PreprintarXiv licencearXiv
Interpretable Memory Models for Spaced Repetition
Abstract
Spaced repetition software schedules reviews with a memory model fit to review logs. Accuracy on a test set is not sufficient evidence of quality since available data are produced by existing schedulers, and new solutions must extrapolate beyond them. A model also needs a simple mechanistic interpretation. We present SBD, a model that is more interpretable and 80% smaller than the current state of the art at nearly the same accuracy.
Related
- The mammalian genome is punctuated by regularly spaced nucleosome islands
- Massively parallel characterization reveals context-dependent and non-additive regulatory effects of closely spaced variant pairs
- Impact of repetition on physical and imagined movements
- Forward reactivation in human hippocampal CA1 supports repetition learning and is preserved in the aging brain
- Input-space geometry shapes adaptation dynamics underlying repetition suppression in a neural network model of relatedness priming
BibTeX
@misc{schill2026interpretable,
title = {{Interpretable Memory Models for Spaced Repetition}},
author = {Anders Schill},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10548},
eprint = {2610.10548},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10548},
}
RIS
TY - UNPB
TI - Interpretable Memory Models for Spaced Repetition
AU - Anders Schill
PY - 2026
DA - 2026/10/01
PB - arXiv
DO - 10.48550/arxiv.2610.10548
UR - https://arxiv.org/abs/2610.10548
AB - Spaced repetition software schedules reviews with a memory model fit to review logs. Accuracy on a test set is not sufficient evidence of quality since available data are produced by existing schedulers, and new solutions must extrapolate beyond them. A model also needs a simple mechanistic interpretation. We present SBD, a model that is more interpretable and 80% smaller than the current state of the art at nearly the same accuracy.
ER -