A continuous IRT model disentangles latent rider skill and condition difficulty from binary behavioral outcomes, anchored to an expert curve prior and validated on synthetic data.
Darrell and Aitkin, Murray , date =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Fine-tuned transformers with multi-task learning recover substantial wording-derived signal for item difficulty at small sample sizes typical in applied testing.
citing papers explorer
-
Inverse Suitability: Identifying Condition Difficulty and Rider Skill from Behavioural Outcomes via Continuous-Item Response Theory
A continuous IRT model disentangles latent rider skill and condition difficulty from binary behavioral outcomes, anchored to an expert curve prior and validated on synthetic data.
-
Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning
Fine-tuned transformers with multi-task learning recover substantial wording-derived signal for item difficulty at small sample sizes typical in applied testing.