Knowing where something goes is not the same as knowing what it does.
Working manuscript · v0.1
The operator knows where the model goes. It doesn’t know what the model does.
OPEN
What would distinguish following a trajectory from reproducing the computation?
A useful experiment would compare both natural trajectories and responses to controlled changes. A result belongs in its own sourced record.
Experimental notebook / Working draft
Where this leaves the experiment
Predicting where a model’s trajectory goes and reproducing its computation are different capabilities.