Haven’t read the paper (or looked at the code), but not sure there’s a general obligation to cite anything that’s not a pre-print/published. If they knew of and used the code, that would be a different story, but otherwise it seems okay, if understandably frustrating for the person that wrote the code.

This is especially the case for something like this where it’s a relatively obvious idea and the evaluation matters more.

I'm not in academia so forgive this for being a naive question: is it expected that if you publish a preprint, and someone comes to you with related work that you haven't studied/considered/used, that you then add a citation to that work?

They fail to follow scientific ethics by refusing to cite pre-existing art, so that they can claim novelty for their methods.

How many times has this happened? The corporate labs are erasing independent contributors from scientific history, by falsifying it.

Is your objection to the word "Novel" or to the refusal to reference your work?

If they were not aware of your work, which is the only reasonable assumption, then their work is original and independent research. Almost all work is novel, unless you're arguing they have literally copied your work.

Would you be happy if they dropped that single word?

They would only need to cite you if you're a source. Unless they mention your work or results of your work you're not a source. It feels like you're just giving reviewer feedback that they should improve their introduction by giving more context, which is a quality of writing issue not an ethical one.

If they were to mention you the reader would assume they knew about your work before publication, and the next question would be "why haven't they compared their model to their sources"

Simultaneous publication happens all the time, and it's entirely possible for both papers to be novel. Asking the slower paper to redo work and rewrite just isn't practical, and could be a never ending treadmill.