We propose a formal framework for interpretable machine learning. Combining elements from statistical learning, causal interventionism, and decision theory, we design an idealised explanation game in which players collaborate to find the best explanation for a given algorithmic prediction. Through an iterative procedure of questions and answers, the players establish a three-dimensional Pareto frontier that describes the optimal trade-offs between explanatory accuracy, simplicity, and relevance. Multiple rounds are played at different levels of abstraction, allowing the players to explore overlapping causal (...) patterns of variable granularity and scope. We characterise the conditions under which such a game is almost surely guaranteed to converge on a optimal explanation surface in polynomial time, and highlight obstacles that will tend to prevent the players from advancing beyond certain explanatory thresholds. The game serves a descriptive and a normative function, establishing a conceptual space in which to analyse and compare existing proposals, as well as design new and improved solutions. (shrink)

Normative explanations of why things are wrong, good, or unfair are ubiquitous in ordinary practice and normative theory. This paper argues that normative explanation is subject to a justification condition: a correct complete explanation of why a normative fact holds must identify features that would go at least some way towards justifying certain actions or attitudes. I first explain and motivate the condition I propose. I then support it by arguing that it fits well with various theories of normative (...) reasons, makes good sense of certain legitimate moves in ordinary normative explanatory discourse, and helps to make sense of our judgments about explanatory priority in certain cases of normative explanation. This last argument also helps to highlight respects in which normative explanation won’t be worryingly discontinuous with explanations in other domains even though these other explanations aren’t subject to the justification condition. Thus the paper aims not only to do some constructive theorizing about the relatively neglected topic of normative explanation but also to cast light on the broader question of how normative explanation may be similar to and different from explanations in other domains. (shrink)

A compelling idea holds that reality has a layered structure. We often disagree about what inhabits the bottom layer, but we agree that higher up we find chemical, biological, geological, psychological, sociological, economic, /etc./, entities: molecules, human beings, diamonds, mental states, cities, interest rates, and so on. How is this intuitive talk of a layered structure of entities to be understood? Traditionally, philosophers have proposed to understand layered structure in terms of either reduction or supervenience. But these traditional views face (...) well-known problems. A plausible alternative is that layered structure is to be explicated by appeal to explanations of a certain sort, termed / grounding explanations/. Grounding explanations tell us what obtains in virtue of what. Unfortunately, the use of grounding explanations to articulate the layered conception faces a problem, which I call /the collapse/. The collapse turns on the question of how to ground the facts stated by the explanations themselves. In this paper I make a suggestion about how to ground explanations that avoids the collapse. Briefly, the suggestion is that the fact stated by a grounding explanation is grounded in its /explanans/. (shrink)

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that "All models are wrong but some are useful." We focus on (...) the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly. (shrink)

It is often thought that metaphysical grounding underwrites a distinctive sort of metaphysical explanation. However, it would be a mistake to think that all metaphysical explanations are underwritten by metaphysical grounding. In service of this claim, I offer a novel kind of metaphysical explanation called metaphysical explanation by constraint, examples of which have been neglected in the literature. I argue that metaphysical explanations by constraint are not well understood as grounding explanations.

Scientific explanations must bear the proper relationship to the world: they must depict what, out in the world, is responsible for the explanandum. But explanations must also bear the proper relationship to their audience: they must be able to create human understanding. With few exceptions, philosophical accounts of explanation either ignore entirely the relationship between explanations and their audience or else demote this consideration to an ancillary role. In contrast, I argue that considering an explanation’s communicative role (...) is crucial to any satisfactory account of explanation. (shrink)

The ontic conception of scientific explanation has been constructed and motivated on the basis of a putative lexical ambiguity in the term explanation. I raise a puzzle for this ambiguity claim, and then give a deflationary solution under which all ontically-rendered talk of explanation is merely elliptical; what it is elliptical for is a view of scientific explanation that altogether avoids the ontic conception. This result has revisionary consequences for New Mechanists and other philosophers of science, many of whom have (...) assimilated their conception of explanation to the ontic conception. (shrink)

Some properties are causally relevant for a certain effect, others are not. In this paper we describe a problem for our understanding of this notion and then offer a solution in terms of the notion of a program explanation.

