A widespread need to explain the behavior and outcomes of AI-based systems has emerged, due to their ubiquitous presence. Thus, providing renewed momentum to the relatively new research area of eXplainable AI (XAI). Nowadays, the importance of XAI lies in the fact that the increasing control transference to this kind of system for decision making -or, at least, its use for assisting executive stakeholders- already affects many sensitive realms (as in Politics, Social Sciences, or Law). The decision-making power handover to (...) opaque AI systems makes mandatory explaining those, primarily in application scenarios where the stakeholders are unaware of both the high technology applied and the basic principles governing the technological solutions. The issue should not be reduced to a merely technical problem; the explainer would be compelled to transmit richer knowledge about the system (including its role within the informational ecosystem where he/she works). To achieve such an aim, the explainer could exploit, if necessary, practices from other scientific and humanistic areas. The first aim of the paper is to emphasize and justify the need for a multidisciplinary approach that is beneficiated from part of the scientific and philosophical corpus on Explaining, underscoring the particular nuances of the issue within the field of Data Science. The second objective is to develop some arguments justifying the authors’ bet by a more relevant role of ideas inspired by, on the one hand, formal techniques from Knowledge Representation and Reasoning, and on the other hand, the modeling of human reasoning when facing the explanation. This way, explaining modeling practices would seek a sound balance between the pure technical justification and the explainer-explainee agreement. (shrink)

We revisit the flight-to-quality and flight-from-quality occurrences vis-à-vis the stock-bond nexus across differing investment time scales in the COVID-19 era, using a novel technique hinged on a denoised frequency-domain transfer entropy. Our findings divulge that flights, both FTQ and FFQ, could be attained during stress periods. Generally, in the intermediate term of the COVID-19 pandemic, both Islamic and conventional bonds could act as safe havens, diversifiers, and hedges for international equities, and the same could be observed for international equities. We (...) reiterate empirically that flights may improve the financial system’s stability and robustness by allowing diversity to be effective when it is most required. The findings have financial and portfolio implications for investors considering how to deploy their investments in the COVID-19 era. Our findings may impact policymakers’ responses to changes in various asset classes, allowing them to better monitor financial markets and adjust macroeconomic policies. (shrink)

Recent years have seen growing interest in modifying interventionist accounts of causal explanation in order to characterise noncausal explanation. However, one surprising element of such accounts is that they have typically jettisoned the core feature of interventionism: interventions. Indeed, the prevailing opinion within the philosophy of science literature suggests that interventions exclusively demarcate causal relationships. This position is so prevalent that, until now, no one has even thought to name it. We call it “intervention puritanism” (I-puritanism, for short). In this (...) paper, we mount the first sustained defence of the idea that there are distinctively noncausal explanations which can be characterized in terms of possible interventions; a position we call “intervention liberalism” (I-liberalism, for short). While many have followed James Woodward (2003) in committing to I-puritanism, we trace support for I-liberalism back to the work of Jaegwon Kim (1974). Furthermore, we analyse two recent sources of scepticism regarding I-liberalism: debate surrounding mechanistic constitution; and attempts to provide a monistic account of explanation. We show that neither literature provides compelling reasons for adopting I-puritanism. Finally, we present a novel taxonomy of available positions upon the role of possible interventions in explanation: weak causal imperialism; strong causal imperialism; monist intervention puritanism; pluralist intervention puritanism; monist intervention liberalism; and finally, the specific position defended in this paper, pluralist intervention liberalism. (shrink)

These preprints were automatically compiled into a PDF from the collection of papers deposited in PhilSci-Archive in conjunction with the PSA 2018.

