An essential part of science is the ability to recreate the results of a given study as other scientists need to be able to verify and expand on it.
As Karl Popper stated in his book “The Logic of Scientific Discovery”: “Non-reproducible single occurrences are of no significance to science.”

The three R’s in the title can be used interchangeably as in the end they all mean that one should be able achieve the same results by repeating an experiment.
However, as research findings get published, this is often not properly ensured.
For instance, a paper might introduce a new AI model but without providing access to all the training data and all parameters, including the random seeding, the research is not reproducible.

I have given this talks in the context of a course on good scientific practice together with Simon Steuernagel, a fellow PhD student at the time.
The full slides of the talk can be found here: Slides.