoldSplitter(K=20, random_state=42) # Splitter
-
-# Conformal prediction canvas
-conformal_predictor = ConformalPredictor(predictor=my_predictor,
-                                        calibrator=my_calibrator,
-                                        splitter=kfold_splitter)
-```
-
-`deel.puncc.api.conformalization.ConformalPredictor` implements two methods:
-
-* A `fit` method that fits the predictor model and computes nonconformity scores accodingly to the calibrator and to the data split strategy provided by the splitter
-
-```python
-# X_train and y_train are the full training dataset
-# The splitter passed as argument to ConformalPredictor assigns data
-# to the fit and calibration sets based on the provided splitting strategy
-conformal_predictor.fit(X_train, y_train)
-```
-
-* And a `predict` method that estimates for new samples the point predictions and prediction intervals [y_pred_lower, y_pred_upper], w.r.t a chosen error (significance) level $\alpha$
-
-
-```python
-# Coverage target of 1-alpha = 90%
-y_pred, y_pred_lower, y_pred_upper = conformal_predictor.predict(X_new, alpha=.1)
-```
-
-The full code snippet of the previous CVplus-like procedure with a randomly generated dataset is provided below:
-
-```python
-# Imports
-from sklearn.datasets import make_regression
-from sklearn.model_selection import train_test_split
-from sklearn import linear_model
-from deel.puncc.api.conformalization import ConformalPredictor
-from deel.puncc.api.prediction import BasePredictor
-from deel.puncc.api.calibration import BaseCalibrator
-from deel.puncc.api.splitting import KFoldSplitter
-from deel.puncc.plotting import plot_prediction_intervals
-from deel.puncc import metrics
-
-# Data
-## Generate a random regression problem
-X, y = make_regression(n_samples=1000, n_features=4, n_informative=2,
-                        random_state=0, shuffle=False)
-
-## Split data into train and test
-X_train, X_test, y_train, y_test = train_test_split(
-    X, y, test_size=.2, random_state=0
-)
-
-# Regression linear model
-model = linear_model.LinearRegression()
-
-# Definition of a predictor (This will be explained later)
-my_predictor = BasePredictor(model) # Predictor
-
-# Definition of a calibrator, built for a given nonconformity scores and a
-# procedure to build the prediction sets
-
-## Definition of a custom nonconformity scores function.
-## Alternatively, several ready-to-use nonconf scores are provided in
-## the module deel.puncc.nonconformity_scores (more on this later)
-def my_ncf(y_pred, y_true):
-    return np.abs(y_pred-y_true)
-
-## Definition of a custom function to build prediction sets.
-## Alternatively, several ready-to-use procedure are provided in
-## the module deel.puncc.prediction_sets (more on this later)
-def my_psf(y_pred, nonconf_scores_quantile):
-    y_lower = y_pred - nonconf_scores_quantile
-    y_upper = y_pred + nonconf_scores_quantile
-    return y_lower, y_upper
-
-## Calibrator construction
-my_calibrator = BaseCalibrator(nonconf_score_func=my_ncf,
-                                pred_set_func=my_psf) # Calibrator
-
-# Definition of a K-fold splitter that produces 20 folds of fit/calibration
-kfold_splitter = KFoldSplitter(K=20, random_state=42) # Splitter
-
-# Conformal prediction canvas
-conformal_predictor = ConformalPredictor(predictor=my_predictor,
-                                        calibrator=my_calibrator,
-                                        splitter=kfold_splitter)
-conformal_predictor.fit(X_train, y_train)
-y_pred, y_pred_lower, y_pred_upper = conformal_predictor.predict(X_test, alpha=.1)
-
-# Compute empirical marginal coverage and average width of the prediction intervals
-coverage = metrics.regression_mean_coverage(y_test, y_pred_lower, y_pred_upper)
-width = metrics.regression_sharpness(y_pred_lower=y_pred_lower,
-                                    y_pred_upper=y_pred_upper)
-print(f"Marginal coverage: {np.round(coverage, 2)}")
-print(f"Average width: {np.round(width, 2)}")
-
-# Figure of the prediction bands
-plot_prediction_intervals(
-    X = X_test[:,0],
-    y_true=y_test,
-    y_pred=y_pred,
-    y_pred_lower=y_pred_lower,
-    y_pred_upper=y_pred_upper,
-    sort_X=True,
-    size=(10, 6),
-    loc="upper left")
-```
-
-## Predictor
-
-The `deel.puncc.api.prediction.BasePredictor` and `deel.puncc.api.prediction.DualPredictor` classes are wrappers of ML/DL models
-that aims to expose a standardized interface and guarantee compliance with the `puncc`'s framework.
-The predictors have to implement:
-
-* a `fit` method used to train the model. It takes as arguments two iterables X, Y (collection of data such as ndarray and tensors) and any additional configuration of the underlying model (e.g., random seed).
-* a `predict` method used to predict targets for a given iterable X. It takes as arguments an iterable X and any additional configuration of the underlying model (e.g., batch size).
-* a `copy` method that returns a copy of the predictor (useful in cross validation for example). It has to deepcopy the underlying model.
-
-The constructor of `deel.puncc.api.prediction.BasePredictor` takes in the model to be wrapped, a flag to inform if the model is already trained
-and compilation keyword arguments if the underlying model needs to be compiled (such as in TensorFlow or PyTorch).
-
-The constructor of `deel.puncc.api.prediction.DualPredictor` is conceptually similar but take as arguments a list of two models, a list of two trained flags and a list of two compilation kwargs.
-Such predictor is useful when the calibration relies of several models (such as upper and lower quantiles in CQR).
-Note that the output `y_pred` of the `predict` method are a collection of couples, where the first (resp. second) axis is associated to the output of the first (resp. second) model.
-Specifically, `deel.puncc.api.prediction.MeanVarPredictor` is a subclass of `deel.puncc.api.prediction.DualPredictor` that
-trains the first model on the data and the second one to predict the absolute error of the former model.
-
-These three predictor classes cover plenty of use case in conformal prediction.
-But if you have a special need, you can subclass `deel.puncc.api.prediction.BasePredictor` or `deel.puncc.api.prediction.DualPredictor` or
-even create a predictor from scratch.
-
-Here is a example of situation where you need to define your own predictor:
-you have a classification problem and you build a `RandomForestClassifier`
-from sklearn. The procedure `RAPS` to conformalize the classifier requires
-a `predict` method that outputs the estimated probabily of each class. This is not the case
-as `RandomForestClassifier.predict` returns only the most likely class. In this case,
-we need to create a predictor in which we redefine the `predict` call:
-
-```python
-from sklearn.ensemble import RandomForestClassifier
-from deel.puncc.api.prediction import BasePredictor
-
-# Create rf classifier
-rf_model = RandomForestClassifier(n_estimators=100, random_state=0)
-
-# Create a wrapper of the random forest model to redefine its predict method
-# into logits predictions. Make sure to subclass BasePredictor.
-# Note that we needed to build a new wrapper (over BasePredictor) only because
-# the predict(.) method of RandomForestClassifier does not predict logits.
-# Otherwise, it is enough to use BasePredictor (e.g., neural network with softmax).
-class RFPredictor(BasePredictor):
-    def predict(self, X, **kwargs):
-        return self.model.predict_proba(X, **kwargs)
-
-# Wrap model in the newly created RFPredictor
-rf_predictor = RFPredictor(rf_model)
-```
-
-## Calibrator
-
-The calibrator provides a structure to estimate the nonconformity scores
-on the calibration set and to compute the prediction sets. At the constructor `deel.puncc.api.calibration.BaseCalibrator`,
-one decides which nonconformity score and prediction set functions to use.
-Then, the calibrator instance computes **nonconformity scores** (e.g., mean absolute deviation) by calling
-`deel.puncc.api.calibration.Calibrator.fit` on the calibration dataset. Based on the estimated quantiles of nonconformity scores,
-the method `deel.puncc.api.calibration.BaseCalibrator.calibrate` enables to **construct** and/or **calibrate** prediction sets.
-
-For example, the `BaseCalibrator` in the split conformal prediction procedure
-uses the mean absolute deviation as nonconformity score and and prediction set
-are built as constant intervals. These two functions are already provided in
-`deel.puncc.api.nonconformity_scores.mad` and `deel.puncc.api.prediction_sets.constant_interval`, respectively:
-
-```python
-from deel.puncc.api.calibration import BaseCalibrator
-from deel.puncc.api import nonconformity_scores
-from deel.puncc.api import prediction_sets
-
-## Calibrator construction
-my_calibrator = BaseCalibrator(nonconf_score_func=nonconformity_scores.mad,
-                                pred_set_func=prediction_sets.constant_interval)
-```
-
-Alternatively, one can define custom functions and pass them as arguments to the calibrator:
-
-```python
-from deel.puncc.api.calibration import BaseCalibrator
-
-## Definition of a custom nonconformity scores function.
-## Alternatively, several ready-to-use nonconf scores are provided in
-## the module deel.puncc.nonconformity_scores
-def my_ncf(y_pred, y_true):
-    return np.abs(y_pred-y_true)
-
-## Definition of a custom function to build prediction sets.
-## Alternatively, several ready-to-use procedure are provided in
-## the module deel.puncc.prediction_sets
-def my_psf(y_pred, nonconf_scores_quantile):
-    y_lower = y_pred - nonconf_scores_quantile
-    y_upper = y_pred + nonconf_scores_quantile
-    return y_lower, y_upper
-
-## Calibrator construction
-my_calibrator = BaseCalibrator(nonconf_score_func=my_ncf, pred_set_func=my_psf)
-```
-
-## Splitter
-
-In conformal prediction, the assignement of data into fit and calibration sets is motivated by two criteria:
-data availability and computational resources. If quality data is abundant,
-we can split the training samples into disjoint subsets $D_{fit}$ and $D_{calib}$.
-When data is scarce, a cross-validation strategy is preferred but is more
-ressource-consuming as different models are trained and nonconformity scores
-are computed for different disjoint folds.
-
-The two plans are implemented in `deel.puncc.api.splitting` module,
-and are agnostic to the data structure (which can be ndarrays, tensors and dataframes):
-
-- `deel.puncc.api.splitting.RandomSplitter`: random assignement of samples in $D_{fit}$ and $D_{calib}$
-- `deel.puncc.api.splitting.KFoldSplitter`: random assignement of samples into K disjoint folds. Note that if K equals the size of training set, the split is identified with the leave-one-out strategy
-
-Additionnaly, if the user already implemted a split plan, the obtained data asignement
-is wrapped in `deel.puncc.api.splitting.IdSplitter` to produce iterables.
-
-These methods produce **iterables** that are used by the `ConformalPredictor` instance.
diff --git a/deel/puncc/api/nonconformity_scores.py b/deel/puncc/api/nonconformity_scores.py
index 1e5aa65..ea12636 100644
--- a/deel/puncc/api/nonconformity_scores.py
+++ b/deel/puncc/api/nonconformity_scores.py
@@ -48,7 +48,11 @@
 