This paper examines explanations that turn on non-local geometrical facts about the space of possible configurations a system can occupy. I argue that it makes sense to contrast such explanations from "geometry of motion" with causal explanations. I also explore how my analysis of these explanations cuts across the distinction between kinematics and dynamics.

Philippe Huneman has recently questioned the widespread application of mechanistic models of scientific explanation based on the existence of structural explanations, i.e. explanations that account for the phenomenon to be explained in virtue of the mathematical properties of the system where the phenomenon obtains, rather than in terms of the mechanisms that causally produce the phenomenon. Structural explanations are very diverse, including cases like explanations in terms of bowtie structures, in terms of the topological properties of (...) the system, or in terms of equilibrium. The role of mathematics in bowtie structured systems and in topologically constrained systems has recently been examined in different papers. However, the specific role that mathematical properties play in equilibrium explanations requires further examination, as different authors defend different interpretations, some of them closer to the new-mechanistic approach than to the structural model advocated by Huneman. In this paper, we cover this gap by investigating the explanatory role that mathematics play in Blaser and Kirschner’s nested equilibrium model of the stability of persistent long-term human-microbe associations. We argue that their model is explanatory because: i) it provides a mathematical structure in the form of a set of differential equations that together satisfy an ESS; ii) that the nested nature of the ESSs makes the explanation of host-microbe persistent associations robust to any perturbation; iii) that this is so because the properties of the ESS directly mirror the properties of the biological system in a non-causal way. The combination of these three theses make equilibrium explanations look more similar to structural explanations than to causal-mechanistic explanation. (shrink)

It is not a particularly hard thing to want or seek explanations. In fact, explanations seem to be a large and natural part of our cognitive lives. Children ask why and how questions very early in development and seem genuinely to want some sort of answer, despite our often being poorly equipped to provide them at the appropriate level of sophistication and detail. We seek and receive explanations in every sphere of our adult lives, whether it be (...) to understand why a friendship has foundered, why a car will not start, or why ice expands when it freezes. Moreover, correctly or incorrectly, most of the time we think we know when we have or have not received a good explanation. There is a sense both that a given, successful explanation satisfies a cognitive need, and that a questionable or dubious explanation does not. There are also compelling intuitions about what make good explanations in terms of their form, that is, a sense of when they are structured correctly. (shrink)

Moral philosophers are, among other things, in the business of constructing moral theories. And moral theories are, among other things, supposed to explain moral phenomena. Consequently, one’s views about the nature of moral explanation will influence the kinds of moral theories one is willing to countenance. Many moral philosophers are (explicitly or implicitly) committed to a deductive model of explanation. As I see it, this commitment lies at the heart of the current debate between moral particularists and moral generalists. In (...) this paper I argue that we have good reasons to give up this commitment. In fact, I show that an examination of the literature on scientific explanation reveals that we are used to, and comfortable with, non-deductive explanations in almost all areas of inquiry. As a result, I argue that we have reason to believe that moral explanations need not be grounded in exceptionless moral principles. (shrink)

Explanation is asymmetric: if A explains B, then B does not explain A. Tradition- ally, the asymmetry of explanation was thought to favor causal accounts of explanation over their rivals, such as those that take explanations to be inferences. In this paper, we develop a new inferential approach to explanation that outperforms causal approaches in accounting for the asymmetry of explanation.

The ontic conception of explanation is predicated on the proposition that “explanation is a relation between real objects in the world” and hence, according to this approach, scientific explanation cannot take place absent such a premise. Despite the fact that critics have emphasized several drawbacks of the ontic conception, as for example its inability to address the so-called “abstract explanations”, the debate is not settled and the ontic view can claim to capture cases of explanation that are non-abstract, such (...) as causal relations between events. However, by eliminating the distinction between abstract and non-abstract explanations, it follows that ontic and epistemic proposals can no longer contend to capture different cases of explanation and either all are captured by the ontic view or all are captured by the epistemic view. On closer inspection, it turns out that the ontic view deals with events that fall outside the scientists’ scope of observation and that it does not accommodate common instances of explanation such as explanations from false propositions and hence it cannot establish itself as the dominant philosophical stance with respect to explanation. On the contrary, the epistemic conception does account for almost all episodes of explanation and can be described as a relation between representations, whereby the explanans transmit information to the explanandum and that this information can come, dependent on context, in the form of any of the available theories of explanation (law-like, unificatory, causal and non-causal). The range of application of the ontic view thus is severely restricted to trivial cases of explanation that come through direct observation of the events involved in an explanation and explanation is to be mostly conceived epistemically. (shrink)

This book introduces readers to the topic of explanation. The insights of Plato, Aristotle, J.S. Mill and Carl Hempel are examined, and are used to argue against the view that explanation is merely a problem for the philosophy of science. Having established its importance for understanding knowledge in general, the book concludes with a bold and original explanation of explanation.

