This article discusses minimal model explanations, which we argue are distinct from various causal, mechanical, difference-making, and so on, strategies prominent in the philosophical literature. We contend that what accounts for the explanatory power of these models is not that they have certain features in common with real systems. Rather, the models are explanatory because of a story about why a class of systems will all display the same large-scale behavior because the details that distinguish them are irrelevant. This story (...) explains patterns across extremely diverse systems and shows how minimal models can be used to understand real systems. (shrink)

Explainable AI (xAI) methods are important for establishing trust in using black-box models. However, recent criticism has mounted against current xAI methods that they disagree, are necessarily false, and can be manipulated, which has started to undermine the deployment of black-box models. Rudin (2019) goes so far as to say that we should stop using black-box models altogether in high-stakes cases because xAI explanations ‘must be wrong’. However, strict fidelity to the truth is historically not a desideratum in science. Idealizations (...) – the intentional distortions introduced to scientific theories and models – are commonplace in the natural sciences and are seen as a successful scientific tool. Thus, it is not falsehood qua falsehood that is the issue. In this paper, I outline the need for xAI research to engage in idealization evaluation. Drawing on the use of idealizations in the natural sciences and philosophy of science, I introduce a novel framework for evaluating whether xAI methods engage in successful idealizations or deceptive explanations (SIDEs). SIDEs evaluates whether the limitations of xAI methods, and the distortions that they introduce, can be part of a successful idealization or are indeed deceptive distortions as critics suggest. I discuss the role that existing research can play in idealization evaluation and where innovation is necessary. Through a qualitative analysis we find that leading feature importance methods and counterfactual explanations are subject to idealization failure and suggest remedies for ameliorating idealization failure. (shrink)

Abstraction and idealization are the two notions that are most often discussed in the context of assumptions employed in the process of model building. These notions are also routinely used in philosophical debates such as that on the mechanistic account of explanation. Indeed, an objection to the mechanistic account has recently been formulated precisely on these grounds: mechanists cannot account for the common practice of idealizing difference-making factors in models in molecular biology. In this paper I revisit the debate and (...) I argue that the objection does not stand up to scrutiny. This is because it is riddled with a number of conceptual inconsistencies. By attempting to resolve the tensions, I also draw several general lessons regarding the difficulties of applying abstraction and idealization in scientific practice. Finally, I argue that more care is needed only when speaking of abstraction and idealization in a context in which these concepts play an important role in an argument, such as that on mechanistic explanation. (shrink)

One can find in the literature two sets of views concerning the relationship between understanding and explanation: that one understands only if 1) one has knowledge of causes and 2) that knowledge is provided by an explanation. Taken together, these tenets characterize what I call the narrow knowledge account of understanding. While the first tenet has recently come under severe attack, the second has been more resistant to change. I argue that we have good reasons to reject it on the (...) basis of theoretical models that provide how-possibly explanations. These models, while they do not explain in the strict sense, afford understanding. In response, I propose an alternative epistemology of understanding, broad KAU, that takes cases of theoretical modelling into account. (shrink)

How can we use models to understand real phenomena if models misrepresent the very phenomena we seek to understand? Some accounts suggest that models may afford understanding by providing causal knowledge about phenomena via how-possibly explanations. However, general equilibrium models, for example, pose a challenge to this solution since their contribution appears to be purely mathematical results. Despite this, practitioners widely acknowledge that it improves our understanding of the world. I argue that the Arrow–Debreu model provides a mathematical how-possibly explanation (...) which establishes claims of mathematical dependence. The account developed reveals how mathematical knowledge can inform claims about the world, allow ‘what-if-things-had-been-different’ inferences, and thus improve our understanding. (shrink)

One puzzle concerning highly idealized models is whether they explain. Some suggest they provide so-called ‘how-possibly explanations’. However, this raises an important question about the nature of how-possibly explanations, namely what distinguishes them from ‘normal’, or how-actually, explanations? I provide an account of how-possibly explanations that clarifies their nature in the context of solving the puzzle of model-based explanation. I argue that the modal notions of actuality and possibility provide the relevant dividing lines between how-possibly and how-actually explanations. Whereas how-possibly (...) explanations establish claims of possible explanations, how-actually explanations establish claims of actual ones. Models, in turn, simply provide evidence for these claims. (shrink)

