Mimic / Surrogate

Reported on 4 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology4 results

regressiononConcrete Compressive Strength
R2 Score· 2025-06-13
0.5821
best: 0.8588 (Neural Network)
Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth arXiv:2506.12176
regressiononMedical Cost Personal Dataset
R2 Score· 2025-06-13
0.7835
best: 0.8673 (Neural Network)
Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth arXiv:2506.12176
regressiononSynthetic: y = x * sin x
R2 Score· 2025-06-13
-0.0137
best: 0.9755 (Neural Network)
Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth arXiv:2506.12176
regressiononCalifornia Housing Prices
R2 Score· 2025-06-13
0.5658
best: 0.7908 (Neural Network)
Fidelity Isn't Accuracy: When Linearly Decodable Functions Fail to Match the Ground Truth arXiv:2506.12176