INFLUENCER_POOL.schema.json

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "$id": "https://influx.local/schema/influencer.schema.json",
  "title": "Influx Influencer Profile",
  "description": "Simplified profile schema for influencer entries per POR pivot. Captures core identity, status, 30-day engagement metrics, metadata/provenance, and optional extensions.",
  "type": "object",
  "additionalProperties": false,
  "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.",
      "examples": [
        "jack",
        "TwitterDev"
      ]
    },
    "name": {
      "type": "string",
      "minLength": 1,
      "description": "Profile display name as shown on Twitter.",
      "examples": [
        "Jack Dorsey",
        "Twitter Dev"
      ]
    },
    "verified": {
      "type": "string",
      "enum": [
        "none",
        "blue",
        "org",
        "legacy"
      ],
      "description": "Verification status: none (unverified), blue (X Blue), org (Organization), or legacy (historical verified).",
      "examples": [
        "legacy",
        "blue",
        "none"
      ]
    },
    "followers_count": {
      "type": "integer",
      "minimum": 0,
      "description": "Follower count at the time of last refresh.",
      "examples": [
        6500000,
        12345
      ]
    },
    "is_org": {
      "type": "boolean",
      "default": false,
      "description": "True if heuristics identify account as brand/company/media.",
      "examples": [
        false,
        true
      ]
    },
    "is_official": {
      "type": "boolean",
      "default": false,
      "description": "True if heuristics identify account as official/team/support/PR.",
      "examples": [
        false,
        true
      ]
    },
    "lang_primary": {
      "type": "string",
      "minLength": 2,
      "maxLength": 2,
      "description": "Primary profile language (ISO 639-1, lowercase).",
      "examples": [
        "en",
        "es",
        "ja"
      ]
    },
    "topic_tags": {
      "type": "array",
      "description": "Topical tags the profile consistently covers (freeform short tags).",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "uniqueItems": true,
      "examples": [
        [
          "ai",
          "startups",
          "engineering"
        ]
      ]
    },
    "metrics_30d": {
      "type": "object",
      "title": "30-day Metrics",
      "description": "Engagement metrics computed over the last rolling 30 days.",
      "additionalProperties": false,
      "properties": {
        "posts_original": {
          "type": "integer",
          "minimum": 0,
          "description": "Count of original posts (excludes pure retweets/reposts) in the last 30 days.",
          "examples": [
            12
          ]
        },
        "median_likes": {
          "type": "integer",
          "minimum": 0,
          "description": "Median likes per original post (30-day window).",
          "examples": [
            1400
          ]
        },
        "p90_likes": {
          "type": "integer",
          "minimum": 0,
          "description": "90th percentile likes per original post (30-day window).",
          "examples": [
            5000
          ]
        },
        "median_replies": {
          "type": "integer",
          "minimum": 0,
          "description": "Median replies per original post (30-day window).",
          "examples": [
            120
          ]
        },
        "median_retweets": {
          "type": "integer",
          "minimum": 0,
          "description": "Median retweets/reposts per original post (30-day window).",
          "examples": [
            200
          ]
        }
      }
    },
    "meta": {
      "type": "object",
      "title": "Metadata",
      "description": "Scoring, global rank, activity, and provenance details for the record.",
      "additionalProperties": false,
      "properties": {
        "score": {
          "type": "number",
          "minimum": 0,
          "maximum": 100,
          "description": "Composite influence/quality score scaled 0-100 (float).",
          "examples": [
            87.5
          ]
        },
        "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"
          ]
        },
        "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 the provenance snapshot for this record.",
          "examples": [
            "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
          ]
        }
      },
      "required": [
        "score",
        "last_refresh_at",
        "sources",
        "provenance_hash"
      ]
    },
    "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"
  ],
  "examples": [
    {
      "id": "2244994945",
      "handle": "jack",
      "name": "Jack Dorsey",
      "verified": "legacy",
      "followers_count": 6500000,
      "is_org": false,
      "is_official": false,
      "lang_primary": "en",
      "topic_tags": [
        "technology",
        "bitcoin",
        "startups"
      ],
      "metrics_30d": {
        "posts_original": 12,
        "median_likes": 1400,
        "p90_likes": 5000,
        "median_replies": 120,
        "median_retweets": 200
      },
      "meta": {
        "score": 87.5,
        "rank_global": 123,
        "last_active_at": "2025-11-01T14:33:22Z",
        "last_refresh_at": "2025-11-13T12:00:00Z",
        "sources": [
          {
            "method": "twitter-api-v2",
            "fetched_at": "2025-11-13T12:00:00Z",
            "evidence": "tweet counts + user lookup"
          }
        ],
        "provenance_hash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
      },
      "ext": {
        "region": "US",
        "notes": "VIP list v2"
      }
    }
  ]
}