diff --git a/MANIFEST.in b/MANIFEST.in
index 959d48e..8d58b75 100644
--- a/MANIFEST.in
+++ b/MANIFEST.in
@@ -1,13 +1,4 @@
-include maps.txt
 include README.md
 include README.rst
+include ivtmetrics/maps.txt
 recursive-include data *
-README.txt
-setup.cfg
-setup.py
-maps.txt
-ivtmetrics/__init__.py
-ivtmetrics/detection.py
-ivtmetrics/disentangle.py
-ivtmetrics/recognition.py
-ivtmetrics/maps.txt
diff --git a/README.rst b/README.rst
index b8f0b72..ee52e67 100644
--- a/README.rst
+++ b/README.rst
@@ -19,7 +19,8 @@ Supports disentangle prediction and obtained filtered performance for
 the various components of the triplets as well as their association
 performances at various levels.
 
-## Installation
+Installation
+============
 
 Install via PyPi
 ~~~~~~~~~~~~~~~~
@@ -39,7 +40,8 @@ Install via Conda
 
 Python 3.5-3.9 and numpy and scikit-learn are required.
 
-## Metrics
+Metrics
+=======
 
 The metrics have been aligned with what is reported by
 `CholecT50 <https://arxiv.org/abs/2109.03223>`__ benchmark.
@@ -133,7 +135,8 @@ args:
 -  the output is a ``dict`` with keys(“AP”, “mAP”) for per-class and
    mean AP respectively.
 
-#### Example usage
+Example usage
+~~~~~~~~~~~~~
 
 .. code:: python
 
@@ -232,7 +235,7 @@ The following function are possible with the ``Detection`` class:
 args:
 ~~~~~
 
-1. **list of list format**: [[tripletID, toolID, toolProbs, x, y, w, h],
+1. ``list of list format``: [[tripletID, toolID, toolProbs, x, y, w, h],
    [tripletID, toolID, toolProbs, x, y, w, h], …], where:
 
    -  ``tripletID`` = triplet unique identity
@@ -244,7 +247,7 @@ args:
    -  ``h`` = height of the box
    -  The [x,y,w,h] are scaled between 0..1
 
-2. **list of dict format**: [{“triplet”:tripletID, “instrument”:[toolID,
+2. ``list of dict format``: [{“triplet”:tripletID, “instrument”:[toolID,
    toolProbs, x, y, w, h]}, {“triplet”:tripletID, “instrument”:[toolID,
    toolProbs, x, y, w, h]}, …].
 3. ``format`` args describes the input format with either of the values
@@ -258,7 +261,8 @@ args:
    “mPre”) for per-class AP, mean AP, per-class Recall, mean Recall,
    per-class Precision and mean Precision respectively.
 
-#### Example usage
+Example usage
+~~~~~~~~~~~~~
 
 .. code:: python
 
@@ -303,11 +307,13 @@ args:
 Any ``nan`` value in results is for classes with no occurrence in the
 data sample.
 
-## Docker
+Docker
+======
 
 coming soon ..
 
-# Citation
+Citation
+========
 
 If you use this metrics in your project or research, please consider
 citing the associated publication:
@@ -321,7 +327,8 @@ citing the associated publication:
      year={2021}
    }
 
-### References
+References
+==========
 
 1. Nwoye, C. I., Yu, T., Gonzalez, C., Seeliger, B., Mascagni, P.,
    Mutter, D., … & Padoy, N. (2021). Rendezvous: Attention Mechanisms
@@ -335,6 +342,7 @@ citing the associated publication:
 3. https://cholectriplet2021.grand-challenge.org
 4. http://camma.u-strasbg.fr/datasets
 
+
 License
 -------
 
diff --git a/ivtmetrics/__init__.py b/ivtmetrics/__init__.py
index 9fb401d..0480d75 100644
--- a/ivtmetrics/__init__.py
+++ b/ivtmetrics/__init__.py
@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 __library__ = "ivtmetrics"
-__version__ = "0.0.4"
+__version__ = "0.0.5"
 __author__  = 'Chinedu Nwoye'
 __supervisor__  = 'Nicolas Padoy'
 __credits__ = 'CAMMA, ICube Lab, University of Strasbourg, France'
diff --git a/ivtmetrics/disentangle.py b/ivtmetrics/disentangle.py
index dc659f3..bb7d802 100644
--- a/ivtmetrics/disentangle.py
+++ b/ivtmetrics/disentangle.py
@@ -26,7 +26,7 @@ class Disentangle(object):
         call filter a component labels from the inputs labels     
     """
 
-    def __init__(self, url="maps.txt"):
+    def __init__(self, url="maps.py"):
         self.bank = np.genfromtxt(url, dtype=int, comments='#', delimiter=',', skip_header=0)
         
     def decompose(self, inputs, component):
diff --git a/setup.py b/setup.py
index 628a469..dd4f0b1 100644
--- a/setup.py
+++ b/setup.py
@@ -6,7 +6,7 @@
 
 setup(
     name='ivtmetrics',
-    version='0.0.4',    
+    version='0.0.5',    
     packages=['ivtmetrics'],
     author='Chinedu Nwoye',
     author_email='nwoye@unistra.fr',    
@@ -15,9 +15,8 @@
     long_description = long_description,
     long_description_content_type ='text/x-rst',
     url='https://github.com/CAMMA-public/ivtmetrics',
-    download_url = 'https://github.com/CAMMA-public/ivtmetrics/archive/refs/tags/v0.0.4.tar.gz',    # I explain this later on
+    download_url = 'https://github.com/CAMMA-public/ivtmetrics/archive/refs/tags/v0.0.5.tar.gz',    # I explain this later on
     license='BSD 2-clause', # Chose a license from here: https://help.github.com/articles/licensing-a-repository
-    package_data={'': ['ivtmetrics/maps.txt', 'README.md', 'README.rst']},
     include_package_data=True,
     install_requires=['scikit-learn',
                       'numpy',
@@ -39,4 +38,5 @@
 )    
 
 # guide @ https://medium.com/@joel.barmettler/how-to-upload-your-python-package-to-pypi-65edc5fe9c56
-# 'Operating System :: POSIX :: Linux :: Windows :: Mac :: Unix',   
+# 'Operating System :: POSIX :: Linux :: Windows :: Mac :: Unix',  
+#    package_data={'': ['ivtmetrics/maps.txt', 'README.md', 'README.rst']},