相关论文: What Causes a System to Satisfy a Specification?

Validation is often defined as the process of determining the degree to which a model is an accurate representation of the real world from the perspective of its intended uses. Validation is crucial as industries and governments depend…

It is widely accepted that understanding system requirements is important for software development project success. However, this paper presents two novel challenges to the requirements concept. First, where many plausible approaches to…

Causal models defined in terms of structural equations have proved to be quite a powerful way of representing knowledge regarding causality. However, a number of authors have given examples that seem to show that the Halpern-Pearl (HP)…

Reliability prediction is crucial for ensuring the safety and security of software systems, especially in the context of industry practices. While various metrics and measurements are employed to assess software reliability, the complexity…

In the recent years, machine learning has made great advancements that have been at the root of many breakthroughs in different application domains. However, it is still an open issue how make them applicable to high-stakes or…

Test suites are designed to validate the operation of a system against requirements. One important aspect of a test suite design is to ensure that system operation logic is tested completely. A test suite should drive a system through all…

There are many widely used tools for measuring test-coverage and code-coverage. Test coverage is the ratio of requirements or other non-code artifacts covered by a test suite, while code-coverage is the ratio of source code covered by…

The importance of security metrics can hardly be overstated. Despite the attention that has been paid by the academia, government and industry in the past decades, this important problem stubbornly remains open. In this survey, we present a…

As autonomous systems rapidly become ubiquitous, there is a growing need for a legal and regulatory framework to address when and how such a system harms someone. There have been several attempts within the philosophy literature to define…

Test effectiveness refers to the capability of a test suite in exposing faults in software. It is crucial to be aware of factors that influence this capability. We aim at inferring the causal relationship between the two factors (i.e.,…

Understanding causal relationships among the variables of a system is paramount to explain and control its behavior. For many real-world systems, however, the true causal graph is not readily available and one must resort to predictions…

There is growing interest in explainable recommender systems that provide recommendations along with explanations for the reasoning behind them. When evaluating recommender systems, most studies focus on overall recommendation performance.…

We propose a new definition of actual cause, 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…

Determining whether a provided context contains sufficient information to answer a question is a critical challenge for building reliable question-answering systems. While simple prompting strategies have shown success on factual questions,…

In this paper we introduce a notion of counterfactual causality in the Halpern and Pearl sense that is compositional with respect to the interleaving of transition systems. The formal framework for reasoning on what caused the violation of…

Existing procedures for model validation have been deemed inadequate for many engineering systems. The reason of this inadequacy is due to the high degree of complexity of the mechanisms that govern these systems. It is proposed in this…

Many debugging tools rely on compiler-produced metadata to present a source-language view of program states, such as variable values and source line numbers. While this tends to work for unoptimised programs, current compilers often…

To be considered reliable, a model must be calibrated so that its confidence in each decision closely reflects its true outcome. In this blogpost we'll take a look at the most commonly used definition for calibration and then dive into a…

Recommender systems have become crucial in information filtering nowadays. Existing recommender systems extract user preferences based on the correlation in data, such as behavioral correlation in collaborative filtering, feature-feature,…

AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…