# https://www.robotstxt.org/robotstxt.html

# Everything here is meant to be found, read and cited — including by
# assistants answering questions on someone's behalf.
User-agent: *
Allow: /

# The PDFs under /assets/papers/ are published papers. Several are the
# publisher's typeset version, reproduced here under open-access terms or as
# the author's accepted manuscript. They are free to read, link and cite, but
# they are not offered as training data. Crawlers that collect corpora for
# model training are asked to skip that directory; the DOI of every paper is
# on /publications/, so nothing is hidden.
User-agent: GPTBot
Disallow: /assets/papers/

User-agent: ClaudeBot
Disallow: /assets/papers/

User-agent: Google-Extended
Disallow: /assets/papers/

User-agent: Applebot-Extended
Disallow: /assets/papers/

User-agent: CCBot
Disallow: /assets/papers/

User-agent: Bytespider
Disallow: /assets/papers/

User-agent: meta-externalagent
Disallow: /assets/papers/

Sitemap: https://karol.chlasta.pl/sitemap.xml