Sometimes, scientific models are either intended to or plausibly interpreted as representing nonactual but possible targets. Call this “hypothetical modeling”. This paper raises two epistemological challenges concerning hypothetical modeling. To begin with, I observe that given common philosophical assumptions about the scope of objective possibility, hypothetical models are fallible with respect to what is objectively possible. There is thus a need to distinguish between accurate and inaccurate hypothetical modeling. The first epistemological challenge is that no account of the epistemology of (...) hypothetical models seems to cohere with the most characteristic function of scientific modeling in general, i.e., surrogative representation. The second epistemological challenge is a version of “reliability challenges” familiar from other areas. There is a challenge to explain how hypothetical models could be a reliable guide to what is possible, given that they are not and cannot be compared against their nonactual targets and updated accordingly. I close with some brief remarks on possible solutions to these challenges. (shrink)

Simple idealized models seem to provide more understanding than opaque, complex, and hyper-realistic models. However, an increasing number of scientists are going in the opposite direction by utilizing opaque machine learning models to make predictions and draw inferences, suggesting that scientists are opting for models that have less potential for understanding. Are scientists trading understanding for some other epistemic or pragmatic good when they choose a machine learning model? Or are the assumptions behind why minimal models provide understanding misguided? In (...) this paper, using the case of deep neural networks, I argue that it is not the complexity or black box nature of a model that limits how much understanding the model provides. Instead, it is a lack of scientific and empirical evidence supporting the link that connects a model to the target phenomenon that primarily prohibits understanding. (shrink)

Philosophers of science have recently taken care to highlight different modeling practices where scientific models primarily contribute modal information, in the form of for example possibility claims, how-possibly explanations, or counterfactual conditionals. While examples abound, comparatively little attention is being paid to the question of under what conditions, and in virtue of what, models can perform this epistemic function. In this paper, we firstly delineate modal modeling from other modeling practices, and secondly reviewattempts to spell out and explain the epistemic (...) success conditions of modal modeling. The aim is to more clearly expose the respective justificatory strategies of these accounts, and secondly, to identify lacunae where further work is needed. (shrink)

Relationships of counterfactual dependence have played a major role in recent debates of explanation and understanding in the philosophy of science. Usually, counterfactual dependencies have been viewed as the explanantia of explanation, i.e., the things providing explanation and understanding. Sometimes, however, counterfactual dependencies are themselves the targets of explanations in science. These kinds of explanations are the focus of this paper. I argue that “micro-level model explanations” explain the particular form of the empirical regularity underlying a counterfactual dependency by representing (...) it as a physical necessity on the basis of postulated microscopic entities. By doing so, micro-level models rule out possible forms the regularity could have taken. Micro-model explanations, in other words, constrain empirical regularities and their associated counterfactual dependencies. I introduce and illustrate micro-level model explanations in detail, contrast them to other accounts of explanation, and consider potential problems. (shrink)

Within the modeling literature, there is often an implicit assumption about the relationship between a given model and a scientific explanation. The goal of this article is to provide a unified framework with which to analyze the myriad relationships between a model and an explanation. Our framework distinguishes two fundamental kinds of relationships. The first is metaphysical, where the model is identified as an explanation or as a partial explanation. The second is epistemological, where the model produces understanding that is (...) related to the explanation of interest. Our analysis reveals that the epistemological relationships are not always dependent on the metaphysical relationships, contrary to what has been assumed by many philosophers of science. Moreover, we identify several importantly different ways that scientific models instantiate these relationships. We argue that our framework provides novel insights concerning the nature of models, explanation, idealization, and understanding. (shrink)

Catherine Elgin has recently argued that a nonfactive conception of understanding is required to accommodate the epistemic successes of science that make essential use of idealizations and models. In this paper, I argue that the fact that our best scientific models and theories are pervasively inaccurate representations can be made compatible with a more nuanced form of scientific realism that I call Understanding Realism. According to this view, science aims at (and often achieves) factive scientific understanding of natural phenomena. I (...) contend that this factive scientific understanding is provided by grasping a set of true modal information about the phenomenon of interest. Furthermore, contrary to Elgin’s view, I argue that the facticity of this kind of scientific understanding can be separated from the inaccuracy of the models and theories used to produce it. (shrink)

This paper analyzes two ways idealized biological models produce factive scientific understanding. I then argue that models can provide factive scientific understanding of a phenomenon without providing an accurate representation of the features of their real-world target system. My analysis of these cases also suggests that the debate over scientific realism needs to investigate the factive scientific understanding produced by scientists’ use of idealized models rather than the accuracy of scientific models themselves.

In this paper, we argue that rather than exclusively focusing on trying to determine if an idealized model fits a particular account of scientific explanation, philosophers of science should also work on directly analyzing various explanatory schemas that reveal the steps and justification involved in scientists’ use of highly idealized models to formulate explanations. We develop our alternative methodology by analyzing historically important cases of idealized statistical modeling that use a three-step explanatory schema involving idealization, mathematical operation, and explanatory interpretation.

