It has become a common pattern in our field: One group introduces a language\ntask, exemplified by a dataset, which they argue is challenging enough to serve\nas a benchmark. They also provide a baseline model for it, which then soon is\nimproved upon by other groups. Often, research efforts then move on, and the\npattern repeats itself. What is typically left implicit is the argumentation\nfor why this constitutes progress, and progress towards what. In this paper, we\ntry to step back for a moment from this pattern and work out possible\nargumentations and their parts.\n