 
 def raps_score(
-    Y_pred: Iterable, y_true: Iterable, lambd: float = 0, k_reg: int = 1
+    Y_pred: Iterable,
+    y_true: Iterable,
+    lambd: float = 0,
+    k_reg: int = 1,
+    rand: bool = True,
 ) -> Iterable:
     """RAPS nonconformity score.
 
@@ -69,6 +73,8 @@ def raps_score(
         from which the regularization is applied. For example,
         if :math:`k_{reg} = 3`, then the fourth most likely estimated class has
         an extra penalty of size :math:`\\lambda`.
+    : param bool rand: turn on or off the randomization term that smoothes the
+        discrete probability mass jump when including a new class.
 
 
     :returns: RAPS nonconformity scores.
@@ -84,8 +90,6 @@ def raps_score(
         raise NotImplementedError(
             "RAPS/APS nonconformity scores only implemented for ndarrays"
         )
-    # Generate u randomly from a uniform distribution
-    u = np.random.uniform(size=len(y_true))
 
     # Sort classes by descending probability order
     class_ranking = np.argsort(-Y_pred, axis=1)
@@ -104,17 +108,27 @@ def raps_score(
     # Threshold of cumulative probability mass to include the real class
     E = [sorted_cum_mass[i, L[i]] for i in range(y_true.shape[0])]
 
-    E = [
-        E[i]
-        + lambd * np.maximum((L[i] + 1 - k_reg), 0)
-        - u[i] * sorted_proba[i, L[i]]
-        for i in range(y_true.shape[0])
-    ]
+    if rand:
+        # Generate u randomly from a uniform distribution
+        u = np.random.uniform(size=len(y_true))
+        E = [
+            E[i]
+            + lambd * np.maximum((L[i] + 1 - k_reg), 0)
+            - u[i] * sorted_proba[i, L[i]]
+            for i in range(y_true.shape[0])
+        ]
+    else:
+        E = [
+            E[i] + lambd * np.maximum((L[i] + 1 - k_reg), 0)
+            for i in range(y_true.shape[0])
+        ]
 
     return np.array(E)
 
