diff --git a/.gitattributes b/.gitattributes
index 1723186a06b5fc2a2badaf1300cc66aa36c95e2e..213696d2e3bfed163e0bbe2e8516489193cb5a43 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -120,3 +120,4 @@ data/AB/1953/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1954/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1955/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
 data/AB/1956/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
+data/AB/1957/02_extractedxml.tar.gz filter=lfs diff=lfs merge=lfs -text
diff --git a/.renku/workflow/899c1f250e114d49bd45a4540717de0d_python.cwl b/.renku/workflow/899c1f250e114d49bd45a4540717de0d_python.cwl
new file mode 100644
index 0000000000000000000000000000000000000000..241fcbe0bed4b0d52b2856051e49ce326e7d55fb
--- /dev/null
+++ b/.renku/workflow/899c1f250e114d49bd45a4540717de0d_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/1957/00_rawpdfs.tar.gz
+    inputBinding:
+      position: 2
+      separate: true
+      shellQuote: true
+    streamable: false
+    type: File
+  input_3:
+    default: data/AB/1957/02_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/1957
+    writable: true
+successCodes: []
+temporaryFailCodes: []
diff --git a/data/AB/1957/02_extractedxml.tar.gz b/data/AB/1957/02_extractedxml.tar.gz
new file mode 100644
index 0000000000000000000000000000000000000000..902f301388116fa6f46fbedc0485ff89cb616949
--- /dev/null
+++ b/data/AB/1957/02_extractedxml.tar.gz
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7132b687005178dde3c4fcf4c6cc27ddebf57f672db26f1bc0160cfbd1448374
+size 136878287