All research
benchmarkIn progress
Spacing intervals at topic level, not card level
An in-progress evaluation of scheduling review by topic mastery rather than per-item, using StudyFlow's early cohort data.
- learning
- scheduling
- evaluation
Classical spaced repetition schedules individual items. Learners, however, forget topics — related items decay together, and scheduling them independently produces redundant review of things you clearly still know.
More research
- Attribution is not accuracyGrounded generation systems are routinely evaluated as if faithfulness to retrieved text were the same thing as being right. It is not. We separate the two and show where the confusion costs you.
- Latency budgets for interfaces that feel instantA practical set of per-interaction time budgets, and what we give up to hold them. Measured on the products in this lab rather than borrowed from a 1968 paper.