Call an explanation in which a non-mathematical fact is explained—in part or in whole—by mathematical facts: an extra-mathematical explanation. Such explanations have attracted a great deal of interest recently in arguments over mathematical realism. In this article, a theory of extra-mathematical explanation is developed. The theory is modelled on a deductive-nomological theory of scientific explanation. A basic DN account of extra-mathematical explanation is proposed and then redeveloped in the light of two difficulties that the basic theory faces. The final (...) view appeals to relevance logic and uses resources in information theory to understand the explanatory relationship between mathematical and physical facts. 1Introduction2Anchoring3The Basic Deductive-Mathematical Account4The Genuineness Problem5Irrelevance6Relevance and Information7Objections and Replies 7.1Against relevance logic7.2Too epistemic7.3Informational containment8Conclusion. (shrink)

Grounding and explanation are said to be intimately connected. Some even maintain that grounding just is a form of explanation. But grounding and explanation also seem importantly different—on the face of it, the former is ‘worldy’ or ‘objective’ while the latter isn’t. In this paper, we develop and respond to an argument to the effect that there is no way to fruitfully address this tension that retains orthodox views about grounding and explanation but doesn’t undermine a central piece of methodology, (...) namely that explanation is a guide to ground. (shrink)

This chapter examines the status of inference to the best explanation in naturalistic metaphysics. The methodology of inference to the best explanation in metaphysics is studied from the perspective of contemporary views on scientific explanation and explanatory inferences in the history and philosophy of science. This reveals serious shortcomings in prevalent attempts to vindicate metaphysical "explanationism" by reference to similarities between science and naturalistic metaphysics. This critique is brought out by considering a common gambit of methodological unity: (1) Both metaphysics (...) and science employ inference to the best explanation. (2) One has no reason to think that if explanationism is truth-conducive in science, it is not so in metaphysics. (3) One has a positive reason to think that if explanationism is truth-conducive in science, it is also so in metaphysics. (shrink)

Inflationists have argued that truth is a causal-explanatory property on the grounds that true belief facilitates practical success: we must postulate truth to explain the practical success of certain actions performed by rational agents. Deflationists, however, have a seductive response. Rather than deny that true belief facilitates practical success, the deflationist maintains that the sole role for truth here is as a device for generalisation. In particular, each individual instance of practical success can be explained only by reference to a (...) relevant instance of a T-schema; the role of truth is just to generalise over these individualised explanations. I present a critical problem for this strategy. Analogues of the deflationist’s individualised explanations can be produced by way of explanation of coincidental instances of practical success where the agent merely has the right false beliefs. By deflationary lights, there is no substantive explanatory difference between such coincidental and non-coincidental instances of practical success. But the non-/coincidental distinction just is an explanatory distinction. The deflationist’s individualised explanations of non-coincidental instances of practical success must therefore be inadequate. However, I argue that the deflationist’s prospects for establishing an explanatory contrast between these cases by supplementing her individualised explanations are, at best, bleak. The inflationist, by contrast, is entitled to the obvious further explanatory premise needed to make sense of the distinction. As such, pending some future deflationary rejoinder, the deflationary construal of the principle that true belief facilitates practical success must be rejected; and with it the deflationary conception of truth. (shrink)

This paper offers a new account of metaphysical explanation. The account is modelled on Kitcher’s unificationist approach to scientific explanation. We begin, in Sect. 2, by briefly introducing the notion of metaphysical explanation and outlining the target of analysis. After that, we introduce a unificationist account of metaphysical explanation before arguing that such an account is capable of capturing four core features of metaphysical explanations: irreflexivity, non-monotonicity, asymmetry and relevance. Since the unificationist theory of metaphysical explanation inherits irreflexivity and (...) non-monotonicity directly from the unificationist theory of scientific explanation that underwrites it, we focus on demonstrating how the account can secure asymmetry and relevance. (shrink)

