diff --git a/.gitattributes b/.gitattributes
index a1ffcba401875e2e9f1bdf0831442fb0e5c1cdf5..4d308d941d5c2ac00bb09fa5c25a644a9ccd94ff 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -130,3 +130,4 @@ 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
 data/AB/1966/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1967/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/dd3cbb773a4c485489c52abdecb3c5c4_python.cwl b/.renku/workflow/dd3cbb773a4c485489c52abdecb3c5c4_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..7041691ff2211535a665dbbfc8ace618baaf909f
--- /dev/null
+++ b/.renku/workflow/dd3cbb773a4c485489c52abdecb3c5c4_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/1967/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1967/02_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/1967
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1967/02_extractedxml.tar.gz b/data/AB/1967/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5bc52b588be1043164ad43c5aa8ef19291cc1c6d
--- /dev/null
+++ b/data/AB/1967/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322560dfe7c2bc064ffeff7b778114d897e65f16d06a8efcacb2df82adaef79f
+size 113579365