{
  "schema_version": 2,
  "created": "2026-09-20",
  "purpose": "Controlled multilingual OCR benchmark fixtures for CreatorPrivacyKit Local OCR",
  "scoring_note": "Score core_expected_text and ground_truth.fields. Incidental decorative copy on the generated scenes is not required ground truth. Ground truth is the characters visible on the final image, not the generation prompt.",
  "fixtures": [
    {
      "id": "en",
      "locale": "en-US",
      "script": "Latin",
      "scenario": "office invoice photographed on a desk",
      "file": "ocr-en-2026.jpg",
      "difficulty": [
        "table",
        "currency",
        "email",
        "url",
        "phone",
        "perspective"
      ],
      "core_expected_text": [
        "INVOICE",
        "Invoice No: OCR-EN-2026-001",
        "Date: 2026-09-20",
        "Bill To: Harbor Metrics LLC",
        "Address: 1450 Market Street, Suite 810, San Francisco, CA 94103",
        "Email: billing@harbormetrics.com",
        "Phone: +1 (415) 555-0182",
        "OCR Evaluation Package",
        "Layout Stress Test",
        "Subtotal: $134.00",
        "Tax (8.25%): $11.06",
        "Grand Total: $145.06",
        "Notes: Please pay within 15 days.",
        "Website: https://harbormetrics.com/pay"
      ],
      "pack": "eng",
      "public_id": "OCR-EN-2026-001",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "INVOICE",
        "public_id": "OCR-EN-2026-001",
        "fields": [
          {
            "type": "title",
            "value": "INVOICE"
          },
          {
            "type": "id",
            "value": "OCR-EN-2026-001"
          },
          {
            "type": "date",
            "value": "2026-09-20"
          },
          {
            "type": "address",
            "value": "1450 Market Street, Suite 810, San Francisco, CA 94103"
          },
          {
            "type": "email",
            "value": "billing@harbormetrics.com"
          },
          {
            "type": "phone",
            "value": "+1 (415) 555-0182"
          },
          {
            "type": "body",
            "value": "OCR Evaluation Package"
          },
          {
            "type": "body",
            "value": "Layout Stress Test"
          },
          {
            "type": "price",
            "value": "$49.50"
          },
          {
            "type": "price",
            "value": "$99.00"
          },
          {
            "type": "price",
            "value": "$35.00"
          },
          {
            "type": "price",
            "value": "$134.00"
          },
          {
            "type": "percentage",
            "value": "8.25%"
          },
          {
            "type": "price",
            "value": "$11.06"
          },
          {
            "type": "currency",
            "value": "$145.06"
          },
          {
            "type": "url",
            "value": "https://harbormetrics.com/pay"
          }
        ]
      }
    },
    {
      "id": "zh-cn",
      "locale": "zh-CN",
      "script": "Han (Simplified Chinese)",
      "scenario": "community notice pinned to a wall",
      "file": "ocr-zh-cn-2026.jpg",
      "difficulty": [
        "CJK",
        "dates",
        "time-range",
        "email",
        "url",
        "phone",
        "perspective"
      ],
      "core_expected_text": [
        "社区服务中心通知",
        "文件编号：OCR-ZH-2026-002",
        "发布时间：2026年9月20日",
        "主题：周末设备维护安排",
        "维护时间：2026年9月22日 09:00-17:30",
        "影响范围：一楼大厅自助终端、二楼打印室、三楼会议预约屏",
        "联系人：李明",
        "联系电话：021-5558-1266",
        "电子邮箱：support@example.cn",
        "地址：上海市浦东新区世纪大道88号A座3层",
        "请提前保存重要资料，以免造成不便。",
        "官网：https://example.cn/notice"
      ],
      "pack": "chi_sim",
      "public_id": "OCR-ZH-2026-002",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "社区服务中心通知",
        "public_id": "OCR-ZH-2026-002",
        "fields": [
          {
            "type": "title",
            "value": "社区服务中心通知"
          },
          {
            "type": "id",
            "value": "OCR-ZH-2026-002"
          },
          {
            "type": "date",
            "value": "2026年9月20日"
          },
          {
            "type": "body",
            "value": "周末设备维护安排"
          },
          {
            "type": "date",
            "value": "2026年9月22日"
          },
          {
            "type": "time",
            "value": "09:00-17:30"
          },
          {
            "type": "phone",
            "value": "021-5558-1266"
