Skip to content

ASSISTments2009, EdNet-KT1, and XES3G5M knowledge-tracing benchmark datasets

Product or Programme · All products and programmes
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

A set of publicly used learner–question interaction datasets from online tutoring and exercise platforms, used to develop and evaluate knowledge-tracing models.

Components

  • Three real-world KT benchmark datasets: ASSISTments2009, EdNet-KT1 and XES3G5M: The article evaluates MBP-KT on three widely-used educational datasets spanning different scales and sparsity levels: ASSISTments2009 (5,766 learners, 13,441 questions, 412,332 interactions, 99.47% sparsity), EdNet-KT1 (6,609 learners, 12,100 questions, 2,148,355 interactions, 97.31% sparsity), and XES3G5M (18,066 learners, 7,645 questions, 5,168,974 interactions, 96.26% sparsity). Evaluation used a single-point prediction protocol with maximum sequence length L=30, and sequences shorter than 5 interactions were filtered out. (Yuhao Jia et al. (2026))

Claims

-

Key Sources

  • Yuhao Jia, Duantengchuan Li, Jinsong Chen, Zhongjie Mao, Mingwen Tong, Yue Li, Xiaoguang Wang. (2026). MBP-KT: Learning Global Collaborative Information from Meta-Behavioral Pattern for Enhanced Knowledge Tracing. Preprint. https://arxiv.org/abs/2605.08697
Page metadata
Field Value
type product
id assistments2009-ednet-kt1-and-xes3g5m-knowledge-tracing-benchmark-datasets
title ASSISTments2009, EdNet-KT1, and XES3G5M knowledge-tracing benchmark datasets
description A set of publicly used learner–question interaction datasets from online tutoring and exercise platforms, used to develop and evaluate knowledge-tracing models.
status review
product_kind dataset
generated by process:settle-candidates on 2026-10-11
trust unverified — no one has confirmed this page's content

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