Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

JOBS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Individual Treatment Effect EstimationJobs (out-of-sample)
R_pol0.733
32
Treatment Effect EstimationJOBS semi-synthetic (test)
MSE0
22
Individual Treatment Effect EstimationJobs (within-sample)
R_pol0.256
18
Counterfactual Error EstimationJobs (in-sample)
R_pol0.13
15
Conditional Average Treatment Effect (CATE) estimationJobs semi-synthetic
PEHE0.478
9
Bias EstimationJOBS (test)
Estimated alpha (alpha = 1)4.718
7
Partial identification of causal effectsJobs semi-synthetic RCT-derived labels
Validity100
6
Semantic ParsingJOBS
Accuracy92.9
6
Causal effect estimationJobs
ATT989.346
5
Semantic ParsingJOBS (test)
Precision97.3
3
Treatment Effect EstimationJobs
Coverage Mean93.48
1
Showing 11 of 11 rows