# arvaken.com
# Publications are licensed under CC BY 4.0. This file blocks dedicated training crawlers and states a no-training
# preference; both are requests the licence does not enforce. See https://arvaken.com/publications#reuse

User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

# Crawlers whose operators document them as collecting AI training data, named as the operators name them.
# Common Crawl's CCBot is not listed: it is a public archive, and the ai-train=no signal carries the preference.
# Names reviewed 2026-09-14. Operators rename crawlers: review this list whenever security.txt is renewed.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: Applebot-Extended
Disallow: /

Sitemap: https://arvaken.com/sitemap.xml