diff --git a/.gitattributes b/.gitattributes
index 1c4795fcf8171d3abefcc624c99388154c84296d..da3927a5b29a0d6c4235a06a17477b3a7c6c355f 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -82,3 +82,4 @@ data/AB/1933/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1934/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1935/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1936/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1937/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/b906608633a3431aabcedc5614bd7be7_python.cwl b/.renku/workflow/b906608633a3431aabcedc5614bd7be7_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..2fcb2ba4a6c9b113cd6e4b94abe7b93eafd58f62
--- /dev/null
+++ b/.renku/workflow/b906608633a3431aabcedc5614bd7be7_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/1937/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1937/02_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/1937
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1937/02_extractedxml.tar.gz b/data/AB/1937/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..4f0eb287c0fb5f71b82c1fea18c2533d1d8875d6
--- /dev/null
+++ b/data/AB/1937/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20f6575338eac2068ae03c61d764c27cca332b255804312d343b5a7c969b7a30
+size 121153203