Evolutionary explanations are not only common in the biological sciences, but also widespread outside biology. But an account of how evolutionary explanations perform their explanatory work is still lacking. This paper develops such an account. I argue that available accounts of explanations in evolutionary science miss important parts of the role of history in evolutionary explanations. I argue that the historical part of evolutionary science should be taken as having genuine explanatory force, and that it provides how‐possibly explanations sensu Dray. (...) I propose an account of evolutionary explanations as comparative‐composite explanations consisting of two distinct kinds of explanations, one processual and one historical, that are connected via the explanandum's evolvability to show how the explanandum is the product of its evolutionary past. The account is both a reconstruction of how evolutionary explanations in biology work and a guideline specifying what kind of explanations evolutionary research programs should develop. (shrink)

There is increasing attention to the centrality of idealization in science. One common view is that models and other idealized representations are important to science, but that they fall short in one or more ways. On this view, there must be an intermediary step between idealized representation and the traditional aims of science, including truth, explanation, and prediction. Here I develop an alternative interpretation of the relationship between idealized representation and the aims of science. In my view, continuing, widespread idealization (...) calls into question the idea that science aims for truth. I argue that understanding must replace truth as the ultimate epistemic aim of science. Additionally, science has a wide variety aims, epistemic and non-epistemic, and these aims motivate different kinds of scientific products. Finally, I show how these diverse aims---all rather distant from truth---result in the expanded influence of social values on science. (shrink)

How can a reflective scientist put forward an explanation using a model when they are aware that many of the assumptions used to specify that model are false? This paper addresses this challenge by making two substantial assumptions about explanatory practice. First, many of the propositions deployed in the course of explaining have a non-representational function. In particular, a proposition that a scientist uses and also believes to be false, i.e. an “idealization”, typically has some non-representational function in the practice, (...) such as the interpretation of some model or the specification of the target of the explanation. Second, when an agent puts forward an explanation using a model, they usually aim to remain agnostic about various features of the phenomenon being explained. In this sense, explanations are intended to be autonomous from many of the more fundamental features of such systems. I support these two assumptions by showing how they allow one to address a number of recent concerns raised by Bokulich, Potochnik and Rice. In addition, these assumptions lead to a defense of the view that explanations are wholly true that improves on the accounts developed by Craver, Mäki and Strevens. (shrink)

The use of idealized scientific theories in explanations of empirical facts and regularities is problematic in two ways: they don’t satisfy the condition that the explanans is true, and they may fail to entail the explanandum. An attempt to deal with the latter problem was proposed by Hempel and Popper with their notion of approximate explanation. A more systematic perspective on idealized explanations was developed with the method of idealization and concretization by the Poznan school in the 1970s. If idealizational (...) laws are treated as counterfactual conditionals, they can be true or truthlike, and the concretizations of such laws may increase their degree of truthlikeness. By replacing Hempel’s truth requirement with the condition that an explanatory theory is truthlike one can distinguish several important types of approximate, corrective, and contrastive explanations by idealized theories. The conclusions have important consequences for the debates about scientific realism and anti-realism. (shrink)

In this paper, I show how idealizations contribute to social activities in science, such as the recruitment of experts to a research project. These contributions have not been explicitly discussed by recent philosophical accounts of scientific idealization. These accounts have focused on how idealizations influence activities like scientific theorization, explanation, and modeling. Other accounts focus on how idealizations influence policy-making and science communication. I expand these accounts by exploring the uses of idealized phylogenetic trees in science. Trees are not only (...) useful for improving our understanding and public communication of evolutionary history, but they also help with the organization of laboratories and collaboration among scientists. Attending to the relation between idealizations and these social practices in science matters. It can help us understand why idealized models become entrenched and why certain social practices change over time. (shrink)

The goal of this article is to address the problem of inconsistent models and the challenge it poses for perspectivism. I analyze the argument, draw attention to some hidden premises behind it, and deflate them. Then I introduce the notion of perspectival models as a distinctive class of modeling practices whose primary function is exploratory. I illustrate perspectival modeling with two examples taken from contemporary high-energy physics at the Large Hadron Collider at the European Organization for Nuclear Research, which are (...) designed to show how a plurality of seemingly incompatible models is methodologically crucial to advance the realist quest in cutting-edge areas of scientific inquiry. (shrink)

Science is replete with falsehoods that epistemically facilitate understanding by virtue of being the very falsehoods they are. In view of this puzzling fact, some have relaxed the truth requirement on understanding. I offer a factive view of understanding that fully accommodates the puzzling fact in four steps: (i) I argue that the question how these falsehoods are related to the phenomenon to be understood and the question how they figure into the content of understanding it are independent. (ii) I (...) argue that the falsehoods do not figure into the understanding’s content by being elements of its periphery or core. (iii) Drawing lessons from case studies, I argue that the falsehoods merely enable understanding. When working with such falsehoods, only the truths we extract from them are elements of the content of our understanding. (iv) I argue that the extraction view is compatible with the thesis that falsehoods can have an epistemic value by virtue of being the very falsehoods they are. (shrink)

