Update curated.py

curated.py

@@ -571,6 +571,28 @@ phil_examples = Div(
     ),
 )
 
+def get_arx_data(data_source: str = "Arxiv", doc_id: int = 3, target: str = "foo"):
+    doc_id = max(0, min(int(doc_id), 9))
+
+    if data_source == "Arxiv":
+        raw_sample_doc = json.load(open("data/curated_samples/arxiv_raw.json"))
+        extracted_sample_doc = json.load(
+            open("data/curated_samples/arxiv_extract.json")
+        )
+    else:
+        raw_sample_doc = extracted_sample_doc = [{} for _ in range(10)]
+
+    raw_json = raw_sample_doc[doc_id]
+    extracted_json = extracted_sample_doc[doc_id]
+    return view_data(
+        raw_json,
+        extracted_json,
+        doc_id=doc_id,
+        data_source="Arxiv",
+        data_sources="Arxiv",
+        target=target,
+    )
+
 arx_examples = Div(
     Div(
         get_arx_data(target=gen_random_id()),