diff --git a/CHANGELOG.md b/CHANGELOG.md
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,11 @@
 # Changelog
 
+## 0.4.6.2 (2026-07-06)
+
+### Fixed
+
+- Legacy extraction (and the TUI viewer, which uses the same path) no longer inserts U+FFFD before each character for Type0 Identity-H fonts whose `/CIDSystemInfo` ordering is not `Adobe-Japan1` (e.g. Kozuka Mincho in scanned CACM papers); hex CID strings are now split as 2-byte codes consistently with the geometry pipeline.
+
 ## 0.4.6.1 (2026-07-06)
 
 ### Fixed
diff --git a/hpdft.cabal b/hpdft.cabal
--- a/hpdft.cabal
+++ b/hpdft.cabal
@@ -1,6 +1,6 @@
 cabal-version:       3.8
 name:                hpdft
-version:             0.4.6.1
+version:             0.4.6.2
 synopsis:            PDF parsing library and CLI for text, layout, diff, images, and forms
 description:
     hpdft is a Haskell library and command-line tool for parsing PDF files.
diff --git a/src/PDF/DocumentStructure.hs b/src/PDF/DocumentStructure.hs
--- a/src/PDF/DocumentStructure.hs
+++ b/src/PDF/DocumentStructure.hs
@@ -789,9 +789,7 @@
                        Just (PdfText o) -> o
                        _ -> T.empty
           cmap = registry `T.append` "-" `T.append` ordering
-      in if cmap == "Adobe-Japan1"
-         then CIDmap cmap
-         else WithCharSet T.empty
+      in CIDmap cmap
 
 
 charDiff :: [Obj] -> Encoding