EduStudio: Towards a unified library for student cognitive modeling

Student cognitive modeling is a fundamental task in the intelligence education field. It serves as the basis for various downstream applications, such as personalized educational content recommendation, adaptive testing, and so on. Cognitive Diagnosis (CD) and Knowledge Tracing (KT) are two mainstream categories for student cognitive modeling, which measure the cognitive ability from a limited time (e.g., an exam) and the learning ability dynamics over a long period (e.g., learning records from a year) respectively.

Recent efforts have been dedicated to the development of open-source code libraries for student cognitive modeling. However, existing libraries often focus on a particular category and overlook the relationships between them. Additionally, these libraries lack sufficient modularization, which hinders reusability.

To address these limitations, a research team led by Le Wu published their new research on 15 August 2025 in Frontiers of Computer Science co-published by Higher Education Press and Springer Nature.

The team developed a unified Pytorch-based library EduStudio, which unifies CD and KT for student cognitive modeling. The design philosophy of EduStudio is from two folds. From a horizontal perspective, EduStudio employs the modularization that separates the main step pipeline of each algorithm. From a vertical perspective, EduStudio uses templates with the inheritance style to implement each module.

Based on the design philosophy, the overall framework is illustrated in the diagram below. Steps 2–5 are four templatized modules, while steps 1 and 6 are common modules that are shared by all the models.

For the four templatized modules (i.e, Data Preparation, Model Implementation, Training Control, Model Evaluation), EduStudio abstracts the intricate elements within each module into various reusable templates.

Within each templatized module, EduStudio implements multiple templates with inheritance relationships. Each template inherits from a basic template prefixed with Base. These basic templates only provide basic functionalities to maintain the fundamental operation of the library.

With this templatized design, users can easily extend a new template within any module, enabling reusability when implementing new models.

There are also some eco-services of EduStudio, such as the repository that collects resources about student cognitive modeling and the leaderboard that demonstrates comparison among models. The detailed content is available at the official site https://edustudio.ai.

For the future direction, one is to implement models including more scenarios. Another is to refine and update the eco-services promptly.