Reject overlapping SearchQA manifest ids

Runnable SearchQA splits should remain disjoint. A duplicate manifest id across train, val, or test previously collapsed into the wanted-id set and reused the same row in multiple output splits without warning.

Constraint: Preserve manifest order and output schema for valid manifests.

Rejected: Deduplicate automatically | hiding split overlap would make evaluation contamination harder to notice.

Confidence: high

Scope-risk: narrow

Reversibility: clean

Directive: Fail fast on split-manifest integrity problems instead of repairing them silently.

Tested: uv run --with pytest pytest tests/test_materialize_searchqa.py -q

Tested: uv run --with ruff ruff check scripts/materialize_searchqa.py tests/test_materialize_searchqa.py

Not-tested: Loading the live Hugging Face dataset.

scripts/materialize_searchqa.py

@@ -44,6 +44,27 @@ def load_manifest_ids(manifest_dir: Path) -> dict[str, list[str]]:
     return split_ids
 
 
+def _reject_duplicate_manifest_ids(split_ids: Mapping[str, Iterable[str]]) -> None:
+    seen: dict[str, str] = {}
+    duplicates: dict[str, list[str]] = {}
+    for split, ids in split_ids.items():
+        for item_id in ids:
+            if item_id in seen:
+                duplicates.setdefault(item_id, [seen[item_id]]).append(split)
+            else:
+                seen[item_id] = split
+
+    if duplicates:
+        preview = ", ".join(
+            f"{item_id} ({'/'.join(splits)})"
+            for item_id, splits in sorted(duplicates.items())[:5]
+        )
+        raise ValueError(
+            "SearchQA split manifest contains duplicate IDs across splits. "
+            f"First IDs: {preview}"
+        )
+
+
 def _iter_dataset_rows(dataset: Mapping[str, Iterable[dict]]) -> Iterable[dict]:
     for source_split in dataset.values():
         yield from source_split
@@ -78,6 +99,7 @@ def materialize_searchqa_splits(
     manifest_dir = manifest_dir.resolve()
     output_dir = output_dir.resolve()
     split_ids = load_manifest_ids(manifest_dir)
+    _reject_duplicate_manifest_ids(split_ids)
     wanted_ids = {item_id for ids in split_ids.values() for item_id in ids}
 
     selected: dict[str, dict] = {}

tests/test_materialize_searchqa.py

@@ -64,3 +64,16 @@ def test_materialize_searchqa_splits_fails_on_missing_manifest_id(tmp_path):
             {"train": [_row("a")]},
             dataset_name="example/searchqa",
         )
+
+
+def test_materialize_searchqa_splits_rejects_duplicate_manifest_ids(tmp_path):
+    manifest_dir = tmp_path / "manifest"
+    _write_manifest(manifest_dir, {"train": ["a"], "val": ["a"], "test": []})
+
+    with pytest.raises(ValueError, match="duplicate IDs"):
+        materialize_searchqa_splits(
+            manifest_dir,
+            tmp_path / "out",
+            {"train": [_row("a")]},
+            dataset_name="example/searchqa",
+        )