Expired50% confidenceBenchmarkExact time
The open-source project FSRS incorporates Bayesian inference and machine learning, training on millions of real review data points, and significantly outperforms SM-2 in memory prediction accuracy.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/11/2026
First Seen
Valid until: 10/9/2026(expired)
Sources
闪卡学习法：间隔重复的科学原理与高效实践指南
hackernewshackernews7/10/2026
Related Claims
UnverifiedThe FSRS algorithm uses machine learning to fit users' actual memory curves and is approximately 30%–40% more accurate than SM-2 in predicting forgetting probability.77% similarUnverifiedMachine learning systems automatically discover patterns through training on large amounts of data and make generalized predictions on new data.72% similarUnverifiedDream Engine通过训练机器学习模型高保真预测算法和实现在任意查询类型上的性能，模型基于Databricks十年积累的千万亿数据点查询trace69% similarUnverified对于基于梯度提升树（如XGBoost）的传统机器学习模型，SHAP值、LIME等可解释性工具已相当成熟67% similarUnverifiedReinforcement Learning from Verifiable Rewards (RLVR) has become an important path for enhancing model reasoning capabilities and is one of the key factors behind the capability leaps of several frontier reasoning models67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/486992API
curl https://kongchang.com/api/v1/knowledge/claims/486992MCP
get_claim(id=486992)