What Do Machine Learning Researchers Mean by "Reproducible"?
This work addresses a foundational issue for the AI/ML research community by providing clarity on reproducibility, which is crucial for improving research practices and mitigating the reproducibility crisis.
The paper tackles the ambiguity in the term 'reproducibility' in AI/ML research by clarifying its scope and categorizing related works into eight general topic areas, revealing that many relevant studies predate the recent focus on reproducibility.
The concern that Artificial Intelligence (AI) and Machine Learning (ML) are entering a "reproducibility crisis" has spurred significant research in the past few years. Yet with each paper, it is often unclear what someone means by "reproducibility". Our work attempts to clarify the scope of "reproducibility" as displayed by the community at large. In doing so, we propose to refine the research to eight general topic areas. In this light, we see that each of these areas contains many works that do not advertise themselves as being about "reproducibility", in part because they go back decades before the matter came to broader attention.