Skip to content

Mnemosyne Flashcard Review Log Data

Element · All elements
Evidence · 4 claims (4 for) · 1 study (1 causal), q2 · 0 of 1 report an effect size · 4 claims rest on one study

Description

Large-scale log data from the Mnemosyne flashcard software, used by the article to compare memory models. After filtering, the authors select a random subset that "contains 859 , 591 interactions, 2, 742 users, and 88 , 892 items". Each interaction carries a self-reported 0-5 grade, which the authors discretize into binary recall, and models are compared by ten-fold cross-validated AUC and a held-out test set.

Design Implications

Context

Requirements

  • Filtering out users and items with fewer than five interactions.
  • Discretizing self-reported grades into binary recall outcomes and scaling review intervals to days.

Constraints

Target Learners

  • Users of the Mnemosyne flashcard software

Target Learning Goals

  • Validating memory models of recall as a function of reinforcement and delay

Claims

Examples

-

Key Sources

  • Reddy, S., Labutov, I., Banerjee, S., & Joachims, T. (2016). Unbounded Human Learning: Optimal Scheduling for Spaced Repetition. KDD ’16, San Francisco, CA, USA. https://doi.org/10.1145/2939672.2939850
Page metadata
Field Value
type element
id mnemosyne-flashcard-review-logs
title Mnemosyne Flashcard Review Log Data
description Large-scale log data from the Mnemosyne flashcard software, used by the article to compare memory models.
status review
canonical True
generated by claude/unspecified on 2026-09-24
trust unverified — no one has confirmed this page's content
sources 1 — reddy-2016

Frontmatter is the page's machine-readable record — see the Schema & Guide.