 
-def raps_score_builder(lambd: float = 0, k_reg: int = 1) -> Callable:
+def raps_score_builder(
+    lambd: float = 0, k_reg: int = 1, rand: bool = True
+) -> Callable:
     """RAPS nonconformity score builder. When called, returns a RAPS
     nonconformity score function :func:`raps_score` with given initialitation
     of regularization hyperparameters.
@@ -126,6 +140,8 @@ def raps_score_builder(lambd: float = 0, k_reg: int = 1) -> Callable:
         from which the regularization is applied. For example, if
         :math:`k_{reg} = 3`, then the fourth most likely estimated class has
         an extra penalty of size :math:`\\lambda`.
+    : param bool rand: turn on or off the randomization term that smoothes the
+        discrete probability mass jump when including a new class.
 
     :returns: RAPS nonconformity score function that takes two parameters:
         `Y_pred` and `y_true`.
@@ -134,7 +150,7 @@ def raps_score_builder(lambd: float = 0, k_reg: int = 1) -> Callable:
     """
 
     def _raps_score_function(Y_pred: Iterable, y_true: Iterable) -> np.ndarray:
-        return raps_score(Y_pred, y_true, lambd, k_reg)
+        return raps_score(Y_pred, y_true, lambd, k_reg, rand)
 
     return _raps_score_function
 
diff --git a/deel/puncc/api/prediction_sets.py b/deel/puncc/api/prediction_sets.py
index cd59b20..bffa39a 100644
--- a/deel/puncc/api/prediction_sets.py
+++ b/deel/puncc/api/prediction_sets.py
@@ -44,7 +44,9 @@
 # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Classification ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 
-def raps_set(Y_pred, scores_quantile, lambd: float = 0, k_reg: int = 1) -> List:
+def raps_set(
+    Y_pred, scores_quantile, lambd: float = 0, k_reg: int = 1, rand: bool = True
+) -> List:
     """RAPS prediction set.
 
     .. warning::
@@ -65,6 +67,8 @@ def raps_set(Y_pred, scores_quantile, lambd: float = 0, k_reg: int = 1) -> List:
         from which the regularization is applied. For example, if
         :math:`k_{reg} = 3`, then the fourth most likely estimated class has an
         extra penalty of size :math:`\\lambda`.
+    : param bool rand: turn on or off the randomization term that smoothes the
+        discrete probability mass jump when including a new class.
 
 
     :returns: RAPS prediction sets.
@@ -78,8 +82,9 @@ def raps_set(Y_pred, scores_quantile, lambd: float = 0, k_reg: int = 1) -> List:
 
     logger.debug(f"Shape of Y_pred: {Y_pred.shape}")
 
-    # Generate u randomly from a uniform distribution
-    u = np.random.uniform(size=pred_len)
+    if rand:
+        # Generate u randomly from a uniform distribution
+        u = np.random.uniform(size=pred_len)
 
     # 1-alpha th empirical quantile of conformity scores
     tau = scores_quantile
@@ -109,6 +114,14 @@ def raps_set(Y_pred, scores_quantile, lambd: float = 0, k_reg: int = 1) -> List:
         pred_len,
     )
 
+    if not rand:
+        # Build prediction set
+        prediction_sets = [
+            list(idx_class_pred_ranking[i, : L[i]]) for i in range(pred_len)
+        ]
+        return (prediction_sets,)
+
+    ## The following code runs only when rand argument is True
     # For indexing, use L-1 to denote the L-th element
     # Residual of cumulative probability mass (regularized) and tau
     proba_excess = [
@@ -143,7 +156,9 @@ def raps_set(Y_pred, scores_quantile, lambd: float = 0, k_reg: int = 1) -> List:
     return (prediction_sets,)
 
 
-def raps_set_builder(lambd: float = 0, k_reg: int = 1) -> Callable:
+def raps_set_builder(
+    lambd: float = 0, k_reg: int = 1, rand: bool = True
+) -> Callable:
     """RAPS prediction set builder. When called, returns a RAPS prediction set
     function :func:`raps_set` with given initialitation of regularization
     hyperparameters.
@@ -155,6 +170,8 @@ def raps_set_builder(lambd: float = 0, k_reg: int = 1) -> Callable:
         from which the regularization is applied. For example, if
         :math:`k_{reg} = 3`, then the fourth most likely estimated class has an
         extra penalty of size :math:`\\lambda`.
+    : param bool rand: turn on or off the randomization term that smoothes the
+        discrete probability mass jump when including a new class.
 
     :returns: RAPS prediction set function that takes two parameters:
         `Y_pred` and `scores_quantile`.
@@ -172,7 +189,9 @@ def raps_set_builder(lambd: float = 0, k_reg: int = 1) -> Callable:
     # @TODO: type checking and co
 
     def _raps_set_function(Y_pred, scores_quantile):
-        return raps_set(Y_pred, scores_quantile, lambd=lambd, k_reg=k_reg)
+        return raps_set(
+            Y_pred, scores_quantile, lambd=lambd, k_reg=k_reg, rand=rand
+        )
 
     return _raps_set_function
 
diff --git a/deel/puncc/api/utils.py b/deel/puncc/api/utils.py
index 0760cdb..74cb6bd 100644
--- a/deel/puncc/api/utils.py
+++ b/deel/puncc/api/utils.py
@@ -30,6 +30,7 @@
 from typing import Iterable
 from typing import Optional
 from typing import Tuple
+from typing import Union
 
 import numpy as np
 
@@ -144,7 +145,7 @@ def supported_types_check(*data: Iterable):
             )
 
 
-def alpha_calib_check(alpha: float, n: int, complement_check: bool = False):
+def alpha_calib_check(alpha: Union[float, np.ndarray], n: int, complement_check: bool = False):
     """Check if the value of alpha :math:`\\alpha` is consistent with the size
     of calibration set :math:`n`.
 
