Gradient boosting can be applied to any base model, so doing it with a Quinlan-family decision tree (which allow for such higher-arity splits for categorical features) should make this possible. However, all implementations of gradient boosted trees that I know of (and certainly XGBoost, CatBoost, LightGBM) all use CART as their tree model, so you won't get ...
I posted the same question on the Catboost github (issues) page and got an answer.
The link can be found here: https://github.com/catboost/catboost/issues/1447
Class weights and weights in WKappa are different.
Calculation of WKappa metric consists of two steps:
Confusion matrix calculation - here object and class weights are used.
I'd like to confirm that this situation is not really something to worry about and I do not overfit the data.
No, the situation is not worrying, you can consider it worrying when the test error starts increasing. Normally an optimal model is a bit overfitted.
decision-tree based techniques always drill down the training data
Yes, your intuition is right. ...
You should worry about overfitting when the test error rate starts to go up again. Until then I would set it aside. Overfitting is rather about the number of parameters, e.g. When two models with the same performance have different number of parameters you would prefer the one with less parameters to preserve the generalisation power of the model.