Causal reasoning and game-theoretic reasoning are fundamental topics in artificial intelligence, among many other disciplines: this paper is concerned with their intersection. Despite their importance, a formal framework that supports both these forms of reasoning has, until now, been lacking. We offer a solution in the form of (structural) causal games, which can be seen as extending Pearl's causal hierarchy to the game-theoretic domain, or as extending Koller and Milch's multi-agent influence diagrams to the causal domain. We then consider three (...) key questions: i) How can the (causal) dependencies in games - either between variables, or between strategies - be modelled in a uniform, principled manner? ii) How may causal queries be computed in causal games, and what assumptions does this require? iii) How do causal games compare to existing formalisms? To address question i), we introduce mechanised games, which encode dependencies between agents' decision rules and the distributions governing the game. In response to question ii), we present definitions of predictions, interventions, and counterfactuals, and discuss the assumptions required for each. Regarding question iii), we describe correspondences between causal games and other formalisms, and explain how causal games can be used to answer queries that other causal or game-theoretic models do not support. Finally, we highlight possible applications of causal games, aided by an extensive open-source Python library. (shrink)

It is often assumed that theorizing in terms of natural properties is more objectively valuable than theorizing in terms of non-natural properties. But this assumption faces an explanatory challenge: explain the greater objective value of theorizing in terms of natural properties. In this paper, I answer that challenge by proposing and exploring three different accounts of the objective value of naturalness. Two appeal to constitutive natures: it is part of the constitutive nature of explanation, or of objective value, that theorizing (...) in terms of natural properties is more objectively valuable. The third appeals to the theoretical role that naturalness plays. (shrink)

This article presents a new argument for incorporating a distinction between default and deviant values into the formalism of causal models. The argument is based on considerations about how causal reasoners should represent disagreement over causes, and it is defended against an objection that has been raised against earlier arguments for defaults.

Explanations are backed by many different relations: causation, grounding, and arguably others too. But why are these different relations capable of backing explanations? In virtue of what are they explanatory? In this paper, I propose and defend a monistic account of explanation-backing relations. On my account, there is a single relation which backs all cases of explanation, and which explains why those other relations are explanation-backing.

How should we reason in science? Jan Sprenger and Stephan Hartmann offer a refreshing take on classical topics in philosophy of science, using a single key concept to explain and to elucidate manifold aspects of scientific reasoning. They present good arguments and good inferences as being characterized by their effect on our rational degrees of belief. Refuting the view that there is no place for subjective attitudes in 'objective science', Sprenger and Hartmann explain the value of convincing evidence in terms (...) of a cycle of variations on the theme of representing rational degrees of belief by means of subjective probabilities (and changing them by Bayesian conditionalization). In doing so, they integrate Bayesian inference—the leading theory of rationality in social science—with the practice of 21st century science. Bayesian Philosophy of Science thereby shows how modeling such attitudes improves our understanding of causes, explanations, confirming evidence, and scientific models in general. It combines a scientifically minded and mathematically sophisticated approach with conceptual analysis and attention to methodological problems of modern science, especially in statistical inference, and is therefore a valuable resource for philosophers and scientific practitioners. (shrink)

