# Archive Trust for Research in Mathematical Sciences and Philosophy
# https://archivetrust.org

User-agent: *
Allow: /

# Disallow data files from being indexed directly
Disallow: /data/

# ── AI / LLM training crawlers ───────────────────────────────────────────────
# The Trust reserves all text-and-data-mining and AI/ML training rights over its
# content — see /LICENSE and /.well-known/tdmrep.json. The crawlers below gather
# data used to TRAIN models and are disallowed site-wide. Ordinary search engines
# (Googlebot, Bingbot, …) and user-initiated / answer-retrieval bots are NOT
# listed here, so the archive stays fully discoverable in search and can still be
# cited in AI answers. Tighten or loosen this list as policy is settled.
User-agent: GPTBot
User-agent: Google-Extended
User-agent: CCBot
User-agent: ClaudeBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: Applebot-Extended
User-agent: Bytespider
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Amazonbot
User-agent: cohere-ai
User-agent: PerplexityBot
User-agent: Diffbot
User-agent: Omgilibot
User-agent: ImagesiftBot
User-agent: Timpibot
User-agent: YouBot
User-agent: DuckAssistBot
Disallow: /

Sitemap: https://archivetrust.org/sitemap.xml