Update web.py

web.py

@@ -586,9 +586,12 @@ def web_data():
         P("""
         In this section, we introduce all the quality signals that we have used to filter out low-quality documents.
         Overview of all the quality signals that are used for filtering."""),
-        DVS(
-            json.load(open("data/all_signals.json")),
-            "Overview of all the quality signals that are used for filtering",
+        Details(
+            Summary("Overview of all the quality signals that are used for filtering"),
+            DVS(
+                json.load(open("data/all_signals.json")),
+                "Overview of all the quality signals that are used for filtering",
+            ),
         ),
         P("""Similar to previous sections, we will present sample documents filtered out by the given quality signals. 
         Most of these quality signals were initially introduced by Gopher [2] and subsequently adopted by later 
@@ -636,10 +639,13 @@ def web_data():
         ensures consistency with the overall document character count calculation.
         """),
         H5("Our Implementation"),
-        DV(
-            "data/repeat_line_frac.jsonl",
-            0,
-            "Sample documents filtered by excessive line repetitions / characters in repeated lines",
+        Details(
+            Summary("Sample documents filtered by excessive line repetitions / characters in repeated lines"),
+            DV(
+                "data/repeat_line_frac.jsonl",
+                0,
+                "Sample documents filtered by excessive line repetitions / characters in repeated lines",
+            ),
         ),
         H5("3.1.2 Fraction of Characters in the Most Common N-grams (n=2,3,4)"),
         P("""
@@ -663,10 +669,13 @@ def web_data():
         only once — tend to be short.
         """),
         H5("Our Implementations"),
-        DV(
-            "data/sample_top_ngram.json",
-            0,
-            "Sample documents filtered by the fraction of characters in the most common n-grams (n=2,3,4)",
+        Details(
+            Summary("Sample documents filtered by the fraction of characters in the most common n-grams (n=2,3,4)"),
+            DV(
+                "data/sample_top_ngram.json",
+                0,
+                "Sample documents filtered by the fraction of characters in the most common n-grams (n=2,3,4)",
+            ),
         ),
         H5("3.1.3 Fraction of Characters in Duplicated N-grams (n=5,...,10)"),
         P("""
@@ -710,10 +719,13 @@ def web_data():
         works ([2], [3], [6]), we remove the documents if more than 30% of the lines end with an ellipsis or more than 
         90% of lines start with a bullet point.
         """),
-        DV(
-            "data/line_info.json",
-            0,
-            "Sample documents that are filtered out by line-wise heuristics",
+        Details(
+            Summary("Sample documents that are filtered out by line-wise heuristics"),
+            DV(
+                "data/line_info.json",
+                0,
+                "Sample documents that are filtered out by line-wise heuristics",
+            ),
         ),
         H4("3.3 Statistics-based Heuristics"),
         P("""
@@ -806,7 +818,11 @@ def web_data():
         Following C4, we remove any page where the phrase “lorem ipsum” appeared since some pages had placeholder “lorem ipsum” 
         text.
         """),
-        DV("data/lorem_ipsum.json", 0, "Sample documents containing 'lorem ipsum"),
+        
+        Details(
+            Summary("Sample documents containing 'lorem ipsum'"),
+            DV("data/lorem_ipsum.json", 0, "Sample documents containing 'lorem ipsum'"),
+        ),
         H3("4. Deduplication"),
         P("..."),  # Add detailed content and images as needed
         H3("5. PII Removal"),