diff --git a/.gitattributes b/.gitattributes
index fe9261903f4a8e55309c3386b6160b8bb5e940b3..247f1580e794b71961ff356842c4ae76037183a7 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -76,3 +76,4 @@ data/AB/1927/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1928/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1929/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1930/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1931/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/5ee9e6a8bf674cc59b5f53a7a8e938fb_python.cwl b/.renku/workflow/5ee9e6a8bf674cc59b5f53a7a8e938fb_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..0c80bcdd98dd9fc3b73e736b1c8484e89364bee6
--- /dev/null
+++ b/.renku/workflow/5ee9e6a8bf674cc59b5f53a7a8e938fb_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/1931/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1931/02_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/1931
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1931/02_extractedxml.tar.gz b/data/AB/1931/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..57e609d568382595b5ea12188f92213ec3e1e099
--- /dev/null
+++ b/data/AB/1931/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e86d044006f4280b5860ee4bd3646482cbf8aa6c1868689b5744e96f6ea7f746
+size 142863849