diff --git a/.gitattributes b/.gitattributes
index 5259e5c7e355d3d7bdc0a52825f00753d6994517..9d4c94087dc14c1ae6091bfba957864786b1cb81 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -5,3 +5,4 @@ data/AB/1893/03_correctedmeta.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1891/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1892/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1893/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1894/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/4cf159cef6f948fba8b9972c0c573938_python.cwl b/.renku/workflow/4cf159cef6f948fba8b9972c0c573938_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..35455e33e26e78375c044b58a6de06b9e5c519cf
--- /dev/null
+++ b/.renku/workflow/4cf159cef6f948fba8b9972c0c573938_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/1894/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1894/02_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/1894
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1894/02_extractedxml.tar.gz b/data/AB/1894/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..5a1d7b4670a407c361e688b005d2268836b7b705
--- /dev/null
+++ b/data/AB/1894/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18403d8f232df02cffabc2e850c4be1605cea632cd7fdf04fadb975d50bdb5a
+size 44175955