diff --git a/.renku/workflow/572b352aac8342238f62f172b9b96f9a_python.cwl b/.renku/workflow/572b352aac8342238f62f172b9b96f9a_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..6fe0cfc6d2cc6537ab845e3a869a6f181fd8e6c3
--- /dev/null
+++ b/.renku/workflow/572b352aac8342238f62f172b9b96f9a_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/1891/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1891/02_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/1891
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1891/02_extractedxml.tar.gz b/data/AB/1891/02_extractedxml.tar.gz
index 6e68262b753d30ac54486b1d51f8f21b34f6d3d6..dd7f1684761481bd147561081d0c2724169921af 100644
--- a/data/AB/1891/02_extractedxml.tar.gz
+++ b/data/AB/1891/02_extractedxml.tar.gz
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408b299adff3e39a3d195b486f89c8bfcf6a85ffb91a30256d559cd79b599b8b
-size 43120412
+oid sha256:fd9042dfedfd5e82f5a6ff6d17c5ab31d746d9c4018b67dd6458b96012695c87
+size 43120439
diff --git a/data/AB/1891/04_correctedxml.tar.gz b/data/AB/1891/04_correctedxml.tar.gz
deleted file mode 100644
index 3bf8c314dd94387e7078c2ef088b7acae8769166..0000000000000000000000000000000000000000
--- a/data/AB/1891/04_correctedxml.tar.gz
+++ /dev/null
@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d4649a2d5931b9a944269ea1bfebb3da538e44cceea3b8f3e839d460950ac8b2
-size 3416246