diff --git a/.gitattributes b/.gitattributes
index a9f15a0e1b841a0d7bce0f46a2d0f604d8cb22a8..b16ef73d2fa19136ef75fa28ef132cb7d4b2d6c2 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -71,3 +71,4 @@ data/AB/1922/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1923/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1924/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1925/04_correctedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1926/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/306247fa6b0c43fd9b5cb3ade59ddb74_python.cwl b/.renku/workflow/306247fa6b0c43fd9b5cb3ade59ddb74_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..01fbf6d9e657d644451023d0f7996c4c783a2067
--- /dev/null
+++ b/.renku/workflow/306247fa6b0c43fd9b5cb3ade59ddb74_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/1926/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1926/02_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/1926
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1926/02_extractedxml.tar.gz b/data/AB/1926/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..d9e7746171104a259c228b7e6674f64eea448500
--- /dev/null
+++ b/data/AB/1926/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e0f9a859b3493b8c6e9ab01d68667bcb415179fb4c13b0f31c0a6c9945a8a0
+size 109927116