Release data split manifests

2026-06-01 16:02:14 +00:00
parent 8ebede0efd
commit 181d71b737
29 changed files with 13545 additions and 4 deletions
@@ -0,0 +1,27 @@
+{
+  "benchmark": "OfficeQA",
+  "manifest_type": "id_split",
+  "source_repo": "databricks/officeqa",
+  "source_repo_type": "dataset",
+  "source_url": "https://huggingface.co/datasets/databricks/officeqa",
+  "source_revision": "8ecbf18d3833daf4750a903d14963e4c4c1d4cd8",
+  "source_file": "officeqa_full.csv",
+  "source_split_name": "officeqa_split",
+  "counts": {
+    "train": 50,
+    "val": 24,
+    "test": 172
+  },
+  "item_fields": [
+    "id",
+    "uid",
+    "category",
+    "source_files",
+    "source_docs",
+    "source_split"
+  ],
+  "notes": [
+    "This is a split manifest, not the full OfficeQA payload.",
+    "The official OfficeQA CSV is gated on Hugging Face; materialization requires authorized access."
+  ]
+}