Making Things Happen: A Theory of Causal Explanation

By Keith A. Markus. 2007

2,005 citations recorded by the source corpus.

Subfields: History and Philosophy of Science, Sociology and Political Science, Statistics and Probability, Causal Inference & Discovery, Philosophy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In History and Philosophy of Science

In Sociology and Political Science

In Statistics and Probability

In Causal Inference & Discovery

In Philosophy

Citations in the corpus

A theory of independent mechanisms for extrapolation in generative models (2020, background): “IM reﬂects a foundational aspect of causality, related to concepts in several ﬁelds, such as superex-ogeneity in economics (Engle, Hendry, and Richard 1983), the general concept of invariance in philosophy (Woodward 2003) and modularity .”
Invariant Risk Minimization (2019, background): “A large body of philosophical work [47, 42, 38, 12, 54, 13] studies the close link between invariance and causation.”
Behind Distribution Shift: Mining Driving Forces of Changes and Causal Arrows (2017, positive): “Problem 2, as a sub-problem of causal discovery, exploits a generalized notion of the invariance property [10] or the exogeneity property [2], [13] of causal systems: if there is no nonstationary confounder for Vi and Vj , then the causal mechanisms, represented by the conditional distributions P (V”
Explaining Classifiers with Causal Concept Effect (CaCE) (2019, background): “Using causal language for explanation has a long history, see [17] for a discussion from a philosophy of science point of view.”
A survey of algorithmic recourse: definitions, formulations, solutions, and prospects (2020, background): “Counterfactual reasoning has roots not only in the philosophy of science [81, 82, 108–110, 184], but also in the psychology There are, however, a number of implicit assumptions made in existing setups, e.g., that the world dynamics are known and do not change, the predictive (supervised) model is…”
A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence (2021, background): “…relate to either of the four theoretical milestones: Lewis-Stalnaker’s theory of closest possible worlds [36], [120], Pearl’s Structural Causal Models (SCM) [37], Wood-ward’s Counterfactual Theory of Explanation (CTE) [125], or the Neyman-Rubin Causal Model (NRCM) [107], [115] (see Table 5).”
The problem of variable choice (2016, background): “…characterization of what is involved in causal representation/ explanation, I think of this along broadly interventionist lines in the sense of Woodward (2003): successful causal explanation involves the representation of true claims about what would happen to some variables under…”
How, whether, why: Causal judgments as counterfactual contrasts (2015, background): “Some have argued that causation is fundamentally about dependence – what it means for C to have caused E is that E did somehow depend on C (Lewis, 2000; Woodward, 2003).”
Counterfactual Explanations for Machine Learning: A Review (2020, background): “Philosophers have also validated the concept of causal thinking due to counterfactuals [17, 114].”
Moving Beyond Causes: Optimality Models and Scientific Explanation (2015, background): “…to the causal approach, in order to provide an explanation a model must accurately represent the (contextually or metaphysically) salient causes of, or causal mechanisms that gave rise to, the explanandum (Craver 2007; Lewis 1986; Railton 1981; Salmon 1984; Strevens 2004, 2009; Woodward 2003).”
Learning a theory of causality. (2011, background): “A long tradition in psychology and philosophy has investigated the principles of causal understanding, largely converging on the interventionist or causal Bayes nets account of causality (Pearl, 2000; Woodward, 2003) as a description of the principles by which causal reasoning proceeds.”
Functional explaining: a new approach to the philosophy of explanation (2014, background): “12 See my (Wilkenfeld 2013a, p. 49-50, especially n. 28) for a more extensive defense of this claim.”
What’s in Your Head? Emergent Behaviour in Multi-Task Transformer Models (2021, methodology): “Moreover, we perform interventions (Woodward, 2005; Elazar et al., 2021), where we modify the input representation based on the arguments output by the extractive head, and show this leads to predictable changes in the behaviour of the”
Dissecting explanatory power (2010, background): “The advocates of the IBE have 1 Important exceptions are Miller (1987), Morton (2002), and Hitchcock and Woodward (2003). said surprisingly little about the explanatory virtues2 and our focus is precisely on the crucial notion of explanatory goodness.”
Explainable artificial intelligence (XAI), the goodness criteria and the grasp-ability test (2018, positive): “In particular, we rely on and further extend “the ability theory of understanding,” according to which, roughly speaking, the speaker well explains to the extent that the hearer understands the explanation[5, 4, 6, 7].”