@@ -161,7 +162,7 @@ def alpha_calib_check(alpha: float, n: int, complement_check: bool = False):
 
         0 < \\alpha \cdot (1+1/n) < 1 \implies 0 < \\alpha < n/(n+1)
 
-    :param float alpha: target quantile order.
+    :param float or np.ndarray alpha: target quantile order.
     :param int n: size of the calibration dataset.
     :param bool complement_check: complementary check to compute the
         :math:`\\alpha \cdot (1+1/n)`-th quantile, required by some methods
@@ -171,26 +172,30 @@ def alpha_calib_check(alpha: float, n: int, complement_check: bool = False):
         calibration set.
     """
 
-    if alpha < 1 / (n + 1):
+    if np.any(alpha < 1 / (n + 1)):
         raise ValueError(
-            f"Alpha is too small: (alpha={alpha}, n={n}) {alpha} < {1/(n+1)}. "
+            f"Alpha is too small: (alpha={alpha}, n={n}) "
+            + f"{alpha} < {1/(n+1)} for at least one of its coordinates. "
             + "Increase alpha or the size of the calibration set."
         )
 
-    if alpha >= 1:
+    if np.any(alpha >= 1):
         raise ValueError(
-            f"Alpha={alpha} is too large. Decrease alpha such that alpha < 1."
+            f"Alpha={alpha} is too large. " 
+            + "Decrease alpha such that all of its coordinates are < 1."
         )
 
-    if complement_check and alpha > n / (n + 1):
+    if complement_check and np.any(alpha > n / (n + 1)):
         raise ValueError(
-            f"Alpha is too large: (alpha={alpha}, n={n}) {alpha} < {n/(n+1)}. "
+            f"Alpha is too large: (alpha={alpha}, n={n}) "
+            + f"{alpha} < {n/(n+1)} for at least on of its coordinates. "
             + "Decrease alpha or increase the size of the calibration set."
         )
 
-    if complement_check and alpha <= 0:
+    if complement_check and np.any(alpha <= 0):
         raise ValueError(
-            f"Alpha={alpha} is too small. Increase alpha such that alpha > 0."
+            f"Alpha={alpha} is too small. "
+            + "Increase alpha such that all of its coordinates > 0."
         )
 
 
diff --git a/deel/puncc/classification.py b/deel/puncc/classification.py
index a04938f..fa7f89e 100644
--- a/deel/puncc/classification.py
+++ b/deel/puncc/classification.py
@@ -55,6 +55,8 @@ class RAPS:
         from which the regularization is applied. For example,
         if :math:`k_{reg} = 3`, then the fourth most likely estimated class has
         an extra penalty of size :math:`\\lambda`.
+    : param bool rand: turn on or off randomization used in raps algorithm.
+        One consequence of turning off randomization is avoiding empty prediction sets.
 
     .. note::
 
@@ -138,18 +140,19 @@ def predict(self, X, **kwargs):
     def __init__(
         self,
         predictor,
-        train=True,
+        train: bool = True,
         random_state: float = None,
-        lambd=0,
-        k_reg=1,
+        lambd: float = 0,
+        k_reg: int = 1,
+        rand: bool = True,
     ):
         self.predictor = predictor
         self.calibrator = BaseCalibrator(
             nonconf_score_func=nonconformity_scores.raps_score_builder(
-                lambd=lambd, k_reg=k_reg
+                lambd=lambd, k_reg=k_reg, rand=rand
             ),
             pred_set_func=prediction_sets.raps_set_builder(
-                lambd=lambd, k_reg=k_reg
+                lambd=lambd, k_reg=k_reg, rand=rand
             ),
             weight_func=None,
         )
@@ -267,6 +270,8 @@ class APS(RAPS):
     :param BasePredictor predictor: a predictor implementing fit and predict.
     :param bool train: if False, prediction model(s) will not be trained and
         will be used as is. Defaults to True.
+    : param bool rand: turn on or off randomization used in aps algorithm.
+        One consequence of turning off randomization is avoiding empty prediction sets.
 
     .. _example aps:
 
@@ -340,5 +345,5 @@ def predict(self, X, **kwargs):
 
     """
 
