-- 2026-05-24 PR-Chore-OCR-Column-1 (2/2): ocr_derived backfill. -- Rule R1 단독 (실측 audit 후): extract_meta ? ocr_attempted AND ocr_attempted = true → 8 rows. -- R2 (이미지 file_format) 폐기 = 1건 R1 흡수 + 1건 marker 미처리 false. -- R3 (marker PDF extract_meta 부재 283 rows) 폐기 = born-digital false positive 위험. UPDATE documents SET ocr_derived = true WHERE deleted_at IS NULL AND extract_meta ? 'ocr_attempted' AND (extract_meta->>'ocr_attempted')::boolean = true;