[thereddaikon]

The engineering/materials science/physics ones were fairly easy to identify for me. Usually it would be one or two sentences that were grammatically cohesive but would make a statement that didn't make any sense if you had even a basic understanding of the topic. One that stood out to me was an astrophysics paper that said a planet was orbiting solar wind. I don't have to be a PhD to know that's BS.

The medical and biotech ones are much harder.

[jacquesm]

Yes, this mirrors my experience. Fields that have my interest are pretty easy in isolation (just looking at one subject), but fields that are remote can be a challenge.

[hervature]

In this instance, the medical and biotech generated stuff are much harder to identify because the algorithm doesn't need to introduce grammar issues. For instance, here is a random paper abstract that I changed, can you spot the change? Hint, it is one of the Greek symbols or a number.

Three highly pathogenic β-coronaviruses have crossed the animal-to-human species barrier in the past two decades: SARS-CoV, MERS-CoV and SARS-CoV-2. To evaluate the possibility of identifying antibodies with broad neutralizing activity, we isolated a monoclonal antibody, termed B4, that cross-reacts with eight β-coronavirus spike glycoproteins, including all five human-infecting β-coronaviruses.