Update

app.py

@@ -51,6 +51,7 @@ bug_id_by_cat = {
     "hang": [],
 }
 bug_id_to_comp = dict()
+bug_id_to_title = dict()
 comp_bug_count = dict()
 for issue in dataset["test"]:
     bug_id_to_time[issue["bug_id"]] = pd.to_datetime(issue["knowledge_cutoff"])
@@ -59,6 +60,7 @@ for issue in dataset["test"]:
     bug_id_to_comp[issue["bug_id"]] = issue["hints"]["components"]
     for comp in issue["hints"]["components"]:
         comp_bug_count[comp] = comp_bug_count.get(comp, 0) + 1
+    bug_id_to_title[issue["bug_id"]] = "Issue " + issue["bug_id"] + ": " + issue["issue"]["title"]
 timeline_xs = []
 timeline_ys = []
 timeline_cols = []
@@ -205,7 +207,8 @@ with demo:
             gr.Dataframe(fixed_by_cat_df)
             gr.Dataframe(fixed_by_comp_df)
             gr.Dataframe(unique_bugs_df)
-            gr.Dropdown(list(fixed_bug_ids), label="Issue ID", interactive=True)
+            fixed_bug_title_id_pairs = [(bug_id_to_title[bug_id], bug_id) for bug_id in sorted(fixed_bug_ids)]
+            gr.Dropdown(fixed_bug_title_id_pairs, label="Issue ID", interactive=True)
 
         with gr.TabItem("🚀 Submission", elem_id="llm-benchmark-tab-table", id=1):
             gr.Markdown(EVALUATION_QUEUE_TEXT, elem_classes="markdown-text")