diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml
index c88b26f..2d8a3ef 100644
--- a/.github/workflows/docs.yml
+++ b/.github/workflows/docs.yml
@@ -3,7 +3,6 @@ on:
   push:
     branches:
       - main
-      - tests
 
 jobs:
   build:
diff --git a/.github/workflows/pytest-multiversion.yml b/.github/workflows/pytest-multiversion.yml
index a9d24ef..9b0779f 100644
--- a/.github/workflows/pytest-multiversion.yml
+++ b/.github/workflows/pytest-multiversion.yml
@@ -36,3 +36,4 @@ jobs:
       - name: Test with pytest
         run: |
           pytest -v --alluredir=allure_results  --cov-report=html --cov  --cov-config=.coveragerc --random-order
+          coverage report -m
diff --git a/README.md b/README.md
index 4bb0d11..3a9e52b 100644
--- a/README.md
+++ b/README.md
@@ -109,7 +109,7 @@ The dataset is tabular, where each row corresponds to a labelled MS2 spectra.
   The intensity values of the MS2 spectrum
 
 For example, the DataFrame for the
-[Nine-Species excluding Yeast](https://huggingface.co/datasets/InstaDeepAI/instanovo_ninespecies_exclude_yeast)
+[Nine-Species excluding Yeast](https://huggingface.co/datasets/InstaDeepAI/ms_ninespecies_benchmark)
 dataset look as follows:
 
 |     | sequence             | modified_sequence          | precursor_mz | precursor_charge | mz_array                             | intensity_array                     |
diff --git a/notebooks/getting_started_with_instanovo.ipynb b/notebooks/getting_started_with_instanovo.ipynb
index c6f560c..f0556c1 100644
--- a/notebooks/getting_started_with_instanovo.ipynb
+++ b/notebooks/getting_started_with_instanovo.ipynb
@@ -317,10 +317,10 @@
     "from datasets import load_dataset\n",
     "\n",
     "# Only evaluate on a subset of the data for demo\n",
-    "dataset = load_dataset(\"InstaDeepAI/instanovo_ninespecies_exclude_yeast\", split=\"test[:10%]\")\n",
+    "dataset = load_dataset(\"InstaDeepAI/ms_ninespecies_benchmark\", split=\"test[:10%]\")\n",
     "\n",
     "# Otherwise evaluate on the full test set\n",
-    "# dataset = load_dataset(\"InstaDeepAI/instanovo_ninespecies_exclude_yeast\", split=\"test\")"
+    "# dataset = load_dataset(\"InstaDeepAI/ms_ninespecies_benchmark\", split=\"test\")"
    ]
   },
   {
diff --git a/requirements-docs.txt b/requirements-docs.txt
index 4ee1125..2638393 100644
--- a/requirements-docs.txt
+++ b/requirements-docs.txt
@@ -7,4 +7,4 @@ mkdocs-material==8.5.6
 mkdocs-pymdownx-material-extras==2.2.1
 mkdocstrings==0.23.0
 mkdocstrings-python==1.7.1
-pymdown-extensions==9.5
+pymdown-extensions==10.7
diff --git a/tests/conftest.py b/tests/conftest.py
index 7461d40..157bf58 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -52,7 +52,7 @@ def dataset() -> DatasetDict | Dataset | IterableDatasetDict | IterableDataset:
 
     Loads a specific subset (1% of test data) from the 'instanovo_ninespecies_exclude_yeast' dataset.
     """
-    return load_dataset("InstaDeepAI/instanovo_ninespecies_exclude_yeast", split="test[:1%]")
+    return load_dataset("InstaDeepAI/ms_ninespecies_benchmark", split="test[:1%]")
 
 
 @pytest.fixture(scope="session")