Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mean Estimation on PPE Correctness
Loading...
0.26
MSE / PPI
LinearCal
0.2304
0.4302
0.63
0.8298
Apr 23, 2026
MSE / PPI
Label Savings
Coverage
Updated 1mo ago
Evaluation Results
Method
Method
Links
MSE / PPI
Label Savings
Coverage
LinearCal
n=400
2026.04
0.26
10.5
98.9
AutoCal
n=400
2026.04
0.263
10.2
98.8
Labeled-only
n=400
2026.04
0.299
0
98.8
LinearCal
n=100
2026.04
0.305
10.1
93.1
AutoCal
n=100
2026.04
0.31
9.4
92.9
Labeled-only
n=100
2026.04
0.346
0
92.7
AIPW
n=400
2026.04
0.405
0.9
94.1
AIPW
n=100
2026.04
0.774
0.9
90.6
PPI
n=100
2026.04
1
1
90.4
PPI
n=400
2026.04
1
2
92.4
Feedback
Search any
task
Search any
task