diff --git a/.gitignore b/.gitignore
index c6d8be6..ccc9ac3 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,19 +1,14 @@
-/data/guacamol_v1*.smiles
+data/guacamol_v1*.smiles
 
-runs/
-/runs*/
+runs*/
+runs*.tar.gz
 test/test_runs/*/*.csv
 test/test_runs/*/metrics.json
 
 .vscode/
-# .idea/
-
 __pycache__
 
-/trash/
-
-/notebooks/briem_lessel_plots/BLSets*
-/settings.json
+notebooks/briem_lessel_plots/BLSets*
+settings.json
 
 **/*.egg-info
-runs*
diff --git a/README.md b/README.md
index 86e218e..ca3f975 100644
--- a/README.md
+++ b/README.md
@@ -3,7 +3,7 @@
 <a target="_blank" href="https://colab.research.google.com/github/ml-jku/diverse-hits/blob/main/example.ipynb">
   <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
 </a>
-
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.11004835.svg)](https://doi.org/10.5281/zenodo.11004835)
 
 ![graphic_abstract](https://github.com/ml-jku/diverse-hits/blob/main/notebooks/figures/graphic_abstract.png?raw=true)
 
@@ -134,6 +134,9 @@ python scripts/run_directory.py --base_dir runs/best_variance_time_nodf
 ## Visualize results
 All the plots and tables are created in jupyter notebooks in the `notebooks` folder.
 
+To reproduce figures/tables in the paper, first download the results from the [Zenodo repository](https://doi.org/10.5281/zenodo.11004835) and extract them to the `runs` folder.
+
+
 - `barplots.ipynb`: Main results as barplots + variants not in the paper.
 - `hyperparameter_table.ipynb`: Hyperparameter search spaces and selected parameters.
 - `tables_all_metrics.ipynb`: More metrics including diverse hits, novel diverse hits and internal diversity.
diff --git a/notebooks/convert.ipynb b/notebooks/convert.ipynb
deleted file mode 100644
index f172eb3..0000000
--- a/notebooks/convert.ipynb
+++ /dev/null
@@ -1,88 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "0it [00:00, ?it/s]\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "[]"
-      ]
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "import glob\n",
-    "import os\n",
-    "\n",
-    "import pandas as pd\n",
-    "from joblib import Parallel, delayed\n",
-    "from tqdm import tqdm\n",
-    "\n",
-    "files = glob.glob(\"../runs_parquet/*/*/*.csv\")\n",
-    "# get file sizes and sort by size\n",
-    "files = sorted(files, key=lambda x: os.path.getsize(x), reverse=True)\n",
-    "\n",
-    "# for fname in tqdm(files):\n",
-    "#     df = pd.read_csv(fname)\n",
-    "#     fname_parquet = fname.replace(\".csv\", \".parquet\")\n",
-    "#     df.to_parquet(fname_parquet)\n",
-    "#     os.remove(fname)\n",
-    "\n",
-    "\n",
-    "# do the above in a function so we can parallelize it\n",
-    "def convert_to_parquet(fname):\n",
-    "    df = pd.read_csv(fname)\n",
-    "    fname_parquet = fname.replace(\".csv\", \".parquet\")\n",
-    "    df.to_parquet(fname_parquet)\n",
-    "    os.remove(fname)\n",
-    "\n",
-    "\n",
-    "print(len(files))\n",
-    "\n",
-    "\n",
-    "Parallel(n_jobs=12)(delayed(convert_to_parquet)(fname) for fname in tqdm(files))"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "base",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.5"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}