          },
          {
            "type": "email",
            "value": "support@example.cn"
          },
          {
            "type": "address",
            "value": "上海市浦东新区世纪大道88号A座3层"
          },
          {
            "type": "body",
            "value": "请提前保存重要资料，以免造成不便。"
          },
          {
            "type": "url",
            "value": "https://example.cn/notice"
          }
        ]
      }
    },
    {
      "id": "ja",
      "locale": "ja-JP",
      "script": "Japanese (Kanji/Kana)",
      "scenario": "restaurant menu board",
      "file": "ocr-ja-2026.jpg",
      "difficulty": [
        "CJK",
        "mixed kanji-kana",
        "prices",
        "menu-layout",
        "photos"
      ],
      "core_expected_text": [
        "本日のおすすめ",
        "店舗コード：OCR-JA-2026-003",
        "営業時間 11:30-22:00",
        "住所：東京都新宿区西新宿2-8-1",
        "電話：03-5550-2481",
        "メニュー",
        "1. 醤油ラーメン 980円",
        "2. 味噌ラーメン 1,080円",
        "3. 焼き餃子 6個 420円",
        "4. 半チャーハン 380円",
        "5. 抹茶アイス 300円",
        "本日の合計例：1,700円",
        "メール：info@tokyoramen.jp",
        "サイト：https://tokyoramen.jp"
      ],
      "pack": "jpn",
      "public_id": "OCR-JA-2026-003",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "本日のおすすめ",
        "public_id": "OCR-JA-2026-003",
        "fields": [
          {
            "type": "title",
            "value": "本日のおすすめ"
          },
          {
            "type": "id",
            "value": "OCR-JA-2026-003"
          },
          {
            "type": "time",
            "value": "11:30-22:00"
          },
          {
            "type": "address",
            "value": "東京都新宿区西新宿2-8-1"
          },
          {
            "type": "phone",
            "value": "03-5550-2481"
          },
          {
            "type": "body",
            "value": "醤油ラーメン"
          },
          {
            "type": "price",
            "value": "980円"
          },
          {
            "type": "body",
            "value": "味噌ラーメン"
          },
          {
            "type": "price",
            "value": "1,080円"
          },
          {
            "type": "body",
            "value": "焼き餃子"
          },
          {
            "type": "price",
            "value": "420円"
          },
          {
            "type": "body",
            "value": "半チャーハン"
          },
          {
            "type": "price",
            "value": "380円"
          },
          {
            "type": "body",
            "value": "抹茶アイス"
          },
          {
            "type": "price",
            "value": "300円"
          },
          {
            "type": "price",
            "value": "1,700円"
          },
          {
            "type": "email",
            "value": "info@tokyoramen.jp"
          },
          {
            "type": "url",
            "value": "https://tokyoramen.jp"
          }
        ]
      }
    },
    {
      "id": "ko",
      "locale": "ko-KR",
      "script": "Hangul",
      "scenario": "cafe poster taped to glass",
      "file": "ocr-ko-2026.jpg",
      "difficulty": [
        "Hangul",
        "reflections",
        "prices",
        "poster-layout",
        "photos"
      ],
      "core_expected_text": [
        "가을 시즌 안내",
        "문서번호: OCR-KO-2026-004",
        "행사 기간: 2026년 9월 20일 - 2026년 10월 5일",
        "매장명: 모닝브루 카페",
        "주소: 서울특별시 강남구 테헤란로 152",
        "전화: 02-555-7341",
        "신메뉴",
        "1. 호박 라떼 6,300원",
        "2. 바닐라 크림 콜드브루 5,900원",
        "3. 치즈 스콘 3,800원",
        "이벤트: 음료 2잔 구매 시 쿠키 1개 증정",
        "이메일: hello@morningbrew.kr",
        "웹사이트: https://morningbrew.kr"
      ],
      "pack": "kor",
      "public_id": "OCR-KO-2026-004",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "가을 시즌 안내",
        "public_id": "OCR-KO-2026-004",
        "fields": [
          {
            "type": "title",
            "value": "가을 시즌 안내"
          },
          {
            "type": "id",
            "value": "OCR-KO-2026-004"
          },
          {
            "type": "date",
            "value": "2026년 9월 20일"
          },
          {
            "type": "date",
            "value": "2026년 10월 5일"
          },
          {
            "type": "address",
            "value": "서울특별시 강남구 테헤란로 152"
          },
          {
            "type": "phone",
            "value": "02-555-7341"
          },
          {
            "type": "price",
            "value": "6,300원"
          },
          {
            "type": "price",
