Exclude date-labeled values from numeric identifier fallbacks
Numeric identifier formats often overlap compact dates, so a regex match cannot be accepted without local semantic context. Before adding a format-valid identifier candidate, classify it by the nearest preceding field label in the same OCR token or segment. Reject candidates governed by birth, issue, or expiry labels; allow a candidate after an explicit identifier label even when a later date field shares the token. Keep uniqueness and confidence checks as separate gates. This prevents date values from overwriting valid identifiers without discarding dense OCR lines.
Applies when: OCR emits multiple labeled fields in one token or merged text line. Keywords: OCR parser numeric identifier compact date semantic label context