The scope of assessing ideational consistency can be restricted to a specific field of modelling, or can extend across fields. It has two components, logical consistency and experiential consistency, both of which are
necessary for ideational consistency, but
neither of which is
sufficient in itself. That is, to be ideationally consistent, a model must be both logically consistent, internally and in relation to other models within the scope of meaning-making being assessed, and consistent in modelling experience, in its own terms and in relation to other models within the scope of meaning-making being assessed.
[1]
The scientific method is an attempt to restrict the selection of models to only those that are ideationally consistent. In the modelling of the simplest systems, the principal means of influencing selection — by increasing user certainty in a specific model — is the use of experiments that test the experiential consistency of those variants believed to be logically consistent. It is only in modelling the simplest of systems, or the simplest domains of systems, that the range of potential interpretations of experimental results is narrowed from many to manageably few.
Experiments are ostensibly designed to
falsify hypotheses, not to verify them.
[2] Indeed, for Popper, a model must be falsifiable to be considered scientific.
[3] Failing to falsify an hypothesis is failing to demonstrate an inconsistency between it and other models of which potential users are reasonably certain.
Footnotes:
[1] The point that a model has to fit with those of its time is exemplified by the case of Aristarchus of Samos (310-230BC) who proposed a heliocentric system of what we now call the solar system. It took 18 centuries for it to begin to fit, beginning with the work Copernicus (1473-1543), then Kepler (1571-1630), Galileo (1564-1642), and Newton (1642-1727).
[2] A common example of the misrepresentation of the experimental method is the situation where an experiment whose design does not provide a means of falsifying a model (or its rivals) is interpreted as a verification of the said model.
[3] A strict application of this principle would probably destroy most of what is regarded as scientific, including whole disciplines.
ChatGPT revised:
The scope of assessing ideational consistency can be restricted to a specific field of modelling or extended across fields. It has two necessary components: logical consistency and experiential consistency. Neither is sufficient on its own. For a model to be ideationally consistent, it must be both logically consistent — internally, and in relation to other models within the domain — and experientially consistent — in how it construes experience, both on its own terms and in relation to other models in the same scope of meaning-making.[1]
The scientific method is an attempt to restrict model selection to only those variants that are ideationally consistent. In modelling the simplest systems, the main selection pressure — the main influence on user certainty — is the experimental test of experiential consistency, applied only to those models already assessed as logically consistent. It is only in such simple systems, or simple domains of complex systems, that experimental interpretations can be reduced from many to a manageable few.
Experiments are ostensibly designed to falsify hypotheses, not to verify them.[2] For Popper, a model that cannot be falsified is not scientific.[3] To fail to falsify a hypothesis is merely to fail to demonstrate an inconsistency between it and other models in which users already have high certainty.