This paper presents and argues for an account of objectual understanding that aims to do justice to the full range of cases of scientific understanding, including cases in which one does not have an explanation of the understood phenomenon. According to the proposed account, one understands a phenomenon just in case one grasps a sufficiently accurate and comprehensive model of the ways in which it or its features are situated within a network of dependence relations; one’s degree of understanding is (...) proportional to the comprehensiveness and accuracy of such a model. I compare this account with accounts of scientific understanding that explicate understanding in terms of having an explanation of the understood phenomenon. I discuss three distinct types of cases in which scientific understanding does not amount to possessing an explanation of any kind, and argue that the proposed model-based account can accommodate these cases while still retaining a strong link between understanding and explanation. (shrink)

Humeanism about laws of nature — the view that the laws reduce to the Humean mosaic — is a popular view, but currently existing versions face powerful objections. The non-supervenience objection, the non-fundamentality objection and the explanatory circularity objection have all been thought to cause problems for the Humean. However, these objections share a guiding thought — they are all based on the idea that there is a certain kind of divergence between the practice of science and the metaphysical picture (...) suggested by Humeanism. -/- I suggest that the Humean can respond to these objections not by rejecting this divergence, but by arguing that is appropriate. In particular the Humean can, in the spirit of Loewer (2012), distinguish between scientific and metaphysical explanation — this is motivated by differing aims of explanation in science and metaphysics. And they can further leverage this into distinctions between scientific and metaphysical fundamentality and scientific and metaphysical possibility. We can use these distinctions to respond to the objections that the Humean faces. (shrink)

Mathematicians distinguish between proofs that explain their results and those that merely prove. This paper explores the nature of explanatory proofs, their role in mathematical practice, and some of the reasons why philosophers should care about them. Among the questions addressed are the following: what kinds of proofs are generally explanatory (or not)? What makes a proof explanatory? Do all mathematical explanations involve proof in an essential way? Are there really such things as explanatory proofs, and if so, how (...) do they relate to the sorts of explanation encountered in philosophy of science and metaphysics? (shrink)

What features will something have if it counts as an explanation? And will something count as an explanation if it has those features? In the second half of the 20th century, philosophers of science set for themselves the task of answering such questions, just as a priori conceptual analysis was generally falling out of favor. And as it did, most philosophers of science just moved on to more manageable questions about the varieties of explanation and discipline-specific scientific explanation. Often, such (...) shifts are sound strategies for problem-solving. But leaving fallow certain basic conceptual issues can also result in foundational debates. (shrink)

This chapter provides a systematic overview of topological explanations in the philosophy of science literature. It does so by presenting an account of topological explanation that I (Kostić and Khalifa 2021; Kostić 2020a; 2020b; 2018) have developed in other publications and then comparing this account to other accounts of topological explanation. Finally, this appraisal is opinionated because it highlights some problems in alternative accounts of topological explanations, and also it outlines responses to some of the main criticisms raised (...) by the so-called new mechanists. (shrink)

Ground is all the rage in contemporary metaphysics. But what is its nature? Some metaphysicians defend what we could call, following Skiles and Trogdon (2021), the inheritance view: it is because constitutive forms of metaphysical explanation are such-and-such that we should believe that ground is so-and-so. However, many putative instances of inheritance are not primarily motivated by scientific considerations. This limitation is harmless if one thinks that ground and science are best kept apart. Contrary to this view, we believe that (...) ground is a highly serviceable tool for investigating metaphysical areas of science. In this paper, we defend a naturalistic version of the inheritance view which takes constitutive scientific explanation as a better guide to ground. After illustrating the approach and its merits, we discuss some implications of the emerging scientific conception for the theory of ground at large. (shrink)

I discuss the methodological passage in the begin- ning of Ethica Eudemia I.6 (1216b26-35), which has received attention in connection with Aristotle’s notion of dialectic and his methodology in Ethics. My central focus is not to discuss whether Aristotle is prescribing and using what has been called the method of endoxa. I will focus on how this passage coheres with the remaining parts of the same chapter, which also are advancing methodological remarks. My claim is that the meth- od of (...) Ethica Eudemia I.6 is in agreement with many features of Aristotle’s theory of explanation as presented in the Posterior Analytics: Aristotle’s main concern is a warning against misuses of explanatory arguments. (shrink)

I survey the philosophical literature on grounding explanation and its connection to metaphysical ground.