The very expertise with which psychologists wield their tools for achieving laboratory control may have had the unwelcome effect of blinding psychologists to the possibilities of discovering principles of behavior without conducting experiments. When creatively interrogated, a diverse range of large, real-world data sets provides powerful diagnostic tools for revealing principles of human judgment, perception, categorization, decision-making, language use, inference, problem solving, and representation. Examples of these data sets include patterns of website links, dictionaries, logs of group interactions, collections of (...) images and image tags, text corpora, history of financial transactions, trends in twitter tag usage and propagation, patents, consumer product sales, performance in high-stakes sporting events, dialect maps, and scientific citations. The goal of this issue is to present some exemplary case studies of mining naturally existing data sets to reveal important principles and phenomena in cognitive science, and to discuss some of the underlying issues involved with conducting traditional experiments, analyses of naturally occurring data, computational modeling, and the synthesis of all three methods. (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)

For years, the number of opaque algorithmic decision-making systems (ADM systems) with a large impact on society has been increasing: e.g., systems that compute decisions about future recidivism of criminals, credit worthiness, or the many small decision computing systems within social networks that create rankings, provide recommendations, or filter content. Concerns that such a system makes biased decisions can be difficult to investigate: be it by people affected, NGOs, stakeholders, governmental testing and auditing authorities, or other external parties. Scientific testing (...) and auditing literature rarely focuses on the specific needs for such investigations and suffers from ambiguous terminologies. With this paper, we aim to support this investigation process by collecting, explaining, and categorizing methods of testing for bias, which are applicable to black-box systems, given that inputs and respective outputs can be observed. For this purpose, we provide a taxonomy that can be used to select suitable test methods adapted to the respective situation. This taxonomy takes multiple aspects into account, for example the effort to implement a given test method, its technical requirement (such as the need of ground truth) and social constraints of the investigation, e.g., the protection of business secrets. Furthermore, we analyze which test method can be used in the context of which black box audit concept. It turns out that various factors, such as the type of black box audit or the lack of an oracle, may limit the selection of applicable tests. With the help of this paper, people or organizations who want to test an ADM system for bias can identify which test methods and auditing concepts are applicable and what implications they entail. (shrink)

Habilitation thesis in psychology. The book consists of a collection of reasoning studies. The experimental investigations will take us from people’s reasoning about probabilities, entailments, pragmatic factors, argumentation, and causality to morality. An overarching theme of the book is norm pluralism and individual differences in rationality research.

Recent advances in causal reasoning have given rise to a computational model that emulates the process by which humans generate, evaluate, and distinguish counterfactual sentences. Contrasted with the “possible worlds” account of counterfactuals, this “structural” model enjoys the advantages of representational economy, algorithmic simplicity, and conceptual clarity. This introduction traces the emergence of the structural model and gives a panoramic view of several applications where counterfactual reasoning has benefited problem areas in the empirical sciences.

There is an ethical dilemma present when considering updating predictive clinical artificial intelligence (AI) models, which should be part of the departmental quality improvement process. One needs to consider whether withdrawing the AI model is necessary to obtain the relevant information from a naive patient population or whether to use causal inference techniques to obtain this information. Withdrawing an AI model from patient care might pose challenges if the AI model is considered standard of care, while use of causal inference (...) will not be reliable if the relevant statistical assumptions do not hold true. Hence, each of these two updating strategies is associated with patient risks, but lack of reliable data might endanger future patients. Similarly, not withdrawing an outdated AI might also expose patients to risk. Here I propose a high level ethical framework – epistemic risk management - that provides guidance for which route of model updating should be taken based on the likelihood of the assumptions used during the creation of the original AI model and the assumptions required for causal inference holding true. This approach balances our uncertainty about the status of the AI as standard of care with the risk of not obtaining the necessary data, so as to increase the probability of benefiting current and future patients for whose care the AI is being used. (shrink)

