List your company
ResearchFormerly WizWand

Model diagnostic efficiency on LOMO behavioral dataset (held-out model fold)

1Kendall's TauUncertainty
-0.040.230.50.77Jun 3, 2026
Updated 4mo ago

Evaluation results

MethodLinks
UncertaintyN=5002026.061
IRT-adaptiveN=5002026.060.94
Bench.-strat.N=5002026.060.85
UncertaintyN=2502026.060.82
Taxonomy-cond.N=5002026.060.82
Bench.-strat.N=2502026.060.81
Taxonomy-cond.N=502026.060.81
RandomN=5002026.060.8
IRT-adaptiveN=2502026.060.79
Taxonomy-cond.N=2502026.060.79
Difficulty-strat.N=5002026.060.78
RandomN=2502026.060.76
Bench.-strat.N=1002026.060.76
Difficulty-strat.N=2502026.060.74
Taxonomy-cond.N=1002026.060.74
UncertaintyN=1002026.060.72
UncertaintyN=502026.060.66
Bench.-strat.N=502026.060.64
IRT-adaptiveN=1002026.060.62
IRT-adaptiveN=502026.060.58
RandomN=1002026.060.54
Difficulty-strat.N=1002026.060.44
RandomN=502026.060.34
Difficulty-strat.N=502026.060.34
Taxonomy-cond.N=102026.060.33
Taxonomy-cond.N=252026.060.33
RandomN=252026.060.31
Difficulty-strat.N=252026.060.31
UncertaintyN=252026.060.28
Bench.-strat.N=252026.060.24
Difficulty-strat.N=102026.060.03
RandomN=102026.060.02
Bench.-strat.N=102026.060
IRT-adaptiveN=102026.060
IRT-adaptiveN=252026.060
UncertaintyN=102026.060