feat(ocr-pipeline): generic sub-column detection via left-edge clustering

Detects hidden sub-columns (e.g. page references like "p.59") within
already-recognized columns by clustering word left-edge positions and
splitting when a clear minority cluster exists. The sub-column is then
classified as page_ref and mapped to VocabRow.source_page.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

klausur-service/backend/ocr_pipeline_api.py

@@ -34,6 +34,7 @@ from cv_vocab_pipeline import (
     PageRegion,
     RowGeometry,
     _cells_to_vocab_entries,
+    _detect_sub_columns,
     _fix_character_confusion,
     _fix_phonetic_brackets,
     analyze_layout,
@@ -698,6 +699,9 @@ async def detect_columns(session_id: str):
         cached["_inv"] = inv
         cached["_content_bounds"] = (left_x, right_x, top_y, bottom_y)
 
+        # Split sub-columns (e.g. page references) before classification
+        geometries = _detect_sub_columns(geometries, content_w)
+
         # Phase B: Content-based classification
         regions = classify_column_types(geometries, content_w, top_y, w, h, bottom_y,
                                         left_x=left_x, right_x=right_x, inv=inv)