Causal reasoning is one of our most central cognitive competencies, enabling us to adapt to our world. Causal knowledge allows us to predict future events, or diagnose the causes of observed facts. We plan actions and solve problems using knowledge about cause-effect relations. Without our ability to discover and empirically test causal theories, we would not have made progress in various empirical sciences. In the past decades, the important role of causal knowledge has been discovered in many areas of cognitive (...) psychology. Despite the ubiquity of causal reasoning, textbooks of cognitive psychology have neglected this growing field. The goal of The Oxford Handbook of Causal Reasoning is to fill this gap. The handbook brings together the leading researchers in the field of causal reasoning and offers state-of-the-art presentations of theories and research. It provides introductions of competing theories of causal reasoning, and discusses its role in various cognitive functions and domains. The final section presents research from neighboring fields. 1. Causal Reasoning: An Introduction Michael R. Waldmann Part I: Theories of Causal Cognition 2. Associative Accounts of Causal Cognition Mike E. Le Pelley, Oren Griffiths, and Tom Beesley 3. Rules of Causal Judgment: Mapping Statistical Information Onto Causal Beliefs José C. Perales, Andrés Catena, Antonio Cándido, and Antonio Maldonado 4. The Inferential Reasoning Theory of Causal Learning: Toward a Multi- Process Propositional Account Yannick Boddez, Jan De Houwer, and Tom Beckers 5. Causal Invariance as an Essential Constraint for Creating a Causal Representation of the World: Generalizing the Invariance of Causal Power Patricia W. Cheng and Hongjing Lu 6. The Acquisition and Use of Causal Structure Knowledge Benjamin Margolin Rottman 7. Formalizing Prior Knowledge in Causal Induction Thomas L. Griffiths 8. Causal Mechanisms Samuel G. B. Johnson and Woo-kyoung Ahn 9. Force Dynamics and Causation Phillip Wolff and Robert Thorstad 10. Mental Models and Causation P. N. Johnson- Laird and Sangeet S. Khemlani 11. Pseudocontingencies Klaus Fiedler and Florian Kutzner 12. Singular Causation David Danks 13. Cognitive Neuroscience of Causal Reasoning Joachim T. Operskalski and Aron K. Barbey Part II: Basic Cognitive Functions 14. Visual Impressions of Causality Peter White 15. Goal-Directed Actions Bernhard Hommel 16. Planning and Control Magda Osman 17. Reinforcement Learning and Causal Models Samuel J. Gershman 18. Causation and the Probability of Causal Conditionals David E. Over 19. Causal Models and Conditional Reasoning Mike Oaksford and Nick Chater 20. Concepts as Causal Models: Categorization Bob Rehder 21. Concepts as Causal Models: Induction Bob Rehder 22. Causal Explanation Tania Lombrozo and Nadya Vasilyeva 23. Diagnostic Reasoning Björn Meder and Ralf Mayrhofer 24. Inferring Causal Relations by Analogy Keith J. Holyoak and Hee-Seung Lee 25. Causal Argument Ulrike Hahn, Roland Bluhm, and Frank Zenker 26. Causality in Decision- Making York Hagmayer and Philip M. Fernbach Part III: Domains of Causal Reasoning 27. Intuitive Theories Tobias Gerstenberg and Joshua B. Tenenbaum 28. Space, Time, and Causality Marc J. Buehner 29. Causation in Legal and Moral Reasoning David A. Lagnado and Tobias Gerstenberg 30. The Role of Causal Knowledge in Reasoning About Mental Disorders Woo-kyoung Ahn, Nancy S. Kim, and Matthew S. Lebowitz 31. Causality and Causal Reasoning in Natural Language Torgrim Solstad and Oliver Bott 32. Social Attribution and Explanation Denis Hilton Part IV: Development, Phylogeny, and Culture 33. The Development of Causal Reasoning Paul Muentener and Elizabeth Bonawitz 34. Causal Reasoning in Non-Human Animals Christian Schloegl and Julia Fischer 35. Causal Cognition and Culture Andrea Bender, Sieghard Beller, and Douglas L. Medin. (shrink)

While structural equations modeling is increasingly used in philosophical theorizing about causation, it remains unclear what it takes for a particular structural equations model to be correct. To the extent that this issue has been addressed, the consensus appears to be that it takes a certain family of causal counterfactuals being true. I argue that this account faces difficulties in securing the independent manipulability of the structural determination relations represented in a correct structural equations model. I then offer an alternate (...) understanding of structural determination, and I demonstrate that this theory guarantees that structural determination relations are independently manipulable. The account provides a straightforward way of understanding hypothetical interventions, as well as a criterion for distinguishing hypothetical changes in the values of variables which constitute interventions from those which do not. It additionally affords a semantics for causal counterfactual conditionals which is able to yield a clean solution to a problem case for the standard ‘closest possible world’ semantics. (shrink)

Grounding is often glossed as metaphysical causation, yet no current theory of grounding looks remotely like a plausible treatment of causation. I propose to take the analogy between grounding and causation seriously, by providing an account of grounding in the image of causation, on the template of structural equation models for causation.

This paper argues that so-called “trumping preemption” is in fact overdetermination or early preemption, and is thus not a distinctive form of redundant causation. I draw a novel lesson from cases thought to be trumping: that the boundary between preemption and overdetermination should be reconsidered.

