updates

app.py

@@ -59,7 +59,7 @@ with gr.Blocks() as demo:
         """
         <div style="text-align: center;">
             <h1 style="font-size: 2.5rem; margin-bottom: 0.5rem;">TAG Leaderboard</h1>
-            <p style="font-size: 1.25rem; color: gray;">Evaluating complex natural language queries over structured data.</p>
+            <p style="font-size: 1.25rem; color: gray;">Evaluating complex natural language queries over data.</p>
         </div>
         """
     )

src/about.py

@@ -35,6 +35,19 @@ In this leaderboard, you'll find execution accuracy comparisons of table questio
 
 ## How is accuracy measured?
 Execution accuracy is measured as the number of exact matches to our annotated ground truth answers which are hand-labeled by experts.
+
+## Citation
+```
+@misc{{biswal2024text2sqlenoughunifyingai,
+      title={{Text2SQL is Not Enough: Unifying AI and Databases with TAG}}, 
+      author={{Asim Biswal and Liana Patel and Siddarth Jha and Amog Kamsetty and Shu Liu and Joseph E. Gonzalez and Carlos Guestrin and Matei Zaharia}},
+      year={2024},
+      eprint={2408.14717},
+      archivePrefix={{arXiv}},
+      primaryClass={{cs.DB}},
+      url={{https://arxiv.org/abs/2408.14717}}, 
+}}
+```
 """
 
 EVALUATION_QUEUE_TEXT = """