some of the curves “jump out” of the graph area. What is wrong?
This was a harmless bug in the algorithm in SuperMemo 98/99. The assumption is that intervals cannot grow beyond the value of A-Factor. For that reason, the maximum R-Factor should equal the relevant A-Factor. However, in plotting the forgetting curves, higher values of U-Factors are used as repetitions may be delayed (e.g. with Mercy, user procrastination, etc.). The algorithm puts a cap on the maximum R-Factor value (along the theoretical assumption that R-Factors cannot be greater than corresponding A-Factors). However, the implementation used the maximum U-Factor value as the cap (the one used in plotting the forgetting curve). Consequently, R-Factors could grow larger than A-Factors and the curve would “jump out” of the graph, which displays the correct cap. This bug should have little effect on the learning process. The higher cap does not invalidate the correctness of R-Factors. It just does not prevent very long intervals in case of very good repetition results.