I discuss Aristotle's anomalous terminology in Physics A.1 (involving "universals" and "particulars") and its coherence with Aristotle's notion of scientific demonstration.

There is a widely shared belief that the higher-level sciences can provide better explanations than lower-level sciences. But there is little agreement about exactly why this is so. It is often suggested that higher-level explanations are better because they omit details. I will argue instead that the preference for higher-level explanations is just a special case of our general preference for informative, logically strong, beliefs. I argue that our preference for informative beliefs entirely accounts for why higher-level (...) explanations are sometimes better—and sometimes worse—than lower-level explanations. The result is a step in the direction of the unity of science hypothesis. 1Introduction2Background: Is Omitting Details an Explanatory Virtue? 2.1Anti-reductionist arguments2.2Reductionist argument2.3Logical strength3Bases, Links and Logical Strength4Functionalism and Fodor’s Argument5Two Generalizations6Should the Base Really Be Maximally Strong?7Anti-reductionist Arguments Regarding the Base8Should the Antecedent of the Link Really Be Maximally Weak? (shrink)

We argue that the trend toward providing users with feasible and actionable explanations of AI decisions—known as recourse explanations—comes with ethical downsides. Specifically, we argue that recourse explanations face several conceptual pitfalls and can lead to problematic explanation hacking, which undermines their ethical status. As an alternative, we advocate that explanations of AI decisions should aim at understanding.

In this paper I defend an intermediate position between the ‘bare mathematical results’ view and the ‘transmission’ view of mathematical explanations of physical phenomena (MEPPs). I argue that, in MEPPs, it is not enough to deduce the explanandum from the generalizations cited in the explanans. Rather, we must add information regarding why those generalizations obtain. However, I also argue that it is not necessary to provide explanatory proofs of the mathematical theorems that represent those generalizations. I illustrate this with (...) the bridges of Königsberg case. -/- . (shrink)

[This paper is available as open access from the publisher.] Normative theories aim to explain why things have the normative features they have. This paper argues that, contrary to some plausible existing views, one important kind of normative explanations which first-order normative theories aim to formulate and defend can fail to transmit downward along chains of metaphysical determination of normative facts by non-normative facts. Normative explanation is plausibly subject to a kind of a justification condition whose satisfaction may fail (...) to transmit along the relevant kind of metaphysical hierarchy. A broader aim of the paper is to contribute to systematic theorizing about normative explanation: whereas there has been a great deal of work on scientific explanation, there has been little by way of systematic exploration of what sort of explanations normative theories aim to formulate and defend. (shrink)

Michael Strevens offers an account of causal explanation according to which explanatory practice is shaped by counterbalanced commitments to representing causal influence and abstracting away from overly specific details. In this paper, I challenge a key feature of that account. I argue that what Strevens calls explanatory frameworks figure prominently in explanatory practice because they actually improve explanations. This suggestion is simple but has far-reaching implications. It affects the status of explanations that cite multiply realizable properties; changes the (...) explanatory role of causal factors with small effect; and undermines Strevens’ titular explanatory virtue, depth. This results in greater coherence with explanatory practice and accords with the emphasis that Strevens places on explanatory patterns. Ultimately, my suggestion preserves a tight connection between explanation and the creation of understanding by taking into account explanations’ role in communication. (shrink)

This paper argues for several related theses. First, the epistemological position that knowledge requires safe belief can be motivated by views in the philosophy of science, according to which good explanations show that their explananda are robust. This motivation goes via the idea—recently defended on both conceptual and empirical grounds—that knowledge attributions play a crucial role in explaining successful action. Second, motivating the safety requirement in this way creates a choice point—depending on how we understand robustness, we'll end up (...) with different conceptions of safety in epistemology. Lastly, and most controversially, there's an attractive choice at this point that will not vindicate some of the most influential applications of the safety-theoretic framework in epistemology, e.g., Williamson's arguments against the KK principle, and luminosity. (shrink)