In Making Things Happen, James Woodward influentially combines a causal modeling analysis of actual causation with an interventionist semantics for the counterfactuals encoded in causal models. This leads to circularities, since interventions are defined in terms of both actual causation and interventionist counterfactuals. Circularity can be avoided by instead combining a causal modeling analysis with a semantics along the lines of that given by David Lewis, on which counterfactuals are to be evaluated with respect to worlds in which their antecedents (...) are realized by miracles. I argue, pace Woodward, that causal modeling analyses perform just as well when combined with the Lewisian semantics as when combined with the interventionist semantics. Reductivity therefore remains a reasonable hope. (shrink)

An actual cause of some token effect is itself a token event that helped to bring about that effect. The notion of an actual cause is different from that of a potential cause – for example a pre-empted backup – which had the capacity to bring about the effect, but which wasn't in fact operative on the occasion in question. Sometimes actual causes are also distinguished from mere background conditions: as when we judge that the struck match was a cause (...) of the fire, while the presence of oxygen was merely part of the relevant background against which the struck match operated. Actual causation is also to be distinguished from type causation: actual causation holds between token events in a particular, concrete scenario; type causation, by contrast, holds between event kinds in scenario kinds. (shrink)

An influential tradition in the philosophy of causation has it that all token causal facts are, or are reducible to, facts about difference-making. Challenges to this tradition have typically focused on pre-emption cases, in which a cause apparently fails to make a difference to its effect. However, a novel challenge to the difference-making approach has recently been issued by Alyssa Ney. Ney defends causal foundationalism, which she characterizes as the thesis that facts about difference-making depend upon facts about physical causation. (...) She takes this to imply that causation is not fundamentally a matter of difference-making. In this paper, I defend the difference-making approach against Ney’s argument. I also offer some positive reasons for thinking, pace Ney, that causation is fundamentally a matter of difference-making. (shrink)

We present a probabilistic extension to active path analyses of token causation (Halpern & Pearl 2001, forthcoming; Hitchcock 2001). The extension uses the generalized notion of intervention presented in (Korb et al. 2004): we allow an intervention to set any probability distribution over the intervention variables, not just a single value. The resulting account can handle a wide range of examples. We do not claim the account is complete --- only that it fills an obvious gap in previous active-path approaches. (...) It still succumbs to recent counterexamples by Hiddleston (2005), because it does not explicitly consider causal processes. We claim three benefits: a detailed comparison of three active-path approaches, a probabilistic extension for each, and an algorithmic formulation. (shrink)

A central goal of research in explainable artificial intelligence (XAI) is to facilitate human understanding. However, understanding is an elusive concept that is difficult to target. In this paper, we argue that a useful way to conceptualize understanding within the realm of XAI is via certain human abilities. We present four criteria for a useful conceptualization of understanding in XAI and show that these are fulfilled by an abilities-based approach: First, thinking about understanding in terms of specific abilities is motivated (...) by research from numerous disciplines involved in XAI. Second, an abilities-based approach is highly versatile and can capture different forms of understanding important in XAI application contexts. Third, abilities can be operationalized for empirical studies. Fourth, abilities can be used to clarify the link between explainability, understanding, and societal desiderata concerning AI, like fairness and trustworthiness. Conceptualizing understanding as abilities can therefore support interdisciplinary collaboration among XAI researchers, provide practical benefit across diverse XAI application contexts, facilitate the development and evaluation of explainability approaches, and contribute to satisfying the societal desiderata of different stakeholders concerning AI systems. (shrink)

Cancer biology features the ascription of normal functions to parts of cancers. At least some ascriptions of function in cancer biology track local normality of parts within the global abnormality of the aberration to which those parts belong. That is, cancer biologists identify as functions activities that, in some sense, parts of cancers are supposed to perform, despite cancers themselves having no purpose. The present paper provides a theory to accommodate these normal function ascriptions—I call it the Modeling Account of (...) Normal Function (MA). MA comprises two claims. First, normal functions are activities whose performance by the function-bearing part contributes to the self-maintenance of the whole system and, thereby, results in the continued presence of that part. Second, MA holds that models of system-level activities that are (partly) constitutive of self-maintenance are improved by including a representation of the relevant function-bearing part and by making reference to the activity/activities that part performs which contribute(s) to those system-level activities. I contrast MA with two other accounts that seek to explicate the ascription of normal functions in biology, namely, the organizational account and the selected effects account. Both struggle to extend to cancer biology. However, I offer ecumenical readings which allow them to recover some ascriptions of normal function to parts of cancers. So, though I contend that MA excels in this respect, the purpose of this paper is served if it provides materials for bridging the gap between cancer biology, philosophy of cancer, and the literature on function. (shrink)

Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence, a fast-growing research area that is so far lacking in firm theoretical foundations. In this article, an expanded version of a paper originally presented at the 37th Conference on Uncertainty in Artificial Intelligence, we attempt to fill this gap. Building on work in logic, probability, and causality, we establish the central role of (...) necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We propose a novel formulation of these concepts, and demonstrate its advantages over leading alternatives. We present a sound and complete algorithm for computing explanatory factors with respect to a given context and set of agentive preferences, allowing users to identify necessary and sufficient conditions for desired outcomes at minimal cost. Experiments on real and simulated data confirm our method’s competitive performance against state of the art XAI tools on a diverse array of tasks. (shrink)

