Responsibility and blame: a structural-model approach

By Hana Chockler, Joseph Y. Halpern. 2003

418 citations recorded by the source corpus.

Causality is typically treated an all-or-nothing concept; either A is a cause of B or it is not. We extend the definition of causality introduced by Halpern and Pearl [2004a] to take into account the degree of responsibility of A for B. For example, if someone wins an election 11-0, then each person who votes for him is less responsible for the victory than if he had won 6-5. We then define a notion of degree of blame, which takes into account an agent's epistemic state. Roughly speaking, the degree of blame of A for B is the expected degree of responsibility of A for B, taken over the epistemic state of an agent.

Subfields: Economics and Econometrics, Management Science and Operations Research, Philosophy

How researchers see this paper

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

In Economics and Econometrics

In Management Science and Operations Research

In Philosophy

Citations in the corpus

Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, background): “Chockler and Halpern [29] modified the structural equation model proposed by Halpern and Pearl [58] (see Section 2.”
Finding fault: Causality and counterfactuals in group attributions (2012, positive): “…with negative, and in particular severe, outcomes (Weiner, 1995); can be mitigated by possible justifications (Shaver, 1985) and ignorance on the part of the acting agent (Chockler & Halpern, 2004); and in the view of some scholars is closely linked with emotional responses (Alicke, 2000).”
Causal Responsibility and Counterfactuals (2013, methodology): “The case also provides a real-world example of over-determination, which plays a central role in philosophical discussions of causality (Collins, Hall, & Paul, 2004; Moore, 2009) and is seen as a major problem for standard counterfactual theories of causation.”
Degrees of Causation (2009, background): “An example is that due to Chockler and Halpern (2004) who present a measure that depends on the minimal number of changes that have to be made before an action becomes a NESS condition.”
Causes and explanations in the structural-model approach: Tractable cases (2002, methodology): “Finally, Chockler and Halpern [3] and Chockler, Halpern, and Kupferman [4] have shown that the optimization problems RESPONSIBILITY and BLAME are complete for the classes FP P 2 [log n] andFP Σ2 ‖ , respectively, in the general case, and complete for FP n] andFP ‖ , respectively, in the binary case.”
Causes and Explanations: A Structural-Model Approach: Part 1: Causes (2013, background): “easonableness of the deﬁnition. Further support is provided by the ease with which it can be extended to deﬁne other notions, such as explanation(see Part II of thispaper) and responsibilityand blame[Chockler and Halpern 2004]. A Appendix: Some Technical Issues In this appendix, we consider some tec”
Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems (2016, background): “Another thread of work by Halpern and Pearl discusses actual causation [40], which is extended in [41] to derive a measure of responsibility as degree of causality.”
Causal Reasoning and Large Language Models: Opening a New Frontier for Causality (2023, background): “Halpern (2016); Chockler & Halpern (2004) provide an SCM-based deﬁnition of responsibility; in simple terms, they deﬁne responsibility of event C for event E is 1/(N+1), where N is the minimal number of other causal events contributing to E that have had not happen to make C a necessary cause of E.”
Spreading the blame: The allocation of responsibility amongst multiple agents. (2010, positive): “First, although the Structural Model predicted the data best, there is considerable latitude for developing and testing other models.”
Intuitive Theories (2020, background): “…these accounts have been extended to give graded causal judgments by considering default states of variables (Halpern, 2008; Halpern & Hitchcock, forthcoming), or assign degrees of responsibility when multiple causes are at play (Chockler & Halpern, 2004; Lagnado, Gerstenberg, & Zultan, 2013).”
Judgments of cause and blame: the effects of intentionality and foreseeability. (2008, background): “When assessing people’s attributions, it is important to distinguish between judgments of cause and blame (Chockler & Halpern, 2003; Fincham & Jaspars, 1983; Shaver, 1985; Shultz & Schleifer, 1983).”
Causal superseding. (2015, background): “Building on formal structural models of causal responsibility (Chockler & Halpern, 2004; Halpern & Pearl, 2005), Lagnado et al. (2013) developed a criticality-pivotality model which predicts that people's responsibility attributions to individual group members are influenced both by (a) how…”