Re-evaluation under controlled protocols shows that attention-enhanced PKT models do not consistently outperform standard DKT on the CodeWorkout dataset.
Revisiting knowledge tracing: A simple and powerful model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Ensuring Reliability in Programming Knowledge Tracing: A Re-evaluation of Attention-augmented Models and Experimental Protocols
Re-evaluation under controlled protocols shows that attention-enhanced PKT models do not consistently outperform standard DKT on the CodeWorkout dataset.