There is general consensus that explainable artificial intelligence is valuable, but there is significant divergence when we try to articulate why, exactly, it is desirable. This question must be distinguished from two other kinds of questions asked in the XAI literature that are sometimes asked and addressed simultaneously. The first and most obvious is the ‘how’ question—some version of: ‘how do we develop technical strategies to achieve XAI?’ Another question is specifying what kind of explanation is worth having in the (...) first place. As difficult and important as the challenges are in answering these questions, they are distinct from a third question: why do we want XAI at all? There is vast literature on this question as well, but I wish to explore a different kind of answer. The most obvious way to answer this question is by describing a desirable outcome that would likely be achieved with the right kind of explanation, which would make the explanation valuable instrumentally. That is, XAI is desirable to attain some other value, such as fairness, trust, accountability, or governance. This family of arguments is obviously important, but I argue that explanations are also intrinsically valuable, because unexplainable systems can be dehumanizing. I argue that there are at least three independently valid versions of this kind of argument: an argument from participation, from knowledge, and from actualization. Each of these arguments that XAI is intrinsically valuable is independently compelling, in addition to the more obvious instrumental benefits of XAI. (shrink)

An important, but relatively neglected, aspect of human theory of mind is emotion inference: understanding how and why a person feels a certain why is central to reasoning about their beliefs, desires and plans. The authors review recent work that has begun to unveil the structure and determinants of emotion inference, organizing them within a unified probabilistic framework.

Hall [(2007), Philosophical Studies, 132, 109–136] offers a critique of structural equations accounts of actual causation, and then offers a new theory of his own. In this paper, I respond to Hall’s critique, and present some counterexamples to his new theory. These counterexamples are then diagnosed.

This article proposes a new model of human concept learning that provides a rational analysis of learning feature‐based concepts. This model is built upon Bayesian inference for a grammatically structured hypothesis space—a concept language of logical rules. This article compares the model predictions to human generalization judgments in several well‐known category learning experiments, and finds good agreement for both average and individual participant generalizations. This article further investigates judgments for a broad set of 7‐feature concepts—a more natural setting in several (...) ways—and again finds that the model explains human performance. (shrink)

Recent accounts of actual causation are stated in terms of extended causal models. These extended causal models contain two elements representing two seemingly distinct modalities. The first element are structural equations which represent the or mechanisms of the model, just as ordinary causal models do. The second element are ranking functions which represent normality or typicality. The aim of this paper is to show that these two modalities can be unified. I do so by formulating two constraints under which extended (...) causal models with their two modalities can be subsumed under so called which contain just one modality. These two constraints will be formally precise versions of Lewissystem of weights or priorities” governing overall similarity between possible worlds. (shrink)

Partial explanations are everywhere. That is, explanations citing causes that explain some but not all of an effect are ubiquitous across science, and these in turn rely on the notion of degree of explanation. I argue that current accounts are seriously deficient. In particular, they do not incorporate adequately the way in which a cause’s explanatory importance varies with choice of explanandum. Using influential recent contrastive theories, I develop quantitative definitions that remedy this lacuna, and relate it to existing measures (...) of degree of causation. Among other things, this reveals the precise role here of chance, as well as bearing on the relation between causal explanation and causation itself. (shrink)

Structural equations have become increasingly popular in recent years as tools for understanding causation. But standard structural equations approaches to causation face deep problems. The most philosophically interesting of these consists in their failure to incorporate a distinction between default states of an object or system, and deviations therefrom. Exploring this problem, and how to fix it, helps to illuminate the central role this distinction plays in our causal thinking.

The majority of the currently flourishing theories of actual causation are located in a broadly counterfactual framework that draws on structural equations. In order to account for cases of symmetric overdeterminiation and preemption, these theories resort to rather intricate analytical tools, most of all, to what Hitchcock has labeled explicitly nonforetracking counterfactuals. This paper introduces a regularity theoretic approach to actual causation that only employs material conditionals, standard Boolean minimization procedures, and a stability condition that regulates the behavior of causal (...) models under model expansions. Notwithstanding its lightweight analytical toolbox, this regularity theory performs at least as well as the structural equations accounts with their heavy appliances. (shrink)

We propose a new definition of actual causes, using structural equations to model counterfactuals. We show that the definition yields a plausible and elegant account of causation that handles well examples which have caused problems for other definitions and resolves major difficultiesn in the traditional account.