-    def __init__(self, predictor, train=True):
-        super().__init__(predictor=predictor, train=train, lambd=0)
+    def __init__(self, predictor, train=True, rand=True):
+        super().__init__(predictor=predictor, train=train, lambd=0, rand=rand)
diff --git a/docs/assets/results_quickstart_split_cad_if.png b/docs/assets/results_quickstart_split_cad_if.png
new file mode 100644
index 0000000..1f483ae
Binary files /dev/null and b/docs/assets/results_quickstart_split_cad_if.png differ
diff --git a/docs/puncc_intro.ipynb b/docs/puncc_intro.ipynb
index 67ce572..02f6c60 100644
--- a/docs/puncc_intro.ipynb
+++ b/docs/puncc_intro.ipynb
@@ -8,7 +8,9 @@
    "source": [
     "# 👋 Welcome to the introduction tutorial\n",
     "\n",
-    "In this tutorial, we will guide you, while using *puncc*, throughout the process of uncertainty quantification in two prediction tasks. By the end of this notebook, you will be able to wrap your own models into conformal predictors and analyze their performance. \n",
+    "In this tutorial, we will guide you, while using *puncc*, throughout the process of uncertainty quantification in two prediction tasks. By the end of this notebook, you will be able to wrap your own models into conformal predictors and analyze their performance.\n",
+    "\n",
+    "In addition, we will provide a guide on how to use conformal prediction for anomaly detection. Let's get started !\n",
     "\n",
     "**Table of contents**\n",
     "\n",
@@ -20,6 +22,10 @@
     "    - [💾 MNIST Dataset](#cc-data)\n",
     "    - [🔮 Predicton Model](#cc-pm)\n",
     "    - [⚙️ Conformal Prediction](#cc-cp)\n",
+    "- [🚩 Conformal Anomaly Detection](#cad)\n",
+    "    - [💾 Two moons Dataset](#cad-data)\n",
+    "    - [🔮 Anomaly detector](#cad-pm)\n",
+    "    - [⚙️ Conformal Anomaly Detection](#cad-cp)\n",
     "\n",
     "\n",
     "**Links**\n",
@@ -182,7 +188,7 @@
    "id": "8b7b5e72",
    "metadata": {},
    "source": [
-    "Such model needs to be wrapped in a wrapper provided in the module deel.puncc.api.prediction. The wrapper makes it possible to use various models from different ML/DL libraries such as Scikit-learn, Keras or XGBoost. For more information about model wrappers and supported ML/DL libraries, we refere the user to the documentation.\n",
+    "Such model needs to be wrapped in a wrapper provided in the module `deel.puncc.api.prediction`. The wrapper makes it possible to use various models from different ML/DL libraries such as Scikit-learn, Keras or XGBoost. For more information about model wrappers and supported ML/DL libraries, we refere the user to the documentation.\n",
     "\n",
     "For a linear regression from scikit-learn, we use deel.puncc.api.prediction.BasePredictor as follows:"
    ]
@@ -295,7 +301,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 1500x600 with 1 Axes>"
       ]
@@ -327,7 +333,7 @@
    "id": "cba4c9c2",
    "metadata": {},
    "source": [
-    "## 📊 Conformal Classification"
+    "## 📊 Conformal Classification <a class=\"anchor\" id=\"cc\"></a>"
    ]
   },
   {
@@ -485,11 +491,11 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/2\n",
-      "176/176 [==============================] - 14s 77ms/step - loss: 0.6308 - accuracy: 0.8323 - val_loss: 0.2383 - val_accuracy: 0.9274\n",
+      "176/176 [==============================] - 18s 94ms/step - loss: 0.6308 - accuracy: 0.8323 - val_loss: 0.2383 - val_accuracy: 0.9274\n",
       "Epoch 2/2\n",
-      "176/176 [==============================] - 14s 77ms/step - loss: 0.1707 - accuracy: 0.9492 - val_loss: 0.1518 - val_accuracy: 0.9530\n",
-      "313/313 [==============================] - 1s 3ms/step\n",
-      "313/313 [==============================] - 1s 4ms/step\n"
+      "176/176 [==============================] - 20s 116ms/step - loss: 0.1707 - accuracy: 0.9492 - val_loss: 0.1518 - val_accuracy: 0.9530\n",
+      "313/313 [==============================] - 3s 8ms/step\n",
+      "313/313 [==============================] - 2s 6ms/step\n"
      ]
     }
    ],
@@ -534,7 +540,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 640x480 with 1 Axes>"
       ]
@@ -588,6 +594,241 @@
     "print(f\"Average set size : {mean_size:.2f}\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 🚩 Conformal Anomaly Detection  <a class=\"anchor\" id=\"cad\"></a>\n",
+    "\n",
+    "Let's consider the two moons dataset and a collection of data points randomly scattered across a plane. Among these points, some will stand out as outliers, deviating significantly from the crescent-shaped clusters. Using an isolation forest algorithm, we generate anomaly scores for each data point. Subsequently, we wrap the model with conformal anomaly detection to calibrate the detection threshold. This ensures that the False Detection Rate (FDR) remains below the user-specified threshold $\\alpha$."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 💾 Two moons Dataset <a class=\"anchor\" id=\"cc-data\"></a>\n",
+    "\n",
+    "The two moons dataset is a synthetic dataset that consists of two crescent-shaped clusters of points. It is a popular dataset for evaluating anomaly detection algorithms because it is easy to visualize and has a well-defined structure. In the code below, we generate 5000 examples from the two moons distribution. In addition, we generate 300 new points distributed uniformly across the plane."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from sklearn.datasets import make_moons\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "n_samples = 5000\n",
+    "n_new = 350\n",
+    "\n",
+    "# We generate the two moons dataset\n",
+    "dataset = 4 * make_moons(n_samples=n_samples, noise=0.05, random_state=42)[\n",
+    "    0\n",
+    "] - np.array([0.5, 0.25])\n",
