diff --git a/.gitattributes b/.gitattributes
index d1a64ff6399c7344ec1375e963aed34d0fe4181c..cefbd8bac3783784e047290ac11423ed7990d3aa 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -128,3 +128,4 @@ data/AB/1961/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1962/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1963/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1964/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1965/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/d9b9e759effb467eb6e056c12058984e_python.cwl b/.renku/workflow/d9b9e759effb467eb6e056c12058984e_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..5b0df40177a3b64b7cd987e2f1db907cbe053bb4
--- /dev/null
+++ b/.renku/workflow/d9b9e759effb467eb6e056c12058984e_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/1965/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1965/02_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/1965
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1965/02_extractedxml.tar.gz b/data/AB/1965/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..769b94b784c78a4512bc55a42b72454cd5907cc5
--- /dev/null
+++ b/data/AB/1965/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0645badbd54d80849a60aa78be7f18b1e6907b7d29a7221121c4b078acdfa822
+size 133728236