From working in industry and rubbing shoulders with CS people who prioritize writing papers over writing working software I’m sure that in a high fraction of papers people didn’t implement the algorithm they thought they implemented.

Don't get me started, I have seem repos that I'm fairly sure never ran in their presented form. A guy in our lab thinks authors purposefully mess up their code when publishing on GitHub to make it harder to replicate. I'm starting to come around on his theory.