CausalForest DML Randomness

[silulyu]

Hi, we recently found that we get different prediction results every time we run the causal forest model with ite_estimates = model.effect(df[features]) ite_ci = model.effect_interval(df[features])

The model was pre-trained, saved and then loaded for predictions.

Is it because the effect() and effect_interval() methods often use bootstrap sampling to generate predictions, which introduces randomness?

How could I reproduce predictions with a CausalForest DML model?