diff --git a/.gitattributes b/.gitattributes
index db26be0e8dba3dafdc3f5913526784fa3f73056c..d3267ce8186a0b0ce72a795bbd7f70e82bfd7cd7 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -34,3 +34,4 @@ data/AB/1919/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1920/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1921/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1922/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1923/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/2bb430f219a7477582cd38750b16344c_python.cwl b/.renku/workflow/2bb430f219a7477582cd38750b16344c_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..1fc741bb103b9fd57878a6f60275a358397bd5da
--- /dev/null
+++ b/.renku/workflow/2bb430f219a7477582cd38750b16344c_python.cwl
@@ -0,0 +1,51 @@
+arguments: []
+baseCommand:
+- python
+class: CommandLineTool
+cwlVersion: v1.0
+hints: []
+inputs:
+  input_1:
+    default:
+      class: File
+      path: ../../src/python/run_extract_origxml.py
+    inputBinding:
+      position: 1
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_2:
+    default:
+      class: File
+      path: ../../data/AB/1923/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1923/02_extractedxml.tar.gz
+    inputBinding:
+      position: 3
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: string
+outputs:
+  output_0:
+    outputBinding:
+      glob: $(inputs.input_3)
+    streamable: false
+    type: File
+permanentFailCodes: []
+requirements:
+- class: InlineJavascriptRequirement
+- class: InitialWorkDirRequirement
+  listing:
+  - entry: '$({"listing": [], "class": "Directory"})'
+    entryname: data/AB/1923
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1923/02_extractedxml.tar.gz b/data/AB/1923/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..adb5a50db1c4be1b8128fa39b59b45a40d728ed5
--- /dev/null
+++ b/data/AB/1923/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162cc67bed999e657ed6f216dcfd3f483b3de2aad8e6e5f3ddc19d8949cadeda
+size 97677744