diff --git a/.gitattributes b/.gitattributes
index 65d8007b6e5a18631b0fd1e884419a64ac7aa6eb..827d5a74dda8829709849c7b54a85e6a51cb39d1 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -43,3 +43,4 @@ 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
 data/AB/1924/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1925/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/02ae7a6879d64c20af68c51d6cb0606e_python.cwl b/.renku/workflow/02ae7a6879d64c20af68c51d6cb0606e_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..05054bf40c1e7b6a3703aa1d434373e217e333c1
--- /dev/null
+++ b/.renku/workflow/02ae7a6879d64c20af68c51d6cb0606e_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/1925/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1925/02_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/1925
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1925/02_extractedxml.tar.gz b/data/AB/1925/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..fe2eb88e55bdc57c0b162bb2a6a724b6155f0ea4
--- /dev/null
+++ b/data/AB/1925/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db28abcad77affde42912bc2b4cc043d2e2d2ef2702e09a1324c393477bc60a
+size 1213921280