            "value": "5,900원"
          },
          {
            "type": "price",
            "value": "3,800원"
          },
          {
            "type": "email",
            "value": "hello@morningbrew.kr"
          },
          {
            "type": "url",
            "value": "https://morningbrew.kr"
          }
        ]
      }
    },
    {
      "id": "es",
      "locale": "es-ES",
      "script": "Latin",
      "scenario": "crumpled supermarket receipt",
      "file": "ocr-es-2026.jpg",
      "difficulty": [
        "receipt",
        "wrinkles",
        "currency",
        "diacritics",
        "columns"
      ],
      "core_expected_text": [
        "SUPERMERCADO LA PLAZA",
        "Ticket: OCR-ES-2026-005",
        "Fecha: 20/09/2026 18:42",
        "Dirección: Calle Mayor 18, 28013 Madrid",
        "Tel: +34 91 555 24 80",
        "Artículos",
        "Leche entera 1L 1 x 1,25 €",
        "Pan integral 2 x 1,10 €",
        "Tomate cherry 1 x 2,85 €",
        "Aceite de oliva 500ml 1 x 5,90 €",
        "Subtotal: 12,20 €",
        "IVA: 1,22 €",
        "Total: 13,42 €",
        "Gracias por su compra",
        "Web: https://laplaza.es",
        "Correo: soporte@laplaza.es"
      ],
      "pack": "spa",
      "public_id": "OCR-ES-2026-005",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "SUPERMERCADO LA PLAZA",
        "public_id": "OCR-ES-2026-005",
        "fields": [
          {
            "type": "title",
            "value": "SUPERMERCADO LA PLAZA"
          },
          {
            "type": "id",
            "value": "OCR-ES-2026-005"
          },
          {
            "type": "date",
            "value": "20/09/2026"
          },
          {
            "type": "time",
            "value": "18:42"
          },
          {
            "type": "address",
            "value": "Calle Mayor 18, 28013 Madrid"
          },
          {
            "type": "postal_code",
            "value": "28013"
          },
          {
            "type": "phone",
            "value": "+34 91 555 24 80"
          },
          {
            "type": "price",
            "value": "1,25 €"
          },
          {
            "type": "price",
            "value": "1,10 €"
          },
          {
            "type": "price",
            "value": "2,85 €"
          },
          {
            "type": "price",
            "value": "5,90 €"
          },
          {
            "type": "price",
            "value": "12,20 €"
          },
          {
            "type": "price",
            "value": "1,22 €"
          },
          {
            "type": "currency",
            "value": "13,42 €"
          },
          {
            "type": "url",
            "value": "https://laplaza.es"
          },
          {
            "type": "email",
            "value": "soporte@laplaza.es"
          }
        ]
      }
    },
    {
      "id": "fr",
      "locale": "fr-FR",
      "script": "Latin",
      "scenario": "cultural event flyer on cork board",
      "file": "ocr-fr-2026.jpg",
      "difficulty": [
        "diacritics",
        "schedule",
        "email",
        "url",
        "decorative-layout"
      ],
      "core_expected_text": [
        "Festival de Lecture",
        "Référence : OCR-FR-2026-006",
        "Date : 20 septembre 2026",
        "Lieu : Maison de la Culture, 12 rue Victor Hugo, 69002 Lyon",
        "Programme",
        "10:00 Ouverture des portes",
        "11:30 Table ronde : Lire à l'ère numérique",
        "14:00 Atelier OCR et archivage",
        "16:30 Rencontre avec les auteurs",
        "Contact : Marie Dupont",
        "Téléphone : 04 72 55 18 90",
        "E-mail : contact@festivallecture.fr",
        "Billetterie : https://festivallecture.fr"
      ],
      "pack": "fra",
      "public_id": "OCR-FR-2026-006",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "Festival de Lecture",
        "public_id": "OCR-FR-2026-006",
        "fields": [
          {
            "type": "title",
            "value": "Festival de Lecture"
          },
          {
            "type": "id",
            "value": "OCR-FR-2026-006"
          },
          {
            "type": "date",
            "value": "20 septembre 2026"
          },
          {
            "type": "address",
            "value": "Maison de la Culture, 12 rue Victor Hugo, 69002 Lyon"
          },
          {
            "type": "postal_code",
            "value": "69002"
          },
          {
            "type": "time",
