Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.03246 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917383624458240 |
|---|---|
| author | Beauchesne, Jocelyn Maroti, Christine Bratman, Jeshua Pesenti, Jerome Holt, Laurence Tambellini, Alex McGrath, Allison Guo, Matthew Peterson, Sarah |
| author_facet | Beauchesne, Jocelyn Maroti, Christine Bratman, Jeshua Pesenti, Jerome Holt, Laurence Tambellini, Alex McGrath, Allison Guo, Matthew Peterson, Sarah |
| contents | Recent research demonstrated that students exhibit consistent learning rates across diverse educational contexts. We test these findings using a dataset of 1.8 million (366k post-filtering) student interactions from the digital platform Campus AI providing further evidence to the observation of regularity in learning rate among students. Unlike prior work requiring manual cognitive modeling, Campus AI automatically generates Knowledge Components (KCs) and corresponding exercises, both of which are validated by human experts. This one-to-many mapping facilitates the application of Additive Factors Models to measure learning parameters without complex cognitive modeling.
Using mixed-effects logistic regression, we confirmed the core finding of prior work: students displayed substantial variation in initial knowledge ($\text{IQR} = [2.78, 12.18]$ practice opportunities to reach 80% mastery) but remarkably consistent learning rates ($\text{IQR} = [7.01, 8.25]$ opportunities). Furthermore, students using this fully automated system achieved 80% mastery in a median of 7.22 practice opportunities, comparable to the 6.54 reported for expert-designed curricula. These results suggest that automated, science-grounded content generation can support effective personalized learning at scale. Data and code are publicly available. https://github.com/Campus-edu-AI/learning-rate |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_03246 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Personalized AI Practice Replicates Learning Rate Regularity at Scale Beauchesne, Jocelyn Maroti, Christine Bratman, Jeshua Pesenti, Jerome Holt, Laurence Tambellini, Alex McGrath, Allison Guo, Matthew Peterson, Sarah Computers and Society Artificial Intelligence Recent research demonstrated that students exhibit consistent learning rates across diverse educational contexts. We test these findings using a dataset of 1.8 million (366k post-filtering) student interactions from the digital platform Campus AI providing further evidence to the observation of regularity in learning rate among students. Unlike prior work requiring manual cognitive modeling, Campus AI automatically generates Knowledge Components (KCs) and corresponding exercises, both of which are validated by human experts. This one-to-many mapping facilitates the application of Additive Factors Models to measure learning parameters without complex cognitive modeling. Using mixed-effects logistic regression, we confirmed the core finding of prior work: students displayed substantial variation in initial knowledge ($\text{IQR} = [2.78, 12.18]$ practice opportunities to reach 80% mastery) but remarkably consistent learning rates ($\text{IQR} = [7.01, 8.25]$ opportunities). Furthermore, students using this fully automated system achieved 80% mastery in a median of 7.22 practice opportunities, comparable to the 6.54 reported for expert-designed curricula. These results suggest that automated, science-grounded content generation can support effective personalized learning at scale. Data and code are publicly available. https://github.com/Campus-edu-AI/learning-rate |
| title | Personalized AI Practice Replicates Learning Rate Regularity at Scale |
| topic | Computers and Society Artificial Intelligence |
| url | https://arxiv.org/abs/2604.03246 |