Model-dependent realism

In philosophy, model-dependent realism asserts that all we can know about "reality" consists of networks of world pictures that explain observations by connecting them by rules to concepts defined in models.

A world picture consists of the combination of a set of observations accompanied by a conceptual model and by rules connecting the model concepts to the observations. Different world pictures that describe particular data equally well all have equal claims to be valid. There is no requirement that a world picture be unique, or even that the data selected include all available observations. The universe of all observations possibly may be covered by a network of overlapping world pictures and, where overlap occurs; multiple, equally valid, world pictures exist, a form of ontological pluralism.

As a philosophical position, model-dependent realism is not a strict form of metaphysical realism (the world is as it is, independently of how humans take it to be), but contains features of the anti-realist position that the world is mind-dependent. Like some anti-realist positions, model-dependent realism accepts conceptual relativism, the view that having multiple world-pictures that include the same observations is not a difficulty. However, the notion that the "world is as it is, independently of how humans take it to be" is not abandoned explicitly, but replaced by the notion that whatever the world may be, all we can know of it is conceptually relative, a network of overlapping world pictures.

Outline

Recently the connection between models and observations has been explored by physicists Stephen W. Hawking and Leonard Mlodinow in their book: The Grand Design, where they propose the notion of model-dependent realism, a view of reality based upon world pictures. Hawking/Mlodinow introduce a world picture as follows:

... a physical theory or world picture is a model (generally of a mathematical nature) and a set of rules that connect the elements of the model to observations. This provides a framework with which to interpret modern science.

This quotation defines a "world picture". The concept of model entering a "world picture" is extended to a wider class of mental concepts in the metaphysical position of model-dependent realism as proposed below:

According to the idea of model-dependent realism...our brains interpret the input from our sensory organs by making a model of the outside world. We form mental concepts of our home, trees, other people, the electricity that flows from wall sockets, atoms, molecules, and other universes. These mental concepts are the only reality we can know. There is no model-independent test of reality. It follows that a well-constructed model creates a reality of its own.

Hawking/Mlodinow point out:

• that either an earth-centered (Ptolemaic) or a sun-centered (Copernican) picture of reality can be made consistent with the motion of celestial bodies;
• that goldfish physicists living in a curved bowl, though observing curved paths of motion of bodies that we observe as linear, could still formulate predictive laws governing motion as they see it;
• that we cannot know whether we live in a simulated world, a virtual reality, one that the simulators rendered self-consistent.

Each of those world pictures is not only data-dependent, but is explanation-dependent.

In comparing different world pictures,

According to model-dependent realism, it is pointless to ask whether a model is real, only whether it agrees with observation. If there are two models that both agree with observation,...then one cannot say that one is more real than another. (pp. 45-46)

If two different models agree with the observations, to say that one gives a truer picture of reality than the other involves considerations outside model-independent reality, to consider possibly subjective matters such as which model may be the more convenient to employ in a given situation, the more elegant, the more intriguing, or otherwise appear more appealing.

It should be noted that Hawking/Mlodinow say (p. 7):

In the history of science we have discovered a sequence of better and better theories or models...Will this sequence eventually reach an end point,...or will we continue forever finding better theories, but never one that cannot be improved upon? We do not yet have a definitive answer to this question,...

which raises the prospect that an ultimate world picture of "reality" might be approachable, though perhaps never reached.

Some find the ambiguity introduced by alternative equivalent world pictures to be a defect of the concept of model-dependent realism. That position, however, is based upon outside criteria, and an example of such criteria is provided shortly.

It should be emphasized that there is no restriction that a model use only observable or measurable constructs. The alternatives:

Do unobservable theoretical entities such as quarks and gluons really exist in the physical world, as objective entities independent of human will, or exist merely as human constructions for their utility in organizing our experience and predicting future events?

are addressed by Hawking/Mlodinow in their definition of a model as follows:

QCD [Quantum chromodynamics] also has a property called asymptotic freedom, which we referred to, without naming it, in Chapter 3. Asymptotic freedom means that the strong forces between quarks are small when the quarks are close together but increase if they are farther apart, rather as though they were joined by rubber bands. Asymptotic freedom explains why we don’t see isolated quarks in nature and have been unable to produce them in the laboratory. Still, even though we cannot observe individual quarks, we accept the model because it works so well at explaining the behavior of protons, neutrons, and other particles of matter [Emphasis added].

Therefore, the definition of a model adopts any unobservable constructs as aspects of the reality "created" by that model. With this interpretation of a model, the alternatives posed by Cao above are confronted by the metaphysical position of model-dependent realism first by rejection of any posit of "objective" reality beyond world pictures or networks of world pictures that organize experience, and second, like the world pictures themselves, model-dependent realism accepts any unobservable entities in the models used by these world pictures as part of the reality included in model-dependent realism.