Scientists appeal to models when explaining phenomena. Such explanations are often dubbed model explanations or model-based explanations. But what are the precise conditions for ME? Are ME special explanations? In our paper, we first rebut two definitions of ME and specify a more promising one. Based on this analysis, we single out a related conception that is concerned with explanations that are induced from working with a model. We call them ‘model-induced explanations’. Second, we study three paradigmatic cases of alleged (...) ME. We argue that all of them are MIE, upon closer examination. Third, we argue that this undermines the building consensus that model explanations are special explanations that, e.g., challenge the factivity of explanation. Instead, it suggests that what is special about models in science is the epistemology behind how models induce explanations. (shrink)

The predominance of machine learning based techniques in cognitive neuroscience raises a host of philosophical and methodological concerns. Given the messiness of neural activity, modellers must make choices about how to structure their raw data to make inferences about encoded representations. This leads to a set of standard methodological assumptions about when abstraction is appropriate in neuroscientific practice. Yet, when made uncritically these choices threaten to bias conclusions about phenomena drawn from data. Contact between the practices of multivariate pattern analysis (...) and philosophy of science can help to illuminate the conditions under which we can use artificial neural networks to better understand neural mechanisms. This paper considers a specific technique for MVPA called representational similarity analysis. I develop a theoretically-informed account of RSA that draws on early connectionist research and work on idealization in the philosophy of science. By bringing a philosophical account of cognitive modelling in conversation with RSA, this paper clarifies the practices of neuroscientists and provides a generalizable framework for using artificial neural networks to study neural mechanisms in the brain. (shrink)

Philosophers of science have developed several accounts of how consideration of scientific models can prompt learning about real-world targets. In recent years, various authors advocated the thesis that consideration of so-called minimal models can prompt learning about such targets. In this paper, I draw on the philosophical literature on scientific modelling and on widely cited illustrations from economics and biology to argue that this thesis fails to withstand scrutiny. More specifically, I criticize leading proponents of such thesis for failing to (...) explicate in virtue of what properties or features minimal models supposedly prompt learning and for substantially overstating the epistemic import of minimal models. I then examine and refute several arguments one may put forward to demonstrate that consideration of minimal models can prompt learning about real-world targets. In doing so, I illustrate the implications of my critique for the wider debate on the epistemology of scientific modelling. (shrink)

Many AI systems that make important decisions are black boxes: how they function is opaque even to their developers. This is due to their high complexity and to the fact that they are trained rather than programmed. Efforts to alleviate the opacity of black box systems are typically discussed in terms of transparency, interpretability, and explainability. However, there is little agreement about what these key concepts mean, which makes it difficult to adjudicate the success or promise of opacity alleviation methods. (...) I argue for a unified account of these key concepts that treats the concept of understanding as fundamental. This allows resources from the philosophy of science and the epistemology of understanding to help guide opacity alleviation efforts. A first significant benefit of this understanding account is that it defuses one of the primary, in-principle objections to post hoc explainable AI (XAI) methods. This “rationalization objection” argues that XAI methods provide mere rationalizations rather than genuine explanations. This is because XAI methods involve using a separate “explanation” system to approximate the original black box system. These explanation systems function in a completely different way than the original system, yet XAI methods make inferences about the original system based on the behavior of the explanation system. I argue that, if we conceive of XAI methods as idealized scientific models, this rationalization worry is dissolved. Idealized scientific models misrepresent their target phenomena, yet are capable of providing significant and genuine understanding of their targets. (shrink)

Critics who are concerned over the epistemological status of psychiatric diagnoses often describe them as being constructed. In contrast, those critics usually see symptoms as relatively epistemologically unproblematic. In this paper I show that symptoms are also constructed. To do this I draw upon the demarcation between data and phenomena. I relate this distinction to psychiatry by portraying behaviour of individuals as data and symptoms as phenomena. I then draw upon philosophers who consider phenomena to be constructed to argue that (...) symptoms are also constructed. Rather than being ready made in the world I show how symptoms are constructs we apply to the world. I highlight this with a historical example and describe methodological constraints on symptom construction. I show the epistemic problems with psychiatric diagnoses are also applicable to symptoms. Following this, I suggest that critics of psychiatric diagnoses should extend their criticism to symptoms or, if they still believe symptoms are relatively epistemologically unproblematic, should rethink their concerns over psychiatric diagnoses. (shrink)