{
  "dataset": "crawlers",
  "record": {
    "id": "ai2bot",
    "name": "AI2Bot",
    "operator": "Allen Institute for AI (Ai2)",
    "purpose": "training",
    "ua_substring": "AI2Bot",
    "robots_token": "AI2Bot",
    "respects_robots": true,
    "verify": "Ai2 documents the crawler and states its UA string may be used to filter or reject traffic; there is no published IP file, so match the UA (see documentation_url).",
    "notes": "Collects web content to train Ai2's open language models.",
    "canonical_name": "AI2Bot",
    "user_agent_token": "AI2Bot",
    "ua_full": {
      "value": "Mozilla/5.0 (compatible) AI2Bot (+https://www.allenai.org/crawler)",
      "source": "https://allenai.org/crawler",
      "note": "full UA string as documented by the operator"
    },
    "bot_type": "training",
    "bot_type_extension": null,
    "opt_out_mechanism": "robots.txt disallow (User-agent: AI2Bot); the related tokens Ai2Bot-Dolma and AI2Bot-DeepResearchEval cover other Ai2 uses",
    "published_ip_range_url": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler",
      "note": "no standalone IP-range file confirmed; operator doc is the authoritative reference"
    },
    "asn": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler"
    },
    "reverse_dns_suffix": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler"
    },
    "supports_web_bot_auth": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler"
    },
    "signature_agent_domain": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler"
    },
    "jwks_url": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler"
    },
    "verification_methods": [
      "user-agent-string"
    ],
    "crawl_traffic_share": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://radar.cloudflare.com/bots",
      "note": "not among the figures supplied in research"
    },
    "targeted_content_type": "HTML, text",
    "documentation_url": "https://allenai.org/crawler",
    "first_seen_date": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://allenai.org/crawler"
    },
    "last_verified_date": "2026-07-06",
    "block_vs_allow_recommendation": "conditional — trains open models; block via robots.txt to opt out.",
    "citation_referral_value": "low (training; does not itself cite or refer)",
    "cloudflare_verified_category": {
      "value": null,
      "verify_status": "verify-against-primary-at-build",
      "source_hint": "https://radar.cloudflare.com/bots"
    },
    "status": "active",
    "triples": [
      [
        "AI2Bot",
        "operated_by",
        "Allen Institute for AI (Ai2)"
      ],
      [
        "AI2Bot",
        "has_bot_type",
        "training"
      ],
      [
        "AI2Bot",
        "verified_via",
        "user-agent-string"
      ]
    ],
    "attribute_sources": [
      {
        "claims": [
          "user_agent_token",
          "robots_token"
        ],
        "source": "https://allenai.org/crawler",
        "last_verified": "2026-07-06"
      },
      {
        "claims": [
          "operator",
          "purpose",
          "documentation_url",
          "respects_robots"
        ],
        "source": "https://allenai.org/crawler",
        "last_verified": "2026-07-06"
      }
    ]
  }
}