The methods for creating a new data description that inherits most of the fields from the input data description should really only get used in established processing pipelines and a few other limited circumstances (ie the experimenter is testing a new processing approach).
Currently these methods seem like they should be used for any derived data asset, but we are clarifying in the software docs that this often doesn't apply (analysis that aggregates many inputs, or a new investigator/project reusing data from a different source).
The methods for creating a new data description that inherits most of the fields from the input data description should really only get used in established processing pipelines and a few other limited circumstances (ie the experimenter is testing a new processing approach).
Currently these methods seem like they should be used for any derived data asset, but we are clarifying in the software docs that this often doesn't apply (analysis that aggregates many inputs, or a new investigator/project reusing data from a different source).