diff --git a/.gitattributes b/.gitattributes
index 165eff579c67dd2ba185bfd74e81e8f21c4d5346..f0a573de837769b9060e31e19242272fc65b8ce2 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -116,3 +116,4 @@ src/python/def_classes.py filter=lfs diff=lfs merge=lfs -text
 data/AB/1940/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1951/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1952/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1953/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/a9098add4f884cb3a0b5b3e04b252027_python.cwl b/.renku/workflow/a9098add4f884cb3a0b5b3e04b252027_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..ee22dfd48fc058af7426914a0b398cea838b2baf
--- /dev/null
+++ b/.renku/workflow/a9098add4f884cb3a0b5b3e04b252027_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/1953/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1953/02_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/1953
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1953/02_extractedxml.tar.gz b/data/AB/1953/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..a364fd20a43d415201754d4edd85ea0904f32843
--- /dev/null
+++ b/data/AB/1953/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03d02e1e02bd9459605136e3efce15e4102c94fcd24ee86ba468843c2be2a74
+size 105808890