Related papers: Shining a Light on Forensic Black-Box Studies

Many software engineering tasks, such as testing, and anomaly detection can benefit from the ability to infer a behavioral model of the software.Most existing inference approaches assume access to code to collect execution sequences. In…

Automated decision systems are increasingly used for consequential decision making -- for a variety of reasons. These systems often rely on sophisticated yet opaque models, which do not (or hardly) allow for understanding how or why a given…

Machine learning risks reinforcing biases present in data and, as we argue in this work, in what is absent from data. In healthcare, societal and decision biases shape patterns in missing data, yet the algorithmic fairness implications of…

Whilst an abundance of techniques have recently been proposed to generate counterfactual explanations for the predictions of opaque black-box systems, markedly less attention has been paid to exploring the uncertainty of these generated…

The widespread adoption of natural language processing techniques has led to an unprecedented growth of text classifiers across the modern web. Yet many of these models circulate with their internal semantics undocumented or even…

Unsupervised black-box models are challenging to interpret. Indeed, most existing explainability methods require labels to select which component(s) of the black-box's output to interpret. In the absence of labels, black-box outputs often…

Missing data has the potential to affect analyses conducted in all fields of scientific study, including healthcare, economics, and the social sciences. Several approaches to unbiased inference in the presence of non-ignorable missingness…

Local explanation frameworks aim to rationalize particular decisions made by a black-box prediction model. Existing techniques are often restricted to a specific type of predictor or based on input saliency, which may be undesirably…

With the growing abundance of unlabeled data in real-world tasks, researchers have to rely on the predictions given by black-boxed computational models. However, it is an often neglected fact that these models may be scoring high on…

In the United States, firearm-related deaths and injuries are a major public health issue. Because of limited federal action, state policies are particularly important, and their evaluation informs the actions of other policymakers. The…

Familiar statistical tests and estimates are obtained by the direct observation of cases of interest: a clinical trial of a new drug, for instance, will compare the drug's effects on a relevant set of patients and controls. Sometimes,…

The causes underlying unfair decision making are complex, being internalised in different ways by decision makers, other actors dealing with data and models, and ultimately by the individuals being affected by these decisions. One frequent…

In AI and law, systems that are designed for decision support should be explainable when pursuing justice. In order for these systems to be fair and responsible, they should make correct decisions and make them using a sound and transparent…

A paper evaluating the effects of lessons intended to encourage high school students to continue physics studies made some important errors. One was to underestimate the width of confidence intervals by failing to use standard cluster…

In this paper we examine the claims made by Bullock et. al. on the applicability of black-box injury risk approaches in the sports injury domain. Overall, we agree that transparency is necessary for Machine Learning models to be useful in…

In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The…

Risk assessment tools are widely used around the country to inform decision making within the criminal justice system. Recently, considerable attention has been devoted to the question of whether such tools may suffer from racial bias. In…

With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing need for effective…

Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification. In practice, the variance on some data examples is so large that decisions can be effectively arbitrary.…

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…