Online documentation: peculiar LSS model for beta-series given as an example

Summary of what happened:

In the Nilearn documentation, some code is provided as an example of lss_transformer. However from the design matrix, original regressors are kept as different nuisance regressors in addition to the event_of_interest regressor. However, this is not how it was proposed in Mumford et al. (2012), where all original regressors are collapsed into a single nuisance regressor, regardless of the trial category.
Is there a reason why the lss_transformer example provided is different from the model proposed by Mumford et al ?

Command used (and if a helper script was used, a link to the helper script or the command generated):


Environment (Docker, Singularity, custom installation):

Data formatted according to a validatable standard? Please provide the output of the validator:

Relevant log outputs (up to 20 lines):

Screenshots / relevant information: