{
  "schemaVersion": 1,
  "profileType": "database-inventory-and-sample-consistency",
  "apiVersion": "v2",
  "observationWindow": {
    "metadataAt": "2026-09-26T15:28:18.227Z",
    "randomSamplesAt": "2026-09-26T15:31:54.045Z",
    "countryIndexAt": "2026-09-26T15:33:13.811Z"
  },
  "accuracyMeasured": false,
  "apiCoverageMeasured": false,
  "redisParityChecked": false,
  "independentReferenceLabelsUsed": false,
  "reviewedSourceCatalogPublished": false,
  "countMethod": "MongoDB collStats metadata; no independent countDocuments census",
  "sampleMethod": "MongoDB $sample first stage, 5000 documents per collection; only server-side aggregate counters and field-type summaries returned",
  "sampleSeed": null,
  "frozenDatasetSnapshot": false,
  "collectionProfiles": [
    {
      "collection": "general",
      "metadataDocumentCount": 2483220,
      "uniqueStoredKey": [
        "name"
      ],
      "sampledAt": "2026-09-26T15:31:54.045Z",
      "sample": {
        "documents": 5000,
        "numericRuleFailures": 0,
        "malePlusFemaleNotEqualToTotal": 0,
        "equalMaleAndFemaleCounts": 124,
        "unequalMaleAndFemaleCounts": 4876,
        "updatedAtFieldPresent": 667
      },
      "sampledFieldTypes": [
        {
          "present": 5000,
          "field": "country",
          "type": "string"
        },
        {
          "present": 5000,
          "field": "female",
          "type": "int"
        },
        {
          "present": 5000,
          "field": "male",
          "type": "int"
        },
        {
          "present": 5000,
          "field": "name",
          "type": "string"
        },
        {
          "present": 5000,
          "field": "total",
          "type": "int"
        },
        {
          "present": 667,
          "field": "updated_at",
          "type": "double"
        }
      ]
    },
    {
      "collection": "country-specific",
      "metadataDocumentCount": 4080692,
      "uniqueStoredKey": [
        "name",
        "country"
      ],
      "sampledAt": "2026-09-26T15:31:54.045Z",
      "sample": {
        "documents": 5000,
        "numericRuleFailures": 0,
        "malePlusFemaleNotEqualToTotal": 0,
        "equalMaleAndFemaleCounts": 94,
        "unequalMaleAndFemaleCounts": 4906,
        "updatedAtFieldPresent": 741
      },
      "sampledFieldTypes": [
        {
          "present": 5000,
          "field": "country",
          "type": "string"
        },
        {
          "present": 5000,
          "field": "female",
          "type": "int"
        },
        {
          "present": 5000,
          "field": "male",
          "type": "int"
        },
        {
          "present": 5000,
          "field": "name",
          "type": "string"
        },
        {
          "present": 5000,
          "field": "total",
          "type": "int"
        },
        {
          "present": 741,
          "field": "updated_at",
          "type": "double"
        }
      ]
    }
  ],
  "numericRules": "total must be a positive safe integer; male and female must be finite numeric values between zero and total. male + female = total is checked separately.",
  "countryFieldInventory": {
    "collection": "general",
    "observedAt": "2026-09-26T15:33:13.811Z",
    "method": "Indexed distinct-value grouping with server-side format/type counts",
    "distinctStoredValueCount": 244,
    "uppercaseTwoLetterValueCount": 239,
    "otherFormatValueCount": 5,
    "iso3166ValidationPerformed": false,
    "supportedCountryCoverageMeasured": false,
    "countryRecordDistributionMeasured": false
  },
  "limitations": [
    "Document counts describe two different data structures; overlap and normalized-name deduplication were not measured. Do not add them into a unique-name, unique-person or independent-observation total.",
    "Unique indexes constrain stored values, not normalized-name uniqueness or distinct people.",
    "Sample consistency is not prediction accuracy, calibrated confidence, or API answer coverage. Count ties are not verified ambiguous identities.",
    "The samples were unseeded, not frozen, and not independently labelled. Metadata and samples were read at different times without a snapshot transaction.",
    "No source or licence fields appeared in these samples; this does not prove that no provenance exists in other records or external systems.",
    "updated_at was present as a BSON double in some sampled records. Its values, unit and meaning were not inspected; no record freshness or update cadence is established.",
    "Stored country-value formatting is not ISO membership or evidence of supported-country availability or accuracy.",
    "No full collection quality scan, AI prediction or credit operation was performed."
  ],
  "redisDatasetRelationship": {
    "status": "owner_confirmed_identical",
    "confirmedOn": "2026-09-26",
    "basis": "GenderAPI data owner confirmation",
    "statement": "MongoDB and Redis contain the same dataset."
  }
}