+    "\n",
+    "# We generate uniformly new (test) data points\n",
+    "rng = np.random.RandomState(42)\n",
+    "z_test = rng.uniform(low=-6, high=10, size=(n_new, 2))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### 🔮 Anomaly detection Model <a class=\"anchor\" id=\"cad-pm\"></a>\n",
+    "\n",
+    "We use the isolation forest (IF) algorithm to produce anomaly scores. Such model will be trained in the following section."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn.ensemble import IsolationForest\n",
+    "\n",
+    "ad_model = IsolationForest(random_state=42) \n",
+    "\n",
+    "# Note that any other model could have been used, such as LOF:\n",
+    "# from sklearn.neighbors import LocalOutlierFactor\n",
+    "# ad_model = LocalOutlierFactor(n_neighbors=35, novelty=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Similarily to conformal regression and conformal classification, the underlying model needs to be wrapped in a wrapper provided in the module `deel.puncc.api.prediction`.\n",
+    "By default, the method `score_samples` returns the opposite of anomaly scores. We need to redefine the `predict` call to output the anomaly score:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from deel.puncc.api.prediction import BasePredictor\n",
+    "\n",
+    "# We redefine the predict method to return the opposite of IF scores\n",
+    "class ADPredictor(BasePredictor):\n",
+    "    def predict(self, X):\n",
+    "        return -self.model.score_samples(X)\n",
+    "\n",
+    "# wrap the (IF) anomaly detection model in a predictor\n",
+    "if_predictor = ADPredictor(ad_model)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### ⚙️ Conformal Anomaly Detection <a class=\"anchor\" id=\"cad-cp\"></a>\n",
+    "\n",
+    "The `deel.puncc.anomaly_detection.SplitCAD` wrapper is used to train and calibrate the IF anomaly detector  using 70% and 30% of the two moons dataset, respectively. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from deel.puncc.anomaly_detection import SplitCAD\n",
+    "\n",
+    "# Instantiate CAD on top of IF predictor\n",
+    "if_cad = SplitCAD(if_predictor, train=True, random_state=0)\n",
+    "\n",
+    "# Fit the IF on the proper fitting dataset and\n",
+    "# calibrate it using calibration dataset.\n",
+    "# The two datasets are sampled randomly with a ration of 7:3,\n",
+    "# respectively.\n",
+    "if_cad.fit(z=dataset, fit_ratio=0.7)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now, we call CAD to obtain conformal anomaly detections: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# We set the maximum false detection rate to 5%\n",
+    "alpha = 0.05\n",
+    "# The method `predict` is called on the new data points\n",
+    "# to test which are anomalous and which are not\n",
+    "cad_results = if_cad.predict(z_test, alpha=alpha)\n",
+    "cad_anomalies = z_test[cad_results]\n",
+    "cad_not_anomalies = z_test[np.invert(cad_results)]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Let's compare the results before and after the calibration. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.legend.Legend at 0x2164a72dc70>"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x600 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Detect anomalies with underlying IF model (no conformal)\n",
+    "if_results = if_cad.predictor.model.predict(z_test) == 1\n",
+    "if_not_anomalies = z_test[if_results]\n",
+    "if_anomalies = z_test[np.invert(if_results)]\n",
+    "\n",
+    "fig, ax = plt.subplots(ncols=2, figsize=(12, 6), sharex=True, sharey=True)\n",
+    "\n",
+    "# Plot if results\n",
+    "\n",
+    "ax[0].scatter(dataset[:, 0], dataset[:, 1], s=10, label=\"Inliers\")\n",
+    "ax[0].scatter(\n",
+    "    if_not_anomalies[:, 0],\n",
+    "    if_not_anomalies[:, 1],\n",
+    "    s=40,\n",
+    "    marker=\"x\",\n",
+    "    color=\"blue\",\n",
+    "    label=\"Normal\",\n",
+    ")\n",
+    "ax[0].scatter(\n",
+    "    if_anomalies[:, 0],\n",
+    "    if_anomalies[:, 1],\n",
+    "    s=40,\n",
+    "    marker=\"x\",\n",
+    "    color=\"red\",\n",
+    "    label=\"Anomaly\",\n",
+    ")\n",
+    "ax[0].set_xticks(())\n",
+    "ax[0].set_yticks(())\n",
+    "ax[0].set_title(\"Isolation Forest\")\n",
+    "ax[0].legend(loc=\"lower left\")\n",
+    "\n",
+    "# Plot cad results\n",
+    "ax[1].scatter(dataset[:, 0], dataset[:, 1], s=10, label=\"Inliers\")\n",
+    "ax[1].scatter(\n",
+    "    cad_not_anomalies[:, 0],\n",
+    "    cad_not_anomalies[:, 1],\n",
+    "    marker=\"x\",\n",
+    "    color=\"blue\",\n",
+    "    s=40,\n",
+    "    label=\"Normal\",\n",
+    ")\n",
+    "ax[1].scatter(\n",
+    "    cad_anomalies[:, 0],\n",
+    "    cad_anomalies[:, 1],\n",
+    "    marker=\"x\",\n",
+    "    color=\"red\",\n",
+    "    s=40,\n",
+    "    label=\"Anomaly\",\n",
+    ")\n",
+    "ax[1].set_xticks(())\n",
+    "ax[1].set_yticks(())\n",
+    "ax[1].set_title(\"Conformalized Isolation Forest\")\n",
+    "ax[1].legend(loc=\"lower left\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "See how conformal anomaly detection reduces false alarms !"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -603,7 +844,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "punc-user-env",
+   "display_name": "puncc-dev-env",
    "language": "python",
    "name": "python3"
   },
diff --git a/docs/source/conf.py b/docs/source/conf.py
index 1271ca1..166f75e 100644
--- a/docs/source/conf.py
+++ b/docs/source/conf.py
@@ -23,10 +23,10 @@
     " - All rights reserved. DEEL is a research program operated by IVADO, "
     "IRT Saint Exupéry, CRIAQ and ANITI"
 )
-author = "Mouhcine Mendil, Luca Mossina"
+author = "Mouhcine Mendil, Luca Mossina and Joseba Dalmau"
 