            "value": "10:00"
          },
          {
            "type": "time",
            "value": "11:30"
          },
          {
            "type": "time",
            "value": "14:00"
          },
          {
            "type": "time",
            "value": "16:30"
          },
          {
            "type": "phone",
            "value": "04 72 55 18 90"
          },
          {
            "type": "email",
            "value": "contact@festivallecture.fr"
          },
          {
            "type": "url",
            "value": "https://festivallecture.fr"
          }
        ]
      }
    },
    {
      "id": "de",
      "locale": "de-DE",
      "script": "Latin",
      "scenario": "technical product sheet on clipboard",
      "file": "ocr-de-2026.jpg",
      "difficulty": [
        "umlauts",
        "table-like-fields",
        "units",
        "serial-number",
        "url"
      ],
      "core_expected_text": [
        "Geräteübersicht",
        "Dokument-Nr.: OCR-DE-2026-007",
        "Produkt: MobileScan Pro 12",
        "Hersteller: DatenWerk GmbH",
        "Adresse: Lindenstraße 44, 10117 Berlin",
        "Support: support@datenwerk.de",
        "Telefon: +49 30 5557 8812",
        "Technische Daten",
        "Auflösung: 2400 dpi",
        "Schnittstellen: USB-C, WLAN, Bluetooth 5.2",
        "Gewicht: 1,35 kg",
        "Betriebstemperatur: 5-35 °C",
        "Seriennummer: MSP12-DE-884209",
        "Handbuch: https://datenwerk.de/manual"
      ],
      "pack": "deu",
      "public_id": "OCR-DE-2026-007",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "Geräteübersicht",
        "public_id": "OCR-DE-2026-007",
        "fields": [
          {
            "type": "title",
            "value": "Geräteübersicht"
          },
          {
            "type": "id",
            "value": "OCR-DE-2026-007"
          },
          {
            "type": "body",
            "value": "MobileScan Pro 12"
          },
          {
            "type": "address",
            "value": "Lindenstraße 44, 10117 Berlin"
          },
          {
            "type": "postal_code",
            "value": "10117"
          },
          {
            "type": "email",
            "value": "support@datenwerk.de"
          },
          {
            "type": "phone",
            "value": "+49 30 5557 8812"
          },
          {
            "type": "body",
            "value": "2400 dpi"
          },
          {
            "type": "body",
            "value": "1,35 kg"
          },
          {
            "type": "id",
            "value": "MSP12-DE-884209"
          },
          {
            "type": "url",
            "value": "https://datenwerk.de/manual"
          }
        ]
      }
    },
    {
      "id": "pt-br",
      "locale": "pt-BR",
      "script": "Latin",
      "scenario": "shipping label on cardboard parcel",
      "file": "ocr-pt-br-2026.jpg",
      "difficulty": [
        "diacritics",
        "address",
        "barcode-adjacent-text",
        "tracking-number",
        "perspective"
      ],
      "core_expected_text": [
        "ETIQUETA DE ENVIO",
        "Código: OCR-PTBR-2026-008",
        "Destinatário: Camila Souza",
        "Rua das Palmeiras, 245, Apto 32",
        "Bairro Centro",
        "Curitiba - PR",
        "CEP 80010-120",
        "Remetente: Loja Nova Era",
        "Telefone: (41) 3555-9021",
        "Pedido: NE-784512",
        "Data de postagem: 20/09/2026",
        "E-mail: atendimento@lojanovaera.com.br",
        "Rastreamento: BR420998771",
        "Site: https://lojanovaera.com.br"
      ],
      "pack": "por",
      "public_id": "OCR-PTBR-2026-008",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "ETIQUETA DE ENVIO",
        "public_id": "OCR-PTBR-2026-008",
        "fields": [
          {
            "type": "title",
            "value": "ETIQUETA DE ENVIO"
          },
          {
            "type": "id",
            "value": "OCR-PTBR-2026-008"
          },
          {
            "type": "address",
            "value": "Rua das Palmeiras, 245, Apto 32"
          },
          {
            "type": "postal_code",
            "value": "80010-120"
          },
          {
            "type": "phone",
            "value": "(41) 3555-9021"
          },
          {
            "type": "id",
            "value": "NE-784512"
          },
          {
            "type": "date",
            "value": "20/09/2026"
          },
          {
            "type": "email",
