{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "vignette.pii_masking_eval_input.v1",
  "title": "Vignette PII masking evaluation input",
  "type": "array",
  "items": {
    "type": "object",
    "additionalProperties": false,
    "required": [
      "id",
      "locale",
      "source",
      "category",
      "severity",
      "text",
      "expected_entities",
      "forbidden_substrings"
    ],
    "properties": {
      "id": { "type": "string", "minLength": 1 },
      "locale": { "type": "string", "default": "ko-KR" },
      "source": {
        "type": "string",
        "enum": ["synthetic", "operator_supplied_redacted", "operational_gold"],
        "default": "synthetic"
      },
      "category": {
        "type": "string",
        "enum": [
          "name",
          "organization",
          "contact",
          "national_id",
          "quasi_identifier",
          "negative_control",
          "unspecified"
        ],
        "default": "unspecified"
      },
      "severity": {
        "type": "string",
        "enum": ["low", "medium", "high", "critical"],
        "default": "medium"
      },
      "text": {
        "type": "string",
        "minLength": 1,
        "description": "Evaluation input text. Use only local synthetic or approved redacted/gold text according to data governance gates."
      },
      "expected_entities": {
        "type": "array",
        "items": { "type": "string" },
        "uniqueItems": true,
        "default": []
      },
      "unexpected_entities": {
        "type": "array",
        "items": { "type": "string" },
        "uniqueItems": true,
        "default": []
      },
      "forbidden_substrings": {
        "type": "array",
        "items": { "type": "string" },
        "default": []
      },
      "required_substrings": {
        "type": "array",
        "items": { "type": "string" },
        "default": []
      }
    }
  }
}