Background

The "reality" of science, even when restricted to the interpretation of observations and measurements, has been much discussed. Pierre Duhem (1861-1916) held that a physical model is no more than an aid to memory, summarizing and classifying facts by providing a symbolic representation of them and, moreover, the facts of physical theory are to be distinguished from common sense and metaphysics. His views were further developed by W. V. O. Quine (1908-2000), who suggested "“our statements about the external world face the tribunal of sense experience not individually, but only as a corporate body”. It is impossible to test a scientific hypothesis in isolation, but only as part of a system. These two authors were much concerned with how a theory was coupled to concrete observation and measurement, and how it morphed with admission of new data.

The evolution of science forms part of this discussion. For example, Thomas Kuhn connected changes in scientists' views of reality to "revolutions" in science and changes in "paradigms". As an example, Kuhn suggested that the Copernican "revolution" replaced the views of Ptolemy not because of empirical failures, but because of a new "paradigm" that exerted control over what scientists felt to be the more fruitful way to pursue their goals. Such historical analysis goes beyond the concept of a world picture itself to critique competing world pictures, and to assess how changes in ways to evaluate a world picture affect its influence over the development of knowledge. One aspect in the assessment of competing theories is the pragmatic question of which criteria indicate a fruitful path forward. These matters belong to the fields sociology of science and cognitive science.

The matter is made more complicated by attempts to extend observations of scientific practice to wider realms, including religious systems, in an attempt to compare them. A key author in this arena was Barbour who proposed an approach called critical realism. The word "critical" refers to reflection and analysis. This broad extension lies outside the realm of model-dependent realism itself, and falls into a much vaguer and more tendentious arena.

Model assessment

Many world pictures or theories may be proposed, and the issue of comparing, ranking, and generally critiquing them arises.

For example, quantum mechanics, which is a world picture or theory describing (among other matters) atomic interactions using a mathematical model of Hilbert space, is commonly called incomplete, despite its experimental success, as it is "not accompanied by an interpretation that is widely convincing." Steven Pinker discusses this question using several quotations, including one from Murray Gell-Mann that describes quantum theory as: "that mysterious, confusing discipline which none of us really understands but which we know how to use." These reservations about quantum mechanics appear to seek something more than a world picture, what might be called physical intuition, or visualization.

Hawking/Mlodinov do not address the intuitive qualities of a world picture or theory, or scientists' personal opinions of them, but they do raise the question of what constitutes a good theory. They suggest a good theory has these characteristics,(p. 51), compared in parentheses to the criteria of Colyvan:

1. It is elegant (Formal elegance; no ad hoc modifications)
2. Contains few arbitrary or adjustable elements (Simplicity/Parsimony)
3. Agrees with and explains all existing observations (Unificatory/Explanatory power)
4. Makes detailed predictions about future observations that can disprove or falsify the model if they are not borne out. (Boldness/Fruitfulness: the emphasis by Colyvan is not only upon prediction and falsification, but also upon pregnancy for future work.)

Hawking/Mlodinov note that "If the modifications needed to accommodate new observations become too baroque, it signals the need for a new model." Of course, judgment about what is 'baroque' is somewhat subjective.

The features of a "good" theory have been debated for centuries, going back perhaps even earlier than Occam's razor, which often is taken as an attribute of a good theory. Occam's razor might fall under the heading of "elegant", the first item on the list. The last item on the list is related to the criterion proposed by Popper:

It must be possible for an empirical scientific system to be refuted by experience. (p. 18) Those among us who are unwilling to expose their ideas to the hazard of refutation do not take part in the game of science. (p. 280)

Richard Feynman also expressed this view: "Of course, relativity is deeper than this [referring to a simplistic statement] because we can make definite predictions with it."

Five somewhat similar criteria were proposed by Kuhn as what he called "the shared basis for theory choice", a list selected "not because they are exhaustive, but because they are individually important and collectively sufficiently varied to indicate what is at stake." Another list is discussed by Colyvan.

These desiderata of a "good theory" allow a critique of different theories. Although the various lists of criteria for a good model are very similar, (those of Hawking/Mlodinow, or Kuhn, or Colyvan, for example) and according to their various authors are widely acknowledged, they are only heuristic. Worrall points out "One reason why these criteria do not supply a choice algorithm is that in live cases of theory choice, and, in particular, during scientific revolutions, these different criteria seldom, if ever, tell in the same direction. Much later, once the revolutionary theory has been developed and improved, it may outscore its older rival on all counts - but this happens as a result of the revolution and therefore can't form its rationale." Some argue, nonetheless, that "principles of comparison" may have a justification beyond mere general acceptance.

