diff --git a/.gitattributes b/.gitattributes
index 22defad496d8ab2699b076cbebc5ef4d9559bae7..dad265d404ce830b6f11e6afdf22406c7ca5626f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -125,3 +125,4 @@ data/AB/1958/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1959/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1960/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 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
diff --git a/.renku/workflow/444d11c9acc146a98fad7d6b4644866d_python.cwl b/.renku/workflow/444d11c9acc146a98fad7d6b4644866d_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..8791eb60040f1ad169d1645bbfc3b61a49cc3368
--- /dev/null
+++ b/.renku/workflow/444d11c9acc146a98fad7d6b4644866d_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/1962/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1962/02_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/1962
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1962/02_extractedxml.tar.gz b/data/AB/1962/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..235ed6846591c906ff909bfa0124351182a30f7c
--- /dev/null
+++ b/data/AB/1962/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc5c332d5fa16fdc141d6b2b3872f65124ba47cc212ff2b37c1bb41de8c289b
+size 114122328