This paper investigates conceptions of explanation, teleology, and analogy in the works of Immanuel Kant (1724-1804) and Georges Cuvier (1769-1832). Richards (2000, 2002) and Zammito (2006, 2012, 2018) have argued that Kant’s philosophy provided an obstacle for the project of establishing biology as a proper science around 1800. By contrast, Russell (1916), Outram (1986), and Huneman (2006, 2008) have argued, similar to suggestions from Lenoir (1989), that Kant’s philosophy influenced the influential naturalist Georges Cuvier. In this article, I wish to (...) expand on and further the work of Russell, Outram, and Huneman by adopting a novel perspective on Cuvier and considering (a) the similar conceptions of proper science and explanation of Kant and Cuvier, and (b) the similar conceptions of the role of teleology and analogy in the works of Kant and Cuvier. The similarities between Kant and Cuvier show, contrary to the interpretation of Richards and Zammito, that some of Kant’s philosophical ideas, whether they derived from him or not, were fruitfully applied by some life scientists who wished to transform life sciences into proper sciences around 1800. However, I also show that Cuvier, in contrast to Kant, had a workable strategy for transforming the life sciences into proper sciences, and that he departed from Kant’s philosophy of science in crucial respects. (shrink)

As the demand for explainable deep learning grows in the evaluation of language technologies, the value of a principled grounding for those explanations grows as well. Here we study the state-of-the-art in explanation for neural models for natural-language processing (NLP) tasks from the viewpoint of philosophy of science. We focus on recent evaluation work that finds brittleness in explanations obtained through attention mechanisms.We harness philosophical accounts of explanation to suggest broader conclusions from these studies. From this analysis, we (...) assert the impossibility of causal explanations from attention layers over text data. We then introduce NLP researchers to contemporary philosophy of science theories that allow robust yet non-causal reasoning in explanation, giving computer scientists a vocabulary for future research. (shrink)

Inference to the Best Explanation (IBE) advises reasoners to infer exactly one explanation. This uniqueness claim apparently binds us when it comes to “conjunctive explanations,” distinct explanations that are nonetheless explanatorily better together than apart. To confront this worry, explanationists qualify their statement of IBE, stipulating that this inference form only adjudicates between competing hypotheses. However, a closer look into the nature of competition reveals problems for this qualified account. Given the most common explication of competition, this qualification (...) artificially and radically constrains IBE’s domain of applicability. Using a more subtle, recent explication of competition, this qualification no longer provides a compelling treatment of conjunctive explanations. In light of these results, I suggest a different strategy for accommodating conjunctive explanations. Instead of modifying the form of IBE, I suggest a new way of thinking about the structure of IBE’s lot of considered hypotheses. (shrink)

People often answer why-questions with what we call experiential explanations: narratives or stories with temporal structure and concrete details. In contrast, on most theories of the epistemic function of explanation, explanations should be abstractive: structured by general relationships and lacking extraneous details. We suggest that abstractive and experiential explanations differ not only in level of abstraction, but also in structure, and that each form of explanation contributes to the epistemic goals of individual learners and of science. In (...) particular, experiential explanations support mental simulation and survive transitions across background theories; as a result, they support learning and help us translate between competing frameworks. Experiential explanations play an irreducible role in human cognition – and perhaps in science. (shrink)

Recently, Kit Fine's (1994) view that modal truths aretrue in virtue of,grounded in, orexplained byessentialist truths has been under attack. In what follows we offer two responses to the wave of criticism against his view. While the first response is pretty straightforward, the second is based on the distinction between, what we call,Reductive Finean EssentialismandNon-Reductive Finean Essentialism. Engaging the work of Bob Hale onNon-Reductive Finean Essentialism, we aim to show that the arguments against Fine's view are unconvincing, while we acknowledge (...) the presence of a deep standoff between the two views. (shrink)

Since approval of the EU General Data Protection Regulation (GDPR) in 2016, it has been widely and repeatedly claimed that the GDPR will legally mandate a ‘right to explanation’ of all decisions made by automated or artificially intelligent algorithmic systems. This right to explanation is viewed as an ideal mechanism to enhance the accountability and transparency of automated decision-making. However, there are several reasons to doubt both the legal existence and the feasibility of such a right. In contrast to the (...) right to explanation of specific automated decisions claimed elsewhere, the GDPR only mandates that data subjects receive meaningful, but properly limited, information (Articles 13-15) about the logic involved, as well as the significance and the envisaged consequences of automated decision-making systems, what we term a ‘right to be informed’. Further, the ambiguity and limited scope of the ‘right not to be subject to automated decision-making’ contained in Article 22 (from which the alleged ‘right to explanation’ stems) raises questions over the protection actually afforded to data subjects. These problems show that the GDPR lacks precise language as well as explicit and well-defined rights and safeguards against automated decision-making, and therefore runs the risk of being toothless. We propose a number of legislative and policy steps that, if taken, may improve the transparency and accountability of automated decision-making when the GDPR comes into force in 2018. (shrink)

