In Mnemosyne flashcard log data, adding a delay term improves the recall-prediction performance of exponential forgetting curve memory models.¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2016 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person · overdue for a recheck since 2019: tool and model accuracy changes quickly

Subclaims¶

q2 i? Across paired exponential forgetting curve models with and without a delay term, incorporating the delay term improved predictive performance on Mnemosyne log data; no numeric AUC values are printed in the text. → Reddy 2016

Evidence¶

Reddy 2016¶

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

q2 · i? · associational · r2

Observational study of Mnemosyne flashcard log data, comparing memory models by cross-validated validation AUC. The first of four observations is that "Incorporating a delay term improves the performance of the memory model", shown by paired models in Fig. 2; the text prints no AUC values.

"Positive impact of delay term: Incorporating a delay term improves the performance of the memory model."

Discussion¶

Related Claims¶

• The survey reports, citing Pavlik et al., that no single knowledge tracing model was always the best, and that a better model must consider multiple student features and the learning context. — the general claim this finding bears on, with the studies behind it

• Memory-decay-based models fit fact-learning datasets better than models insensitive to memory decay — the general claim this finding bears on, with the studies behind it

• Spaced Repetition Improves Retention
• In Mnemosyne log data, exponential forgetting curve models that include a delay term perform comparably to 1PL-IRT, the best-performing benchmark model. — related
• In Mnemosyne log data, setting memory strength equal to an item's Leitner deck position predicts recall better than number of past reviews, which beats constant strength. — related
• In Mnemosyne log data, item-specific difficulty parameters outperform a global difficulty for lower and higher Leitner decks, while global difficulty performs better for intermediate decks. — related
• Repeated retrieval practice alters the rate at which learned items are forgotten, according to learn-to-criterion studies and forgetting-curve analyses the chapter reviews — related
• VeriForge's integrated workflow is associated with higher one-week delayed recall of domain terms and a higher retention rate (exploratory) — related