Related papers: Making It Work Is the Work: Engineering Maturity a…
This volume contains the proceedings of MARS 2022, the fifth workshop on Models for Formal Analysis of Real Systems, held as part of ETAPS 2022, the European Joint Conferences on Theory and Practice of Software. The MARS workshops bring…
The foundational pretraining phase determines a model's capability ceiling, as post-training struggles to overcome capability foundations established during pretraining, yet it remains critically under-explored. This stems from a structural…
The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when…
The curse of knowledge can impede communication between experts and laymen. We propose a new task of expertise style transfer and contribute a manually annotated dataset with the goal of alleviating such cognitive biases. Solving this task…
This paper presents a bimodal logic for reasoning about knowledge during knowledge acquisition. One of the modalities represents (effort during) non-deterministic time and the other represents knowledge. The semantics of this logic are…
In the field of evaluation research, computer scientists live constantly upon dilemmas and conflicting theories. As evaluation is differently perceived and modeled among educational areas, it is not difficult to become trapped in dilemmas,…
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving…
Consistent confirmations obtained independently of each other lend credibility to a scientific result. We refer to results satisfying this consistency as reproducible and assume that reproducibility is a desirable property of scientific…
Humans can learn from very few samples, demonstrating an outstanding generalization ability that learning algorithms are still far from reaching. Currently, the most successful models demand enormous amounts of well-labeled data, which are…
MacGyvering is defined as creating or repairing something in an inventive or improvised way by utilizing objects that are available at hand. In this paper, we explore a subset of Macgyvering problems involving tool construction, i.e.,…
Computational Science on large high performance computing resources is hampered by the complexity of these systems. Much of this complexity is due to low-level details on these resources that are exposed to the application and the end user.…
This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the task itself. Code generation has progressed more reliably…
Analysis pipelines commonly use high-level technologies that are popular when created, but are unlikely to be readable, executable, or sustainable in the long term. A set of criteria is introduced to address this problem: Completeness (no…
ML 2.0: In this paper, we propose a paradigm shift from the current practice of creating machine learning models - which requires months-long discovery, exploration and "feasibility report" generation, followed by re-engineering for…
Analogy is one of the core capacities of human cognition; when faced with new situations, we often transfer prior experience from other domains. Most work on computational analogy relies heavily on complex, manually crafted input. In this…
Resilience is a feature that is gaining more and more attention in computer science and computer engineering. However, the definition of resilience for the cyber landscape, especially embedded systems, is not yet clear. This paper discusses…
For improving flexibility and robustness of the engineering of automated production systems (aPS) in case of extending, reducing or modifying parts, several approaches propose an encapsulation and clustering of related functions, e.g. from…
The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch…
Despite the advancement of machine learning techniques in recent years, state-of-the-art systems lack robustness to "real world" events, where the input distributions and tasks encountered by the deployed systems will not be limited to the…
Digital Engineering currently relies on costly and often bespoke integration of disparate software products to assemble the authoritative source of truth of the system-of-interest. Tools not originally designed to work together become an…