Update app.py

add arxiv link

app.py

@@ -36,7 +36,7 @@ st.markdown(
 )
 
 st.markdown(
-    "We are excited to share the BenchBench-Leaderboard, a crucial component of our comprehensive research on Benchmark Agreement Testing (BAT) [work](#). "
+    "We are excited to share the BenchBench-Leaderboard, a crucial component of our comprehensive research on Benchmark Agreement Testing (BAT) [work](https://arxiv.org/abs/2407.13696) -- Benchmark Agreement Testing Done Right: A Guide for LLM Benchmark Evaluation."
     "This leaderboard is a meta-benchmark that ranks benchmarks based on their agreement with the crowd harnessing many different references. "
 )