TSDR consistently improves calibration (ACC and RMSE) even on datasets where AUC gains plateau¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i? On Linux and Database, where AUC gains plateau, TSDR frequently reduces RMSE and improves ACC, including a 1.70% RMSE reduction for SparseKT on Linux. → Peilin Zhan 2026

Evidence¶

Peilin Zhan 2026¶

Peilin Zhan, Wei Chen, Weilin Chen, Shuyi Pan, Ruichu Cai. (2026). Temporal Smoothness Doubly Robust Learning for Debiased Knowledge Tracing. https://arxiv.org/abs/2605.05958 doi:10.48550/arxiv.2605.05958

q2 · i? · design · r2

Secondary-metric analysis (RQ1, Table 1) of ACC and RMSE across the nine benchmark datasets. The article reports TSDR "frequently reduces RMSE and improves ACC" with a "1.70% reduction for SparseKT on Linux."

"Even on datasets where AUC gains plateau, such as Linux and Database, TSDR fre- quently reduces RMSE and improves ACC. A specific exam- ple is the 1.70% reduction for SparseKT on Linux."

Discussion¶

Related Claims¶

• Current best learner performance models are severely biased outside the interval containing most of the data, hindering downstream adaptive policies and open learner models — the general claim this finding bears on, with the studies behind it
• TSDR improves the AUC of six state-of-the-art KT backbones across nine real-world benchmark datasets — related
• Under controlled synthetic MNAR bias, TSDR-equipped models improve across the entire bias spectrum, with the RMSE advantage diminishing beyond gamma > 0.8 — related
• In ablations, temporal smoothness works best on the imputation branch, and the full TSDR variant achieves the best AUC and ACC on all six backbones — related
• TSDR's AUC gains are largest on open-ended platforms and limited on EdNet, whose mandatory bundle completion policy constrains selection bias — related