diff --git a/.gitattributes b/.gitattributes
index 7804cdab1b447d890c26d857350661400231a039..7860d90b2ddd4d614c55351fd9f5744e23a36d5f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -347,3 +347,4 @@ data/AB/1980/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1982/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1983/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1981/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1984/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/f75d45ee43ef402d91dac3367b79acfd_python.cwl b/.renku/workflow/f75d45ee43ef402d91dac3367b79acfd_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..0f70f7705c065af297add17d423ea08b8f9dbe22
--- /dev/null
+++ b/.renku/workflow/f75d45ee43ef402d91dac3367b79acfd_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/1984/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1984/02_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/1984
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1984/02_extractedxml.tar.gz b/data/AB/1984/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..deb4f57668a3c1e9a720673bf63ff6bd3f1b97d8
--- /dev/null
+++ b/data/AB/1984/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a718ccef43bc1125b072b2a92dc58bccedfb3b029dfca09b38a09a131285bbc5
+size 321043084