Normative explanations, which specify why things have the normative features they do, are ubiquitous in normative theory and ordinary thought. But there is much less work on normative explanation than on scientific or metaphysical explanation. Skow (2016) argues that a complete answer to the question why some fact Q occurs consists in all of the reasons why Q occurs. This paper explores this theory as a case study of a general theory that promises to offer us a grip on (...) normative explanation which is independent of particular normative theories. I first argue that the theory doesn’t give an adequate account of certain enablers of reasons which are important in normative explanation. I then formulate and reject three responses on behalf of the theory. But I suggest that since theories of this general sort have the right kind of resources to illuminate how normative explanation might be similar to and different from explanations in other domains, they nonetheless merit further exploration by normative theorists. (shrink)

This paper explores a novel notion of self-explanation that combines ideas from two sources: the tripartite account of explanation, according to which a proposition can help explain another either in the capacity of a reason why the latter obtains or in the capacity of an explanatory link, and the notion of an empty-base explanation, which generalizes the ideas of explanation by zero-grounding and explanation by status. After having introduced these ideas and the novel notion of self-explanation, I argue that the (...) latter has the potential to resist extant arguments against the possibility of self-explanation. In the remainder of the paper, I discuss candidates for such self-explanatory propositions and suggest possible applications for Humeanism about laws of nature, the debate on the grounds of ground, the rationalist tradition, and philosophical theology. (shrink)

In this paper I argue that the common practice of employing moral predicates as explaining phrases can be accommodated on an expressivist account of moral practice. This account does not treat moral explanations as in any way second-rate or derivative, since it subsumes moral explanations under the general theory of program explanations (as defended by Jackson and Pettit). It follows that the phenomenon of moral explanations cannot be used to adjudicate the debate between expressivism and its (...) rivals. (shrink)

This paper tries to get a grip on two seemingly conflicting intuitions about reductionism in quantum mechanics. On the one hand it is received wisdom that quantum mechanics puts an end to ‘reductionism’. Quantum-entanglement is responsible for such features of quantum mechanics as holism, the failure of supervenience and emergence. While I agree with these claims I will argue that it is only part of the story. Quantum mechanics provides us with thorough-going reductionist explanations. I will distinguish two kinds (...) of micro-explanation (or micro-‘reduction’). I will argue that even though quantum-entanglement provides an example for the failure of one kind of micro-explanation it does not affect the other. Contrary to a recent paper by Kronz and Tiehen I claim that the explanation of the dynamics of quantum mechanical systems is just as reductionist as it used to be in classical mechanics. (shrink)

"Explanation and Understanding" (1971) by Georg Henrik von Wright is a modern classic in analytic hermeneutics, and in the philosophy of the social sciences and humanities in general. In this work, von Wright argues against naturalism, or methodological monism, i.e. the idea that both the natural sciences and the social sciences follow broadly the same general scientific approach and aim to achieve causal explanations. Against this view, von Wright contends that the social sciences are qualitatively different from the natural (...) sciences: according to his view, the natural sciences aim at causal explanations, whereas the purpose of the social sciences is to understand their subjects. In support of this conviction, von Wright also puts forward a version of the so-called logical connection argument. -/- Von Wright views scientific explanation along the lines of the traditional covering law model. He suggests that the social sciences, in contrast, utilize what he calls “practical syllogism” in understanding human actions. In addition, von Wright presents in this work an original picture on causation: a version of the manipulability theory of causation. -/- In the four decades following von Wright’s classic work, the overall picture in in the philosophy of science has changed significantly, and much progress has been made in various fronts. The aim of the contribution is to revisit the central ideas of "Explanation and Understanding" and evaluate them from this perspective. The covering law model of explanation and the regularity theory of causation behind it have since then fallen into disfavor, and virtually no one believes that causal explanations even in the natural sciences comply with the covering law model. No wonder then that covering law explanations are not found in the social sciences either. Ironically, the most popular theory of causal explanation in the philosophy of science nowadays is the interventionist theory, which is a descendant of the manipulability theory of von Wright and others. However, this theory can be applied with no special difficulties in both the natural sciences and the social sciences. -/- Von Wright’s logical connection argument and his ideas concerning practical syllogisms are also critically assessed. It is argued that in closer scrutiny, they do not pose serious problems for the view that the social sciences too provide causal explanations. In sum, von Wright’s arguments against naturalism do not appear, in today’s perspective, particularly convincing. (shrink)

