Enhancing Spaced Repetition with Content-Aware Memory Models

Spaced repetition systems are powerful, but they have a fundamental blind spot: they don’t understand what your flashcards are about.

To your SRS, a card asking 'what’s the capital of Italy?' and another asking 'what country is Rome the capital of?' are treated independently, each with its own isolated review history.

At the heart of every SRS is a memory model which predicts how long you’ll remember each card based on your past performance. Most of today’s models ignore the content of the card.