Unfortunately, even the most successful world picture of modern science, the Standard Model of particle physics, satisfies only the last of the Hawking/Mlodinov criteria. As said by Hawking/Mlodinov (p. 52):

..many people view the "standard model" ...as inelegant. ...it contains dozens of adjustable parameters whose values must be fixed to match observations, rather than being determined by the theory itself.

The Standard Model fails the third criterion in not encompassing gravitation. Hawking/Mlodinov (p. 58) deal with the failure of a theory to encompass all observations using the notion of a network of overlapping theories, each describing some observations and agreeing with one another where the theories overlap. To quote:(p. 58):

No single theory within the network can describe every aspect of the universe... Though this situation does not fulfill the traditional physicists' dream of a single unified theory, it is acceptable within the framework of model-dependent realism.

Presumably, each theory or world picture included in a network provides concepts for a "model-dependent reality", though that reality is restricted to the domain of data to which it applies. Where these model-dependent realities overlap, multiple interpretations of reality are available of equal value.

Data collection

...the measuring device has been constructed by the observer, and we have to remember that what we observe is not nature in itself but nature exposed to our method of questioning. —Werner Heisenberg, Physics and Philosophy

The definition of a model given by Hawking/Mlodinow is pretty straightforward if one has in mind a particular set of data to explain. Either the model explains the data or it doesn't, and if two models explain the data differently, any claim for the concepts employed by either as more true of "reality" must be based upon criteria lying outside the reach of model-dependent reality, such as the desiderata for a "good" theory listed earlier.

The matter is less clear when one considers the selection of just what "data" must be explained. Our senses are limited, and we accept that we cannot see and hear everything that comprises reality. So we supplement the senses, for example, by using a telescope or a microscope. Historically the issue arose as to whether such instruments deceived us, and gradually they have been accepted as extensions of our natural capacities.

The gathering of "data" supplementing our senses has gone far beyond the primitive telescope to its modern version (for example, the Hubble telescope) and the microscope to its modern version (for example, the scanning tunneling microscope). Today experiments may require expensive apparatus not available to all, involving observations not even interpretable by many. Examples are the colliders of high-energy physics, and the sophisticated electronic image acquisition of modern astronomy, guided by elaborate computer processing and filtering. One might reasonably ask how well the acquisition of "data" is separated from the "theory" that explains how the acquisition process works, and that often suggests where to look for new "data". Communication and critique of results becomes restricted to a narrow audience of technically oriented specialists, and those outside this group become irrelevant. The process by which data is allowed into the theory influences what is incorporated into "reality".

The gathering of data is complicated by the limited access to these data-acquisition instruments, both in a required training that could be seen as indoctrination (not necessarily deliberate, but de facto), and in limitations upon who, and what investigations, are worthy to use the instruments, as determined by various funding agencies and corporate laboratories. Although censorship is not the motivation directing government and corporate support, a preoccupation with popular and/or commercially attractive projects draws resources and talent away from less conspicuous goals potentially of more significance to a comprehensive "reality". In effect, the expense and expertise of modern research result in blinkers.

The analysis as well as the gathering of data is becoming more complicated as our very notion of thinking, even of mathematical proof, is modified by technology, for example, by computers. Theoretical predictions are made by computer simulations that perform calculations beyond human capacity. The concepts entering a model-based reality may be only implicit in a computer programmable code, in open-ended algorithms, and may not be concepts the human mind is aware of directly.

To a limited degree, the shaping of "reality" based upon modeling of selected data is a public enterprise, with all the foibles that implies. The public does not engage reality at a specialized deeply technical level, but at a metaphoric level:

All theories have metaphorical dimensions...that give depth and meaning to scientific ideas, that add to their persuasiveness and color the way we see reality."

An explicitly metaphoric public participation is "eco-consciousness". Metaphorical involvement also is evident in arenas such as gene research and genetically altered organisms, and investigations of stem cells, where the public is actively engaged. Another example is archaeology and the limitations exerted upon examination of burial sites. In some cases public participation leads to simple clamor, as in the case of global warming. This broad public engagement, frequently informed by vested interests and oversimplifications, facilitates manipulation by groups with their own objectives, similar to the censorship found in the times of Vesalius and Galileo although lacking some of that institutional authority.

Although the above examples suggest an indictment of metaphor as a foible of public participation in shaping reality, public engagement in some form is necessary and desirable, and ultimately a goal of the entire enterprise.