Update curated.py

curated.py

@@ -680,20 +680,17 @@ filtering_process = Div(
         P(B("Download and Extraction: "), "Original PDF files download from", A("https://philarchive.org/oai.pl", href="https://philarchive.org/oai.pl"), ". All available PDF's were downloaded. Each PDF was converted to text using java", D_code("-jar ../philpapers_resources/src/pdfbox-app-2.0.21.jar ExtractText {f0} {FOUT.name}", language="java"), ". After converting to text formatting, a language was detected and added using the langdetect (citation needed) library."),
         H4("Filtering"),
         Ul(
-            Li(P(B("Hyphenation Removal:"), D_code("end-of", style="inline", language="python"), " becomes ", D_code("end of", language="python"))),
-            Li(P(B("Newline Filtering"), "")),
-            Li(P(B("Header/Footer Filtering"), "")),
-            Li(P(B("Double Whitespace Filtering"), "")),
-            Li(P(B("Mean Line Length Check"), "")),
-            Li(P(B("CID Percentage Filter "), "")),
-            Li(P(B("Letterness Filter"), "")),
-            Li(P(B("Removing Leading/Trailing Numbers"), "")),
-            Li(P(B("Fixing Unicode Issues"), "")),
-            Li(P(B("Combining Diacritics Correction"), "")),
-            Li(P(B("Unigram Log Probability"), "")),
-            Li(""),
-            
-            
+            Li(P(B("Hyphenation Removal:"), D_code("end-of", language="python"), " becomes ", D_code("end of", language="python"))),
+            Li(P(B("Newline Filtering:"), D_code("This is/na sentence.", language="python"), " becomes ", D_code("This is a sentence.", language="python")))),
+            Li(P(B("Header/Footer Filtering:"), D_code("(c) 2023 Company Name.", language="python"), " is removed ",))),
+            Li(P(B("Double Whitespace Filtering:"), D_code("This  is  a  test.", language="python"), " becomes ", D_code("This is a test.", language="python")))),
+            Li(P(B("Mean Line Length Check: "), "removes paragraphs with an average line length of < 2.0")),
+            Li(P(B("CID Percentage Filter: "), "removes LaTex heavy paragraphs that contain over 10% “CID” font artifacts.")),
+            Li(P(B("Letterness Filter: "), "discards paragraphs with a low proportion of letters")),
+            Li(P(B("Removing Leading/Trailing Numbers: "), "removes numbers at the start or end of paragraphs. ", D_code("1 This is a sentence.", language="python"), " becomes ", D_code("This is a sentence.", language="python")))),
+            Li(P(B("Fixing Unicode Issues: "), "fixes Unicode issues.",)),
+            Li(P(B("Combining Diacritics Correction: "), D_code("a'", language="python"), " becomes ", D_code("å", language="python")))),
+            Li(P(B("Unigram Log Probability: "), "the document must have higher than -20 average unigram log probability.")),
         ),
         table_div_phil,
         Details(