Update web.py

web.py

@@ -450,10 +450,11 @@ def web_data():
         ),
         
         #DV("data/sample_non_en.json", 3, "Sample documents that are classified as non-English"),
-            
-        
-        DV("data/sample_en_low.json", 3, "Sample documents that are classified as English but with score less than 0.65"),
-             
+
+        Details(
+            Summary("English Documents Scoring Lower than 0.65"),
+            DV("data/sample_en_low.json", 3, "Sample documents that are classified as English but with score less than 0.65"),
+        ),
         
         H4("1.3 URL Filtering"),
         P("""
@@ -466,12 +467,18 @@ def web_data():
         articles, sex education, technical blogs, etc. Specifically, we randomly took 903M URLs and matched them with
         4.6M domain names in the UT1 blocklist. 24 URL domains were detected with more than 4k matches, which are shown below.
         """),
+
+        Details(
+            Summary("24 URL domains with more than 4k matches"),
+            DVS(urls_high_matches, "24 URL domains with more than 4k matches"),
+        ),
         
-        DVS(urls_high_matches, "24 URL domains with more than 4k matches"),
         P("""
         We manually removed the following 6 domains from the UT1 blocklist so that they will not be removed from our dataset.
         """),
+        
         DVS(urls_false_positives, "6 url domains that are removed from the blocklist"),
+        
         DV(
             "data/bad_url_doc.jsonl",
             3,