            "value": "atendimento@lojanovaera.com.br"
          },
          {
            "type": "id",
            "value": "BR420998771"
          },
          {
            "type": "url",
            "value": "https://lojanovaera.com.br"
          }
        ]
      }
    },
    {
      "id": "hi",
      "locale": "hi-IN",
      "script": "Devanagari",
      "scenario": "public information poster",
      "file": "ocr-hi-2026.jpg",
      "difficulty": [
        "Devanagari",
        "mixed Latin digits",
        "email",
        "url",
        "icons"
      ],
      "core_expected_text": [
        "जन सूचना",
        "दस्तावेज़ संख्या: OCR-HI-2026-009",
        "तारीख: 20 सितंबर 2026",
        "विषय: डिजिटल सेवा शिविर",
        "स्थान: सामुदायिक भवन, सेक्टर 12, नोएडा",
        "समय: सुबह 10:00 बजे से शाम 5:00 बजे तक",
        "सेवाएँ: दस्तावेज़ स्कैन, OCR जाँच, ऑनलाइन पंजीकरण",
        "संपर्क व्यक्ति: अजय कुमार",
        "मोबाइल: +91 98765 43210",
        "ईमेल: help@digitalseva.in",
        "वेबसाइट: https://digitalseva.in",
        "कृपया पहचान पत्र साथ लाएँ।"
      ],
      "pack": "hin",
      "public_id": "OCR-HI-2026-009",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "जन सूचना",
        "public_id": "OCR-HI-2026-009",
        "fields": [
          {
            "type": "title",
            "value": "जन सूचना"
          },
          {
            "type": "id",
            "value": "OCR-HI-2026-009"
          },
          {
            "type": "date",
            "value": "20 सितंबर 2026"
          },
          {
            "type": "time",
            "value": "10:00"
          },
          {
            "type": "time",
            "value": "5:00"
          },
          {
            "type": "phone",
            "value": "+91 98765 43210"
          },
          {
            "type": "email",
            "value": "help@digitalseva.in"
          },
          {
            "type": "url",
            "value": "https://digitalseva.in"
          },
          {
            "type": "body",
            "value": "कृपया पहचान पत्र साथ लाएँ।"
          }
        ]
      }
    },
    {
      "id": "ar",
      "locale": "ar-SA",
      "script": "Arabic",
      "scenario": "clinic information sheet and appointment card",
      "file": "ocr-ar-2026.jpg",
      "difficulty": [
        "RTL",
        "Arabic",
        "mixed Latin digits",
        "email",
        "url",
        "multi-document"
      ],
      "core_expected_text": [
        "مركز النور الطبي",
        "المرجع: OCR-AR-2026-010",
        "التاريخ: 20-09-2026",
        "العنوان: شارع الملك فهد، مبنى 18، الرياض",
        "الهاتف: +966 11 555 2480",
        "البريد الإلكتروني: info@alnourmed.sa",
        "موعد المراجعة",
        "اسم المريض: سارة أحمد",
        "العيادة: طب العيون",
        "الوقت: 04:30 مساءً",
        "رقم الملف: 882145",
        "تعليمات: يرجى الحضور قبل الموعد بـ 15 دقيقة.",
        "الموقع: https://alnourmed.sa"
      ],
      "pack": "ara",
      "public_id": "OCR-AR-2026-010",
      "source_type": "synthetic_controlled_fixture",
      "ground_truth_verified": true,
      "verified_at": "2026-09-20",
      "verification_method": "visual_inspection_of_rendered_pixels",
      "ground_truth": {
        "title": "مركز النور الطبي",
        "public_id": "OCR-AR-2026-010",
        "fields": [
          {
            "type": "title",
            "value": "مركز النور الطبي"
          },
          {
            "type": "id",
            "value": "OCR-AR-2026-010"
          },
          {
            "type": "date",
            "value": "20-09-2026"
          },
          {
            "type": "address",
            "value": "شارع الملك فهد، مبنى 18، الرياض"
          },
          {
            "type": "phone",
            "value": "+966 11 555 2480"
          },
          {
            "type": "email",
            "value": "info@alnourmed.sa"
          },
          {
            "type": "url",
            "value": "https://alnourmed.sa"
          },
          {
            "type": "body",
            "value": "سارة أحمد"
          },
          {
            "type": "body",
            "value": "طب العيون"
          },
          {
            "type": "time",
            "value": "04:30"
          },
          {
            "type": "id",
            "value": "882145"
          }
        ]
      }
    }
  ],
  "source_type": "synthetic_controlled_fixture",
  "verified_at": "2026-09-20",
  "verification_method": "visual_inspection_of_rendered_pixels"
}