{
  "format": "agent-article-v0",
  "article_id": "EA-073",
  "canonical_url": "/tools/ea-073-forms-handwriting-barcode-ai",
  "page_type": "reference",
  "claim_ids": [],
  "evidence_ids": [
    "EA-073-R11-RESEARCH",
    "EA-073-R11-WEB-READBACK"
  ],
  "unknown_ids": [
    "EA-073-UNKNOWN-01",
    "EA-073-UNKNOWN-CURRENTNESS"
  ],
  "operational_object_ids": [],
  "provider": [],
  "models": [],
  "plans": [],
  "surfaces": [],
  "regions": [],
  "current_status": "UNKNOWN",
  "observation_status": "SPEC_ONLY",
  "freshness": "UNKNOWN",
  "last_verified": null,
  "supersedes": [],
  "superseded_by": [],
  "provenance": [
    "COMM-069-EA0073",
    "WEBBODY-EA0073-R8-7F634634"
  ],
  "article_sources": [
    {
      "id": "EA-073-R11-RESEARCH",
      "evidence_class": "RESEARCH",
      "title": "EA-073 監査済みresearch / canonical revision binding",
      "supports": [
        "「紙帳票をAIへ取り込む処理はOCRだけではない。文字認識、キーと値の対応、チェック状態、手書き判定、バーコード形式とpayload復号を別々に検証する必要がある。読み取れた文字やQRコードは、それだけで業務上の真正性や安全性を保証しない。原画像と抽出結果のprovenanceを保持し、正規化・検証・認可・必要な人手確認を後段に置く。」"
      ],
      "limit": "canonical監査・revision bindingの存在を示す。外部ソースcurrentnessが本文またはcontrol-planeで確定していない場合は、currentnessをUNKNOWNのまま保持する。",
      "origin_class": "AUDITED_CANONICAL_RESEARCH_PACKET",
      "source_or_experiment_ids": [
        "COMM-069-EA0073"
      ],
      "supporting_locators": [
        "COMM-069-EA0073",
        "EA-073-R5-LEGACY-MIGRATION-20261008-R1",
        "content/staging/EA-073.md"
      ],
      "scope": "監査済みEA本文・canonical revision・既存Source Graph relationの範囲。欠損currentnessは推測で閉じない。",
      "provenance_status": "AUDIT_PASS_CANONICAL_BINDING"
    },
    {
      "id": "EA-073-R11-WEB-READBACK",
      "evidence_class": "IMPL",
      "title": "EA-073 Web body identity / canonical readback",
      "supports": [
        "canonical staging bodyのSHA-256一致とR9 canonical ledger readbackをProduction projectionの入力として検証する。"
      ],
      "limit": "body identity/readbackは本文claim自体の真偽や外部ソースの最新性を追加保証しない。",
      "checked_at": null,
      "origin_class": "IMPLEMENTATION_READBACK",
      "source_or_experiment_ids": [
        "WEBBODY-EA0073-R8-7F634634"
      ],
      "supporting_locators": [
        "WEBBODY-EA0073-R8-7F634634",
        "content/staging/EA-073.md",
        "EA-073-R5-LEGACY-MIGRATION-20261008-R1"
      ],
      "scope": "R9/R10 canonical readback後のProduction生成時body identity。",
      "provenance_status": "CANONICAL_READBACK_BODY_HASH_MATCH"
    }
  ],
  "research_sections": [
    {
      "heading": "SAFE_WORDING_FOR_FUTURE_BOOK",
      "text": "「紙帳票をAIへ取り込む処理はOCRだけではない。文字認識、キーと値の対応、チェック状態、手書き判定、バーコード形式とpayload復号を別々に検証する必要がある。読み取れた文字やQRコードは、それだけで業務上の真正性や安全性を保証しない。原画像と抽出結果のprovenanceを保持し、正規化・検証・認可・必要な人手確認を後段に置く。」"
    },
    {
      "heading": "IMPLEMENTATION_STATE",
      "text": "Core候補 FORM_CAPTURE_CONTRACT: source_hash/capture_device/page-or-frame/ROI, processor-or-decoder/version, raw_text, text_type, key/value linkage, selection_state, barcode_symbology, raw_payload/raw_bytes, geometry, confidence, normalization, validation_rule/result, human_override, provenance, ACL, retention."
    },
    {
      "heading": "OPEN_UNKNOWN",
      "text": "Azure current official barcode model/capability locator、各providerの日本語手書き実効精度、damaged/low-light barcodeのprovider横断実測、active ZXing-C++ canonical release/commit、GS1 Digital Link/署名付き2D code等の業務検証標準との接続。\n\nAUDIT OVERLAY — REAUDIT_VERIFIED_20260929\nVERDICT: RESEARCH_AUDIT_APPROVED_FOR_IMPLEMENTATION\nRE-AUDIT_RESULT: PASS with barcode boundary. Current Microsoft v4.0 remains authoritative surface and migration docs confirm barcode extraction existed in v3.1+; however a generic Document Intelligence capability statement does not justify a provider-wide barcode guarantee across all models/formats. Handwriting/KVP/barcode remain separate."
    },
    {
      "heading": "CURRENTNESS_OR_BOUNDARY",
      "text": "Barcode capability must stay model/version/format scoped; Japanese handwriting effective accuracy remains UNKNOWN."
    }
  ],
  "human_url": "/tools/ea-073-forms-handwriting-barcode-ai",
  "markdown_url": "/agent/article.md?path=%2Ftools%2Fea-073-forms-handwriting-barcode-ai",
  "json_url": "/agent/article.json?path=%2Ftools%2Fea-073-forms-handwriting-barcode-ai"
}