Non-causal accounts of action explanation have long been criticized for lacking a positive thesis, relying primarily on negative arguments to undercut the standard Causal Theory of Action The Stanford Encyclopedia of Philosophy, 2016). Additionally, it is commonly thought that non-causal accounts fail to provide an answer to Donald Davidson’s challenge for theories of reasons explanations of actions. According to Davidson’s challenge, a plausible non-causal account of reasons explanations must provide a way of connecting an agent’s reasons, not only (...) to what she ought to do, but to what she actually does. That is, such explanations must be truth-apt, not mere rationalizations. My aim in this paper is to show how a non-causal account of action can provide explanations that are truth-apt and genuinely explanatory. To make this argument, I take as a given an account of the practical syllogism discussed by Michael Thompson and Eric Wiland, according to which the practical syllogism is truly practical rather than propositional in nature. Next, I present my primary positive thesis: reasons for actions have explanatory power in virtue of being parts of a structure—the practical syllogism—that contains the action being explained. I then argue that structural action explanations can meet Davidson’s challenge and that they genuinely explain actions. Finally, I conclude by addressing some objections to my argument. (shrink)

Philosophers have cataloged a range of genealogical methods by which different sorts of normative conclusions can be established. Although such methods provide diverging ways of pursuing genealogical inquiry, they typically converge in eschewing historiographic methodology, in favor of a uniquely philosophical approach. In contrast, one genealogist who drew on historiographic methodology is Michel Foucault. This article presents the motivations and advantages of Foucault's genealogical use of such a methodology. It advances two mains claims. First, that Foucault's early 1970s work employs (...) a distinct genealogical method, which borrows from contemporary historiographic models of explanation to expand the range of objects that are proper to genealogical accounts of historical change. I demonstrate how Foucault modifies two central commitments of Nietzsche by broadening the dimensions of genealogical inquiry and explanation. Second, that historical method has normative relevance for genealogy, insofar as different historiographic choices can lead to different normative conclusions. I motivate this second claim by explaining how Foucault's multidimensional genealogical method expands both (a) the range of objects that are subject to evaluative assessment, and (b) the set of possible prescriptive recommendations that follow from such assessment. (shrink)

, whereby some causes are deemed more important than others, are ubiquitous in historical studies. Drawing from influential recent work on causation, I develop a definition of causal-explanatory strength. This makes clear exactly which aspects of explanatory weighting are subjective and which objective. It also sheds new light on several traditional issues, showing for instance that: underlying causes need not be more important than proximate ones; several different causes can each be responsible for most of an effect; small causes need (...) not be less important than big ones; and non-additive interactive effects between causes present no particular difficulty. Key Words: causation • explanation • history • interaction • proximate • underlying. (shrink)

In Posterior Analytics II 16-17, Aristotle seems to claim that there cannot be more than one explanans of the same scientific explanandum. However, this seems to be true only for “primary-universal” demonstrations, in which the major term belongs to the minor “in itself” and the middle term is coextensive with the extremes. If so, several explananda we would like to admit as truly scientific would be out of the scope of an Aristotelian science. The secondary literature has identified a second (...) problem in II 16-17: the middle term of a demonstration is sometimes taken as the definition of the minor term (the subject), other times as the definition (or the causal part of the definition) of the major (the demonstrable attribute). I shall argue that Aristotle’s solution to the first problem involves showing that certain problematic attributes, which appear to admit more than one explanation, actually fall into the privileged scenario of primary-universal demonstrations. In addition, his solution suggests a conciliatory way-out to our second problem (or so I shall argue): the existence of an attribute as a definable unity depends on its subject having the essence it has, which suggests that both the essence of subjects and the essence of demonstrable attributes can play explanatory roles in demonstrations. (shrink)