Synthetic Benchmark
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Synthetic Benchmark 1.0 (test)
22.5Hit@2
56
Synthetic benchmark B=256 197 episodes, 907 queries
8.4Hit@2
10
Synthetic benchmark B=128 197 episodes, 907 queries
2.7Hit@2
10
Synthetic Benchmark Overall All Levels
1.57Average Speedup
7
Synthetic Benchmark Level 20
99Accuracy
7
Synthetic Benchmark (Level 5)
99Acc
7
Synthetic Benchmark Level 2
96Accuracy
7
Synthetic Benchmark Level 1
86.8Accuracy
7
synthetic benchmark
95Accuracy
7
Synthetic Benchmark
99.7Accuracy
7
Synthetic Benchmark
99.75Accuracy
7
synthetic benchmark
74.35Accuracy
7
synthetic benchmark
99.9Accuracy
7
Synthetic Benchmark
94.95Accuracy
7
synthetic benchmark 1.0 (test)
100Accuracy
7
Synthetic benchmark softplus aggregator nonlinear f (test)
0.365MAE
6
Synthetic benchmark semi-synthetic health data (test)
91Direction Accuracy
6
Synthetic benchmark (test)
28.1Test True Risk
6
Synthetic Benchmark range do(D) ∈ [-2.5, 2.5] (in-sample)
0.36RMSE
5
Synthetic benchmark with planted ground truth N=1,000, d=8 (test)
0.961R2
5
10 Synthetic Benchmark Datasets varying d from 10 to 500
96.3Mean SCOPE
5
Synthetic benchmark Mixed(3)
0.02Theta RMSE
5
Synthetic benchmark Sudden(3)
0.018RMSE (Theta)
5
Synthetic benchmark Drifting
0.014RMSE ($ heta$)
5
Synthetic Benchmark
0.013RMSE
5