bigv.schema.json

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "$id": "https://influx.local/schema/bigv.schema.json",
  "title": "Influx BigV Profile",
  "description": "Simplified profile schema for BigV influencer entries per POR pivot. Captures core identity, status, 30-day metrics, and metadata/provenance for high-quality author indexing.",
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[0-9]+$",
      "description": "Twitter author_id as a numeric string.",
      "examples": [
        "2244994945"
      ]
    },
    "handle": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_]{1,15}$",
      "description": "Twitter username (handle) without leading @. 1-15 chars, alphanumeric or underscore only.",
      "examples": [
        "jack",
        "TwitterDev",
        "elonmusk"
      ]
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Profile display name as shown on Twitter.",
      "examples": [
        "Jack Dorsey",
        "Elon Musk"
      ]
    },
    "verified": {
      "type": "string",
      "enum": [
        "none",
        "blue",
        "org",
        "legacy",
        "business"
      ]
    },
    "followers_count": {
      "type": "integer",
      "minimum": 0,
      "description": "Follower count at time of last refresh.",
      "examples": [
        6500000,
        100000,
        50000
      ]
    },
    "is_org": {
      "type": "boolean",
      "description": "Whether this account represents an organization, brand, or media entity rather than an individual."
    },
    "is_official": {
      "type": "boolean",
      "description": "Whether this account is an official/PR account for an organization or individual."
    },
    "lang_primary": {
      "type": "string",
      "pattern": "^[a-z]{2}(-[A-Z]{2})?$",
      "description": "Primary language code (ISO 639-1, with optional ISO 3166-1 alpha-2 country code)."
    },
    "topic_tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Topic/domain tags for classification and filtering.",
      "examples": [
        ["ai_core", "gpu"],
        ["security"],
        []
      ]
    },
    "meta": {
      "type": "object",
      "properties": {
        "score": {
          "type": "number",
          "minimum": 0,
          "maximum": 100,
          "description": "Overall influence score (proxy or full model)."
        },
        "last_refresh_at": {
          "type": "string",
          "format": "date-time",
          "description": "ISO 8601 timestamp when this record was last refreshed.",
          "examples": [
            "2025-11-13T12:00:00Z"
          ]
        },
        "sources": {
          "type": "array",
          "description": "Data sources used to assemble this record.",
          "items": {
            "type": "object",
            "additionalProperties": false,
            "properties": {
              "method": {
                "type": "string",
                "description": "Acquisition method, e.g., twitter-api-v2, firehose, web-scrape, manual.",
                "examples": [
                  "twitter-api-v2"
                ]
              },
              "fetched_at": {
                "type": "string",
                "format": "date-time",
                "description": "ISO 8601 timestamp when the source was fetched.",
                "examples": [
                  "2025-11-13T12:00:00Z"
                ]
              },
              "evidence": {
                "type": "string",
                "description": "Freeform evidence or reference (e.g., query details, URL, or notes).",
                "examples": [
                  "tweet counts + user lookup"
                ]
              }
            },
            "required": [
              "method",
              "fetched_at",
              "evidence"
            ]
          },
          "minItems": 1
        },
        "provenance_hash": {
          "type": "string",
          "pattern": "^[A-Fa-f0-9]{64}$",
          "description": "SHA-256 hex digest capturing provenance snapshot for this record.",
          "examples": [
            "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
          ]
        },
        "entry_threshold_passed": {
          "type": "boolean",
          "description": "Whether the record passed influx-harvest pipeline entry thresholds.",
          "examples": [
            true,
            false
          ]
        },
        "quality_score": {
          "type": "number",
          "minimum": 0,
          "maximum": 100,
          "description": "Quality score from influx-harvest pipeline.",
          "examples": [
            87.5,
            95.0
          ]
        },
        "rank_global": {
          "type": "integer",
          "minimum": 1,
          "description": "Global rank position among all profiles (1 = highest).",
          "examples": [
            123
          ]
        },
        "last_active_at": {
          "type": "string",
          "format": "date-time",
          "description": "ISO 8601 timestamp of most recent observed activity.",
          "examples": [
            "2025-11-01T14:33:22Z"
          ]
        }
      },
      "required": [
        "score",
        "last_refresh_at",
        "sources",
        "provenance_hash",
        "entry_threshold_passed",
        "quality_score"
      ]
    },
    "ext": {
      "type": "object",
      "title": "Extensions",
      "description": "Optional implementation-specific custom fields. Keys/values are not validated by this schema.",
      "additionalProperties": true
    }
  },
  "required": [
    "id",
    "handle",
    "name",
    "verified",
    "followers_count",
    "is_org",
    "is_official",
    "lang_primary",
    "topic_tags",
    "meta"
  ]
}