v26

app.py

@@ -575,7 +575,7 @@ with gr.Blocks(title="Leaderboard QA Judge", theme=gr.themes.Soft()) as app:
 # 🏆 Assignment 2 Public Leaderboard
 
 We compute multiple metrics:
-- **Standard metrics:** Answer Recall, F1 (token-level), and ROUGE-1/2/L (reported as an average)
+- **Standard metrics:** Answer Recall, F1, and ROUGE-1/2/L (reported as an average)
 - **LLM-as-judge:** rubric-based score (1–5)
 
 **Total score** is the uniform mean of the available normalized metrics (0–1).
@@ -592,16 +592,18 @@ We compute multiple metrics:
 ```
 
 **Important:** Your submission must include answers for ALL questions in the dataset. The number of answers must exactly match the number of questions in the gold dataset.
+
+**Please don't refresh or redirect the page during evaluation. It may take sometime to finish.**
 """
     )
 
     with gr.Tabs():
         with gr.Tab("📤 Submit"):
-            file_input = gr.File(label="Upload submission.json", file_types=[".json"])
+            file_input = gr.File(label="Upload submission in json", file_types=[".json"])
             submit_btn = gr.Button("🚀 Submit & Evaluate", variant="primary")
             status = gr.Textbox(label="Result", lines=10, interactive=False)
 
-            gr.Markdown("### Sample submission.json")
+            gr.Markdown("### Sample submission")
             sample = gr.Textbox(value=sample_submission_text(), lines=6)
 
         with gr.Tab("🏅 Leaderboard"):