diff --git a/.github/workflows/gen-citation.yaml b/.github/workflows/gen-citation.yaml
new file mode 100644
index 0000000..e76a36a
--- /dev/null
+++ b/.github/workflows/gen-citation.yaml
@@ -0,0 +1,32 @@
+on:
+  pull_request:
+    types:
+      - closed
+
+jobs:
+  if_merged:
+    if: github.event.pull_request.merged == true
+    runs-on: ubuntu-latest
+    steps:
+    - name: Set up Python 3.10
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.10
+
+    - name: Install dependencies
+      run: |
+        pip install .[citation]
+    
+    - name: Generate citation based on pyproject.toml
+      run: |
+        cff-from-621
+    
+    - name: Commit and push changes
+      run: |
+        git config --local user.email "action@github.com"
+        git config --local user.name "GitHub Action"
+        git add .
+        git commit -m "Auto commit after successful merge"
+        git push
+
+      
\ No newline at end of file
diff --git a/pyproject.toml b/pyproject.toml
index 3d95941..c188b9b 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -10,25 +10,53 @@ target-version = "py37"
 [project]
 name = "pymurtree"
 version = "0.0.1"
+description = "Python bindings for MurTree"
+readme = "README.md"
+license = "MIT"
+keywords = ["MurTree", "Optimal decision tree", "Python bindings"]
+
+authors = [
+  {name = "Yasel Quintero", orcid = "0000-0000-0000-0001"},
+  {name = "Jose Urra", orcid = "0000-0000-0000-0002"},
+]
+
 dependencies =[
     "pandas>=1.0.0",
     "numpy>=1.18.0",
 ]
 
+[project.urls]
+homepage = "https://github.com/MurTree/pymurtree.git"
+MurTreeCpp = "https://github.com/MurTree/murtree"
+sample_data = "https://github.com/MurTree/murtree-data"
+journal = "https://doi.org/10.48550/arXiv.2007.12652"
+
 classifiers = [
     "Programming Language :: Python :: 3",
     "License :: OSI Approved :: MIT License",
     "Operating System :: OS Independent", ]
 
 [project.optional-dependencies]
-test = [
+dev = [
     "pytest>=5.3.0",
     "pytest-cov>=2.8.0",
 ]
+citation = [
+    "cff-from-621",
+]
 
 [tool.pytest.ini_options]
 pythonpath = [
   ".", "src/pymurtree",
 ]
 
-[project.urls]
+
+[tool.cff-from-621]
+order = ["message", "cff-version", "title", "abstract", "version", "date-released", "authors", "keywords"]
+
+[tool.cff-from-621.static]
+date-released = "2022-09-18"
+message = "If you use this software, please cite it as below."
+
+[tool.setuptools.dynamic]
+version = {attr = "cff_from_621.version.VERSION"}
diff --git a/tests/test_readdata.py b/tests/test_readdata.py
index 93f4563..50cd02a 100644
--- a/tests/test_readdata.py
+++ b/tests/test_readdata.py
@@ -6,11 +6,12 @@
 import pymurtree.lib as lib
 import pprint
 
+TRAIN_DATA = "./tests/fixtures/test_dataset.txt"
 
 @pytest.fixture
 def dl_from_file() -> np.ndarray:
     ''' Read data from DL formatted file and return as numpy array'''
-    x, y = read_from_file("_no_anneal.txt")
+    x, y = read_from_file(TRAIN_DATA)
     x = x.to_numpy()
     y = y.to_numpy()
     return np.concatenate((y.reshape(-1,1), x), axis=1).astype(np.int32)
@@ -19,7 +20,7 @@ def dl_from_file() -> np.ndarray:
 def dl_x_y() -> tuple:
     ''' Read data from DL formatted file and return as tuple with two numpy arrays 
     (x, y) where x is the feature vectors and y is the labels'''
-    x, y = read_from_file("_no_anneal.txt")
+    x, y = read_from_file(TRAIN_DATA)
     return x, y
 
 @pytest.fixture
@@ -33,7 +34,7 @@ def dl_data_sample() -> np.ndarray:
 
 # test that data read is correct
 def test_read_from_file():
-    x, y = read_from_file("_no_anneal.txt")
+    x, y = read_from_file(TRAIN_DATA)
     assert x is not None
     assert y is not None
     assert type(x) == pd.core.frame.DataFrame
@@ -63,7 +64,7 @@ def test_nparray_to_feature_vectors(dl_data_sample):
 
 def test_compare_feature_vectors(dl_from_file):
     ''' Test that we get exactly the same feature vectors from the file and from the numpy array'''
-    feature_vectors_from_file = lib._read_data_dl("_no_anneal.txt", 1)
+    feature_vectors_from_file = lib._read_data_dl(TRAIN_DATA, 1)
     assert feature_vectors_from_file is not None
     assert type(feature_vectors_from_file) == list
     assert type(feature_vectors_from_file[0]== lib.FeatureVectorBinary)