Research

Only what we measured ourselves goes here.

Articles

One so far. More will be listed here.

Lexa — a cross-card in-context spaced-repetition model

MeasuredRetention-prediction accuracy, against the default settings of FSRS-7
WhenBenchmark run June 2026 / model version Lexa 3.0
ResultAhead on all three public benchmarks (+0.095 Duolingo, +0.050 maimemo, +0.036 Anki)
Read →

What it takes to be published here

We do not publish the conclusion alone. The baseline, the data and the metric sit in the same place as the number — a figure without its conditions can only ever flatter us.

A result is ready when a reader could follow the same steps and see the same thing. The measurement date and the version measured are always stated.

If we cannot produce a number, we do not claim a result. That is a constraint on us, not a feature.

The full standard (Approach, principle 03) →

Last updated: July 2026