Given their examples and examples I've seem Thomas talk about in the past, I doubt a typo like that would be grounds for the ban.

Perhaps the issue is that people aren't logged in or using xcancel so missing part of the tweet thread. Here's an important line

> If a submission contains incontrovertible evidence that the authors did not check the results of LLM generation, this means we can't trust anything in the paper.

Followed by

> Examples of incontrovertible evidence: hallucinated references, meta-comments from the LLM ("here is a 200 word summary; would you like me to make any changes?"; "the data in this table is illustrative, fill it in with the real numbers from your experiments")

I wouldn't look at your case and read that as "incontrovertible evidence". They are looking for the absolutely brain dead, no one at the wheel, type of errors. They're looking for things like your paper saying "As an AI language model". Which, there will be real papers with that exact phrase, but it should get flagged, not auto banned