The investigation of probabilistic causality has been plagued by a variety of misconceptions and misunderstandings. One has been the thought that the aim of the probabilistic account of causality is the reduction of causal claims to probabilistic claims. Nancy Cartwright (1979) has clearly rebutted that idea. Another ill-conceived idea continues to haunt the debate, namely the idea that contextual unanimity can do the work of objective homogeneity. It cannot. We argue that only objective homogeneity in combination with a causal interpretation (...) of Bayesian networks can provide the desired criterion of probabilistic causality. (shrink)

This paper presents an attempt to integrate theories of causal processes—of the kind developed by Wesley Salmon and Phil Dowe—into a theory of causal models using Bayesian networks. We suggest that arcs in causal models must correspond to possible causal processes. Moreover, we suggest that when processes are rendered physically impossible by what occurs on distinct paths, the original model must be restricted by removing the relevant arc. These two techniques suffice to explain cases of late preëmption and other cases (...) that have proved problematic for causal models. (shrink)

Explainable artificial intelligence (XAI) aims to help people understand black box algorithms, particularly of their outputs. But what are these explanations and when is one explanation better than another? The manipulationist definition of explanation from the philosophy of science offers good answers to these questions, holding that an explanation consists of a generalization that shows what happens in counterfactual cases. Furthermore, when it comes to explanatory depth this account holds that a generalization that has more abstract variables, is broader in (...) scope and/or more accurate is better. By applying these definitions and contrasting them with alternative definitions in the XAI literature I hope to help clarify what a good explanation is for AI. (shrink)

This paper develops axiomatic foundations for a probabilistic-interventionist theory of causal strength. Transferring methods from Bayesian confirmation theory, I proceed in three steps: I develop a framework for defining and comparing measures of causal strength; I argue that no single measure can satisfy all natural constraints; I prove two representation theorems for popular measures of causal strength: Pearl's causal effect measure and Eells' difference measure. In other words, I demonstrate these two measures can be derived from a set of plausible (...) adequacy conditions. The paper concludes by sketching future research avenues. (shrink)

This paper explores some issues about the choice of variables for causal representation and explanation. Depending on which variables a researcher employs, many causal inference procedures and many treatments of causation will reach different conclusions about which causal relationships are present in some system of interest. The assumption of this paper is that some choices of variables are superior to other choices for the purpose of causal analysis. A number of possible criteria for variable choice are described and defended within (...) a broadly interventionist approach to causation. (shrink)

In recent years, state-of-the-art artificial intelligence systems have started to show signs of what might be seen as human level intelligence. More specifically, large language models such as OpenAI’s GPT-3, and more recently Google’s PaLM and DeepMind’s GATO, are performing amazing feats involving the generation of texts. However, it is acknowledged by many researchers that contemporary language models, and more generally, learning systems, still lack important capabilities, such as understanding, reasoning and the ability to employ knowledge of the world and (...) common sense in order to reach or at least advance toward general intelligence. Some believe that scaling will eventually bring about these capabilities; others think that a different architecture is needed. In this paper, we focus on the latter, with the purpose of integrating a theoretical–philosophical conception of understanding as knowledge of dependence relations, with the high-level requirements and engineering design of a robust AI system, which integrates machine learning and symbolic components. (shrink)

Natural conditions are provided that are sufficient to ensure that causality as defined by approaches that use counterfactual dependence and structural equations will be transitive.

Newsome ((2003). The debate between current versions of covariation and mechanism approaches to causal inference. Philosophical Psychology, 16, 87-107.) recently published a critical review of psychological theories of human causal inference. In that review, he characterized covariation and mechanism theories, the two dominant theory types, as competing, and offered possible ways to integrate them. I argue that Newsome has misunderstood the theoretical landscape, and that covariation and mechanism theories do not directly conflict. Rather, they rely on distinct sets of reliable (...) indicators of causation, and focus on different types of causation (type vs. token). There are certainly debates in the research field, but the theoretical landscape is not as fractured as Newsome suggests, and a potential unifying framework has already emerged using causal Bayes nets. Philosophical work on causal epistemology matters for psychologists, but not in the way Newsome suggests. (shrink)

The present paper aims to complement causal model approaches to causal explanation by Woodward [15], Halpern and Pearl [5], and Strevens [14]. It centres on a strengthened Ramsey Test of conditionals: α ≫ γ iff, after sus- pending judgment about α and γ, an agent can infer γ from the supposition of α. It has been shown by Andreas and Gu ̈nther [1] that such a conditional can be used as starting point of an analysis of ‘because’ in natural language. (...) In what follows, we shall refine this analysis so as to yield a fully fledged account of causal explanation. (shrink)