update to new file ref

app.py

@@ -283,7 +283,7 @@ with demo:
         )
         gr.Markdown("### Visualization")
         gr.Markdown("This figure presents a fine-grained heatmap illustrating task-level completion across different agents. Each row corresponds to a specific agent, and each column represents a task (identified by its task ID). Blue bars indicate successful completions, while white spaces denote failures. Any agent: A task is considered successful if at least one agent is able to complete it. (This style of visualization is inspired by [HAL](https://hal.cs.princeton.edu/).)")
-        fig = plot_heatmap_with_performance_bar("./human_label_071625.json")
+        fig = plot_heatmap_with_performance_bar("./human_label_082325.json")
         gr.Plot(fig)
         gr.Markdown(EVALUATION_DETAILS)