 # The full version, including alpha/beta/rc tags
-release = "0.1"
+release = "0.7"
 
 
 # -- General configuration ---------------------------------------------------
diff --git a/docs/source/getting_started.rst b/docs/source/getting_started.rst
index 52c3ed7..6f3da89 100644
--- a/docs/source/getting_started.rst
+++ b/docs/source/getting_started.rst
@@ -367,3 +367,179 @@ and the average empirical size of the prediction sets on the test examples:
 
    Empirical coverage : 0.90
    Average set size : 1.03
+
+
+🚩 Conformal Anomaly Detection
+------------------------------
+
+Let's consider the two moons dataset and a collection of data points randomly
+scattered across a plane. Among these points, some will stand out as outliers,
+deviating significantly from the crescent-shaped clusters.
+Using an isolation forest algorithm, we generate anomaly scores for each data point.
+Subsequently, we wrap the model with conformal anomaly detection to calibrate
+the detection threshold. This ensures that the False Detection Rate (FDR)
+remains below the user-specified threshold :math:`\\alpha`.
+
+
+💾 Two moons Dataset
+********************
+
+The two moons dataset is a synthetic dataset that consists of two
+crescent-shaped clusters of points. It is a popular dataset for evaluating
+anomaly detection algorithms because it is easy to visualize and has a
+well-defined structure. In the code below, we generate 5000 examples from the
+two moons distribution. In addition, we generate 300 new points distributed
+uniformly across the plane.
+
+.. code-block:: python
+
+   import numpy as np
+   from sklearn.datasets import make_moons
+   import matplotlib.pyplot as plt
+
+   n_samples = 5000
+   n_new = 350
+
+   # We generate the two moons dataset
+   dataset = 4 * make_moons(n_samples=n_samples, noise=0.05, random_state=42)[
+      0
+   ] - np.array([0.5, 0.25])
+
+   # We generate uniformly new (test) data points
+   rng = np.random.RandomState(42)
+   z_test = rng.uniform(low=-6, high=10, size=(n_new, 2))
+
+
+🔮 Anomaly detection model
+**************************
+
+We use the Isolation Forest (IF) algorithm to produce anomaly scores.
+Such model will be trained in the following section.
+
+.. code-block:: python
+
+   from sklearn.ensemble import IsolationForest
+
+   ad_model = IsolationForest(random_state=42)
+
+Similarily to conformal regression and conformal classification,
+the underlying model needs to be wrapped in a wrapper provided in the module
+:mod:`deel.puncc.api.prediction`. For more information about model wrappers
+and supported ML/DL libraries, checkout :doc:`the documentation <prediction>`.
+
+By default, the method `score_samples` returns the opposite of
+the anomaly scores.
+We need to redefine the `predict` call to output the anomaly score:
+
+.. code-block:: python
+
+   from deel.puncc.api.prediction import BasePredictor
+
+   # We redefine the predict method to return the opposite of IF scores
+   class ADPredictor(BasePredictor):
+      def predict(self, X):
+         return -self.model.score_samples(X)
+
+   # wrap the (IF) anomaly detection model in a predictor
+   if_predictor = ADPredictor(ad_model)
+
+
+⚙️ Conformal Anomaly Detection
+******************************
+
+The :class:`deel.puncc.anomaly_detection.SplitCAD` wrapper is used to train
+and calibrate the IF anomaly detector  using 70% and 30% of the two moons
+dataset, respectively.
+
+.. code-block:: python
+
+   from deel.puncc.anomaly_detection import SplitCAD
+
+   # Instantiate CAD on top of IF predictor
+   if_cad = SplitCAD(if_predictor, train=True, random_state=0)
+
+   # Fit the IF on the proper fitting dataset and
+   # calibrate it using calibration dataset.
+   # The two datasets are sampled randomly with a ration of 7:3,
+   # respectively.
+   if_cad.fit(z=dataset, fit_ratio=0.7)
+
+Now, we call CAD to obtain conformal anomaly detections:
+
+.. code-block:: python
+
+   # We set the maximum false detection rate to 5%
+   alpha = 0.05
+   # The method `predict` is called on the new data points
+   # to test which are anomalous and which are not
+   cad_results = if_cad.predict(z_test, alpha=alpha)
+   cad_anomalies = z_test[cad_results]
+   cad_not_anomalies = z_test[np.invert(cad_results)]
+
+Let's compare the results before and after the calibration.
+
+.. code-block:: python
+
+   # Detect anomalies with underlying IF model (no conformal)
+   if_results = if_cad.predictor.model.predict(z_test) == 1
+   if_not_anomalies = z_test[if_results]
+   if_anomalies = z_test[np.invert(if_results)]
+
+   fig, ax = plt.subplots(ncols=2, figsize=(12, 6), sharex=True, sharey=True)
+
+   # Plot if results
+
+   ax[0].scatter(dataset[:, 0], dataset[:, 1], s=10, label="Inliers")
+   ax[0].scatter(
+      if_not_anomalies[:, 0],
+      if_not_anomalies[:, 1],
+      s=40,
+      marker="x",
+      color="blue",
+      label="Normal",
+   )
+   ax[0].scatter(
+      if_anomalies[:, 0],
+      if_anomalies[:, 1],
+      s=40,
+      marker="x",
+      color="red",
+      label="Anomaly",
+   )
+   ax[0].set_xticks(())
+   ax[0].set_yticks(())
+   ax[0].set_title("Isolation Forest")
+   ax[0].legend(loc="lower left")
+
+   # Plot cad results
+   ax[1].scatter(dataset[:, 0], dataset[:, 1], s=10, label="Inliers")
+   ax[1].scatter(
+      cad_not_anomalies[:, 0],
+      cad_not_anomalies[:, 1],
+      marker="x",
+      color="blue",
+      s=40,
+      label="Normal",
+   )
+   ax[1].scatter(
+      cad_anomalies[:, 0],
+      cad_anomalies[:, 1],
+      marker="x",
+      color="red",
+      s=40,
+      label="Anomaly",
+   )
+   ax[1].set_xticks(())
+   ax[1].set_yticks(())
+   ax[1].set_title("Conformalized Isolation Forest")
+   ax[1].legend(loc="lower left")
+
+
+.. figure:: ../assets/results_quickstart_split_cad_if.png
+   :width: 600px
+   :align: center
+   :height: 300px
+   :figclass: align-center
+
+By calibrating the detection threshold, it is clear from the figure above that
+conformal anomaly detection reduces false alarms rate.
diff --git a/setup.py b/setup.py
index 6a6bb57..31e0fce 100644
--- a/setup.py
+++ b/setup.py
@@ -62,14 +62,15 @@
 setuptools.setup(
     name="puncc",
     version="0.7",
-    author=", ".join(["Mouhcine Mendil", "Luca Mossina"]),
+    author=", ".join(["Mouhcine Mendil", "Luca Mossina", "Joseba Dalmau"]),
     author_email=", ".join(
         [
             "mouhcine.mendil@irt-saintexupery.com",
             "luca.mossina@irt-saintexupery.com",
+            "joseba.dalmau@irt-saintexupery.com",
         ]
     ),
-    description="Predictive Uncertainty Calibration and Conformalization Library",
+    description="Predictive UNcertainty Calibration and Conformalization Library",
     long_description=long_description,
     long_description_content_type="text/markdown",
     url="https://github.com/deel-ai/puncc",
@@ -79,11 +80,11 @@
         "interactive": interactive_requirements,
         "dev": dev_requirements,
     },
-    python_requires=">=3.7",
+    python_requires=">=3.8",
     classifiers=[
-        "License :: MIT License",
+        "License :: OSI Approved :: MIT License",
         "Programming Language :: Python",
         "Programming Language :: Python :: 3",
-        "Operating System :: Cross-platform",
+        "Operating System :: OS Independent",
     ],
 )
diff --git a/tests/api/test_utils.py b/tests/api/test_utils.py
index 0181cbe..e85b190 100644
--- a/tests/api/test_utils.py
+++ b/tests/api/test_utils.py
@@ -133,6 +133,32 @@ def test_too_low_alpha(self):
         with self.assertRaises(ValueError):
             alpha_calib_check(alpha=0.01, n=10)
 
+    def test_proper_alpha_multidim(self):
+        max_n = 10000
+        n_vals = np.random.randint(10, high=max_n, size=100)
+        for n in n_vals:
+            lower_bound = 1 / (n + 1)
+            alpha_vals = (1 - lower_bound) * np.random.random_sample(
+                size=(100)
+            ) + lower_bound
+            alpha_calib_check(alpha_vals, n=n)
+
+    def test_out_lowerbound_alpha_multidim(self):
+        with self.assertRaises(ValueError):
+            alpha = np.array([0, 0.5, 0.5, 0.5])
+            alpha_calib_check(alpha, n=100000)
+
+    def test_out_upperbound_alpha_multidim(self):
+        with self.assertRaises(ValueError):
+            alpha = np.array([1, 0.5, 0.5, 0.5])
+            alpha_calib_check(alpha, n=100000)
+
+    def test_too_low_alpha_multidim(self):
+        with self.assertRaises(ValueError):
+            alpha = np.array([0.01, 0.5, 0.5, 0.5])
+            alpha_calib_check(alpha, n=10)
+
+
 
 class QuantileCheck(unittest.TestCase):
     def test_simple_quantile1d(self):
diff --git a/tests/test_classification_seed.py b/tests/test_classification_seed.py
index 55f9241..2afabc1 100644
--- a/tests/test_classification_seed.py
+++ b/tests/test_classification_seed.py
@@ -39,15 +39,17 @@
 
 RESULTS = {
     "aps": {"cov": 0.89, "size": 1.92},
+    "aps-norand": {"cov": 0.98, "size": 3.91},
     "raps": {"cov": 0.89, "size": 1.9},
+    "raps-norand": {"cov": 0.98, "size": 3.51},
 }
 
