Related papers: Merit and Blame Assignment with Kind 2
The traceability of requirements in the information system design process is considered an essential property of the project, one of its quality characteristics. The point here is that traceability provides the methods of validation and…
This paper introduces an explanation framework designed to enhance the quality of rules in knowledge-based reasoning systems based on dataset-driven insights. The traditional method for rule induction from data typically requires…
Environmental perception obtained via object detectors have no predictable safety layer encoded into their model schema, which creates the question of trustworthiness about the system's prediction. As can be seen from recent adversarial…
Fault detection is crucial for ensuring the safety and reliability of modern industrial systems. However, a significant scientific challenge is the lack of rigorous risk control and reliable uncertainty quantification in existing diagnostic…
Type systems certify program properties in a compositional way. From a bigger program one can abstract out a part and certify the properties of the resulting abstract program by just using the type of the part that was abstracted away.…
The high cost of the test can be dramatically reduced, provided that the coverability as an inherent feature of the code under test is predictable. This article offers a machine learning model to predict the extent to which the test could…
Architecture patterns capture architectural design experience and provide abstract solutions to recurring architectural design problems. They consist of a description of component types and restrict component connection and activation.…
Enforcing safety for dynamical systems is challenging, since it requires constraint satisfaction along trajectory predictions. Equivalent control constraints can be computed in the form of sets that enforce positive invariance, and can thus…
Datasets with significant proportions of bias present threats for training a trustworthy model on NLU tasks. Despite yielding great progress, current debiasing methods impose excessive reliance on the knowledge of bias attributes.…
Rule models are often preferred in prediction tasks with tabular inputs as they can be easily interpreted using natural language and provide predictive performance on par with more complex models. However, most rule models' predictions are…
The prediction quality of machine learnt models and the functionality they ultimately enable (e.g., object detection), is typically evaluated using a variety of quantitative metrics that are specified in the associated model performance…
The reliability and proper function of data-driven applications hinge on the data's continued conformance to the applications' initial design. When data deviates from this initial profile, system behavior becomes unpredictable. Data…
The enormous growth of the complexity of modern computer systems leads to an increasing demand for techniques that support the comprehensibility of systems. This has motivated the very active research field of formal methods that enhance…
Within a component-based approach allowing dynamic reconfigurations, sequences of successive reconfiguration operations are expressed by means of reconfiguration paths, possibly infinite. We show that a subclass of such paths can be…
`Trackability', the ability of systems to follow arbitrary reference commands, is investigated in this work. Controllability is not useful in explaining the tracking behavior of system outputs, a gap that is often overlooked. Trackability…
The importance of mission or safety critical software systems in many application domains of embedded systems is continuously growing, and so is the effort and complexity for reliability and safety analysis. Model driven development is…
Model-based safety analysis approaches aim at finding critical failure combinations by analysis of models of the whole system (i.e. software, hardware, failure modes and environment). The advantage of these methods compared to traditional…
Modern software systems are typically configurable, a fundamental prerequisite for wide applicability and reusability. This flexibility poses an extraordinary challenge for quality assurance, as the enormous number of possible…
We propose using mechanistic interpretability -- techniques for reverse engineering model weights into human-interpretable algorithms -- to derive and compactly prove formal guarantees on model performance. We prototype this approach by…
This paper identifies a new class of shape invariant models. These models are based on extensions of conventional quantum mechanics that satisfy a string-motivated minimal length uncertainty relation. An important feature of our…