Owing to the adverse impact of the COVID-19 pandemic on world economies, it is expected that information flows between commodities and uncertainties have been transformed. Accordingly, the resulting twisted risk among commodities and related uncertainties is presumed to rise during stressed market conditions. Therefore, investors feel pressured to find safe haven investments during the pandemic. For this reason, we model a mixture of asymmetric and non-linear bi-directional causality between global commodities and uncertainties at different frequencies through the information flow theory. (...) Consequently, we utilise the complete ensemble empirical mode decomposition with adaptive noise and the Rényi effective transfer entropy techniques to establish the dynamic flow of information. The intrinsic mode functions from the CEEMDAN are carefully extracted into multi-frequencies through cluster analysis to reconstruct the series into high, medium, and low frequencies in addition to the residue. We utilise daily data from December 31st, 2019, to March 31st, 2021, to provide insights into the COVID-19 pandemic. The correlation coefficients and variances demonstrate that the high frequency which measures the short-term dynamics is the dominant frequency, suggesting short-lived market fluctuations relative to real economic growth for institutional investors. Moreover, outcomes from the multi-frequency entropy indicate a negative bi-directional causality of information flow between global commodities and uncertainties, especially in the long term. Generally, the findings present pertinent inferences for portfolio diversification, policy decisions, and risk management schemes for global commodities and markets volatilities. We, therefore, advocate that market volatilities act as effective hedges for global commodities, and they clearly act as balancing assets rather than substitutes in the long-term dynamics of the COVID-19 pandemic. Investors who delayed in investing within financial markets of commodities and market volatilities are likely to minimise their portfolio risks. (shrink)

Applying causal methods to fields such as healthcare, marketing, and economics receives increasing interest. In particular, optimising the individual-treatment-effect – often referred to as uplift modelling – has peaked in areas such as precision medicine and targeted advertising. While existing techniques have proven useful in many settings, they suffer vividly in a dynamic environment. To address this issue, we propose a novel optimisation target that is easily incorporated in bandit algorithms. Incorporating this target creates a causal model which we name (...) an uplifted contextual multi-armed bandit. Experiments on real and simulated data show the proposed method to effectively improve upon the state-of-the-art. All our code is made available online at https://github.com/vub-dl/u-cmab. (shrink)

While there is a substantive literature on the link between welfare states and individuals’ trust, little is known about the micro-linkage of the conditionality of welfare as a driver of trust. This study presents a unique randomized social experiment investigating this link. Recipients of the regular Dutch social assistance policy are compared to recipients of two alternative schemes inspired by the basic income and based on a more trusting and unconditional approach, testing the main reciprocity argument in the literature: a (...) trusting government will harvest trust from welfare recipients in return. Particularly trust in local government – the level at which the experiment was implemented – increases among recipients of the alternative treatments. Subsequently, we innovatively theorize and test rigorously which mediating mechanisms might explain this increase. Policy evaluation, social integration, and psychological well-being are studied in this respect. Of these, the only underlying mechanism proven to mediate the treatment effect in local political trust, is citizens’ satisfaction with policy. (shrink)

The unsustainable growth in U.S. health care costs is in large part attributable to the rising costs of pharmaceuticals and medical devices and to unnecessary medical procedures. This fact has led health reform advocates and policymakers to place considerable hope in the idea that increased government support for research on the comparative effectiveness of medical treatments will eventually help to reduce health care expenses by informing patients, health care providers, and payers about which treatments for common conditions are effective and (...) which are not. Comparative effectiveness research has shown in some cases that expensive but commonly used treatments are significantly less effective than relatively inexpensive alternatives. Critics warn, however, that CER will homogenize patient care, limit patient choices, and lead to improper health care rationing and even to the denial of lifesaving treatments. (shrink)

Within the field of causal inference, it is desirable to learn the structure of causal relationships holding between a system of variables from the correlations that these variables exhibit; a sub-problem of which is to certify whether or not a given causal hypothesis is compatible with the observed correlations. A particularly challenging setting for assessing causal compatibility is in the presence of partial information; i.e. when some of the variables are hidden/latent. This paper introduces the possible worlds framework as a (...) method for deciding causal compatibility in this difficult setting. We define a graphical object called a possible worlds diagram, which compactly depicts the set of all possible observations. From this construction, we demonstrate explicitly, using several examples, how to prove causal incompatibility. In fact, we use these constructions to prove causal incompatibility where no other techniques have been able to. Moreover, we prove that the possible worlds framework can be adapted to provide a complete solution to the possibilistic causal compatibility problem. Even more, we also discuss how to exploit graphical symmetries and cross-world consistency constraints in order to implement a hierarchy of necessary compatibility tests that we prove converges to sufficiency. (shrink)