 
 @pytest.mark.parametrize(
-    "alpha, random_state",
-    [(0.1, 42)],
+    "alpha, random_state, rand",
+    [(0.1, 42, True)],
 )
-def test_aps(mnist_data, alpha, random_state):
+def test_aps(mnist_data, alpha, random_state, rand):
     tf.keras.utils.set_random_seed(random_state)
 
     # Get data
@@ -79,7 +81,7 @@ def test_aps(mnist_data, alpha, random_state):
     )
 
     # APS
-    aps_cp = APS(class_predictor)
+    aps_cp = APS(class_predictor, rand=rand)
     aps_cp.fit(
         X_fit=X_fit,
         y_fit=y_fit_cat,
@@ -98,10 +100,64 @@ def test_aps(mnist_data, alpha, random_state):
 
 
 @pytest.mark.parametrize(
-    "alpha, random_state, lambd, k_reg",
-    [(0.1, 42, 0.01, 1)],
+    "alpha, random_state, rand",
+    [(0.1, 42, False)],
 )
-def test_raps(mnist_data, alpha, random_state, lambd, k_reg):
+def test_aps_norand(mnist_data, alpha, random_state, rand):
+    tf.keras.utils.set_random_seed(random_state)
+
+    # Get data
+    (X_train, X_test, y_train, y_test, y_train_cat, y_test_cat) = mnist_data
+
+    # Split fit and calib datasets
+    X_fit, X_calib = X_train[:50000], X_train[50000:]
+    y_fit, y_calib = y_train[:50000], y_train[50000:]
+    y_fit_cat, y_calib_cat = y_train_cat[:50000], y_train_cat[50000:]
+
+    # One hot encoding of classes
+    y_fit_cat = to_categorical(y_fit)
+    y_calib_cat = to_categorical(y_calib)
+    y_test_cat = to_categorical(y_test)
+
+    # Classification model
+    nn_model = models.Sequential()
+    nn_model.add(layers.Dense(4, activation="relu", input_shape=(28 * 28,)))
+    nn_model.add(layers.Dense(10, activation="softmax"))
+    compile_kwargs = {
+        "optimizer": "rmsprop",
+        "loss": "categorical_crossentropy",
+        "metrics": [],
+    }
+    fit_kwargs = {"epochs": 2, "batch_size": 128, "verbose": 1}
+    # Predictor wrapper
+    class_predictor = BasePredictor(
+        nn_model, is_trained=False, **compile_kwargs
+    )
+
+    # APS
+    aps_cp = APS(class_predictor, rand=rand)
+    aps_cp.fit(
+        X_fit=X_fit,
+        y_fit=y_fit_cat,
+        X_calib=X_calib,
+        y_calib=y_calib,
+        **fit_kwargs
+    )
+    y_pred, set_pred = aps_cp.predict(X_test, alpha=alpha)
+    assert y_pred is not None
+
+    # Compute marginal coverage
+    coverage = metrics.classification_mean_coverage(y_test, set_pred)
+    width = metrics.classification_mean_size(set_pred)
+    res = {"cov": np.round(coverage, 2), "size": np.round(width, 2)}
+    assert RESULTS["aps-norand"] == res
+
+
+@pytest.mark.parametrize(
+    "alpha, random_state, lambd, k_reg, rand",
+    [(0.1, 42, 0.01, 1, True)],
+)
+def test_raps(mnist_data, alpha, random_state, lambd, k_reg, rand):
     tf.keras.utils.set_random_seed(random_state)
 
     # Get data
@@ -133,7 +189,7 @@ def test_raps(mnist_data, alpha, random_state, lambd, k_reg):
     )
 
     # RAPS
-    raps_cp = RAPS(class_predictor, k_reg=k_reg, lambd=lambd)
+    raps_cp = RAPS(class_predictor, k_reg=k_reg, lambd=lambd, rand=rand)
     raps_cp.fit(
         X_fit=X_fit,
         y_fit=y_fit_cat,
@@ -149,3 +205,57 @@ def test_raps(mnist_data, alpha, random_state, lambd, k_reg):
     width = metrics.classification_mean_size(set_pred)
     res = {"cov": np.round(coverage, 2), "size": np.round(width, 2)}
     assert RESULTS["raps"] == res
+
+
+@pytest.mark.parametrize(
+    "alpha, random_state, lambd, k_reg, rand",
+    [(0.1, 42, 0.01, 1, False)],
+)
+def test_raps_norand(mnist_data, alpha, random_state, lambd, k_reg, rand):
+    tf.keras.utils.set_random_seed(random_state)
+
+    # Get data
+    (X_train, X_test, y_train, y_test, y_train_cat, y_test_cat) = mnist_data
+
+    # Split fit and calib datasets
+    X_fit, X_calib = X_train[:50000], X_train[50000:]
+    y_fit, y_calib = y_train[:50000], y_train[50000:]
+    y_fit_cat, y_calib_cat = y_train_cat[:50000], y_train_cat[50000:]
+
+    # One hot encoding of classes
+    y_fit_cat = to_categorical(y_fit)
+    y_calib_cat = to_categorical(y_calib)
+    y_test_cat = to_categorical(y_test)
+
+    # Classification model
+    nn_model = models.Sequential()
+    nn_model.add(layers.Dense(4, activation="relu", input_shape=(28 * 28,)))
+    nn_model.add(layers.Dense(10, activation="softmax"))
+    compile_kwargs = {
+        "optimizer": "rmsprop",
+        "loss": "categorical_crossentropy",
+        "metrics": [],
+    }
+    fit_kwargs = {"epochs": 2, "batch_size": 128, "verbose": 1}
+    # Predictor wrapper
+    class_predictor = BasePredictor(
+        nn_model, is_trained=False, **compile_kwargs
+    )
+
+    # RAPS
+    raps_cp = RAPS(class_predictor, k_reg=k_reg, lambd=lambd, rand=rand)
+    raps_cp.fit(
+        X_fit=X_fit,
+        y_fit=y_fit_cat,
+        X_calib=X_calib,
+        y_calib=y_calib,
+        **fit_kwargs
+    )
+    y_pred, set_pred = raps_cp.predict(X_test, alpha=alpha)
+    assert y_pred is not None
+
+    # Compute marginal coverage
+    coverage = metrics.classification_mean_coverage(y_test, set_pred)
+    width = metrics.classification_mean_size(set_pred)
+    res = {"cov": np.round(coverage, 2), "size": np.round(width, 2)}
+    assert RESULTS["raps-norand"] == res