Repository-level code comprehension and knowledge sharing remain core challenges in software engineering. Large language models (LLMs) have shown promise by generating explanations of program structure and logic. Retrieval-Augmented Generation (RAG), the state-of-the-art (SOTA), improves relevance by injecting context at inference time. However, these approaches still face limitations: First, semantic fragmentation across structural boundaries impairs comprehension, as relevant knowledge is distributed across multiple files within a repository. Second, retrieval inefficiency and attention saturation degrade performance in RAG workflows, where long, weakly aligned contexts overwhelm model attention. Third, repository specific training data is scarce, often outdated, incomplete or misaligned. Finally, proprietary LLMs hinder industrial adoption due to privacy and deployment constraints. To address these issues, we propose Key-Augmented Neural Triggers (KANT), a novel approach that embeds knowledge anchors, symbolic cues linking code regions to semantic roles, into both training and inference. Unlike prior methods, KANT enables internal access to repository specific knowledge, reducing fragmentation and grounding inference in localized, semantically structured memory. Moreover, we synthesize specialized instruction tuning data directly from code, eliminating reliance on noisy or outdated documentation and comments. At inference, knowledge anchors replace verbose context, reducing token overhead and latency while supporting efficient, on premise deployment. We evaluate KANT via: a qualitative human evaluation of the synthesized dataset’s intent coverage and quality across five dimensions; compare against SOTA baselines across five qualitative dimensions and inference speed; and replication across different LLMs to assess generalizability. Results show that the synthetic training data aligned with information-seeking needs: over 90% of questions and answers were rated relevant and understandable; 77.34%, 69.53%, and 64.58% of answers were considered useful, accurate, and complete, respectively. KANT achieved over 60% preference from human annotators and a LocalStack expert over the baselines (e.g., 21% RAG) and notably the expert preferred KANT in over 79% of cases. Also, KANT reduced inference latency by up to 85% across all models. Overall, KANT demonstrated its effectiveness across all evaluated areas, implying that it is well-suited for scalable, low-latency, on-premise deployments, providing a strong foundation for repository-level code comprehension.

On-the-fly syntax highlighting involves the rapid association of visual secondary notation with each character of a language derivation. This task has grown in importance due to the widespread use of online software development tools, which frequently display source code and heavily rely on efficient syntax highlighting mechanisms. In this context, resolvers must address three key demands: speed, accuracy, and development costs. Speed constraints are crucial for ensuring usability, providing responsive feedback for end users and minimizing system overhead. At the same time, precise syntax highlighting is essential for improving code comprehension. Achieving such accuracy, however, requires the ability to perform grammatical analysis, even in cases of varying correctness. Additionally, the development costs associated with supporting multiple programming languages pose a significant challenge. The technical challenges in balancing these three aspects explain why developers today experience significantly worse code syntax highlighting online compared to what they have locally. The current state-of-the-art relies on leveraging programming languages’ original lexers and parsers to generate syntax highlighting oracles, which are used to train base Recurrent Neural Network models. However, questions of generalisation remain. This paper addresses this gap by extending previous work validation dataset to six mainstream programming languages thus providing a more thorough evaluation. In response to limitations related to evaluation performance and training costs, this work introduces a novel Convolutional Neural Network (CNN) based model, specifically designed to mitigate these issues. Furthermore, this work addresses an area previously unexplored performance gains when deploying such models on GPUs. The evaluation demonstrates that the new CNN-based implementation is significantly faster than existing state-of-the-art methods, while still delivering the same near-perfect accuracy.

Verifying the execution of a program is complicated and often limited by the inability to validate the code's correctness. It is a crucial aspect of scientific research, where it is needed to ensure the reproducibility and validity of experimental results. Similarly, in customer software testing, it is difficult for customers to verify that their specific program version was tested or executed at all. Existing state-of-the-art solutions, such as hardware-based approaches, constraint solvers, and verifiable computation systems, do not provide definitive proof of execution, which hinders reliable testing and analysis of program results. In this paper, we propose an innovative approach that combines a prototype programming language called Mona with a certification protocol OCCP to enable the distributed and decentralized re-execution of program segments. Our protocol allows for certification of program segments in a distributed, immutable, and trustworthy system without the need for naive re-execution, resulting in significant improvements in terms of time and computational resources used. We also explore the use of blockchain technology to manage the protocol workflow following other approaches in this space. Our approach offers a promising solution to the challenges of program execution verification and opens up opportunities for further research and development in this area. Our findings demonstrate the efficiency of our approach in reducing the number of program executions by up to 20-fold, while maintaining resilience against various malicious attacks compared to existing state-of-the-art methods, thus improving the efficiency of certifying program executions. Additionally, our approach handles up to 40% malicious workers effectively, showcasing resilience in detecting and mitigating malicious behavior. In theEquivalentRegistersAttackscenario, it successfully identifies divergent executions even when register values and results appear identical. Moreover, our findings highlight improvements in time and gas efficiency for longer-running problems (scaled with a multiplier of$1{,}000$) compared to baseline methods. Specifically, adopting an informed step size reduces execution time by up to 43-fold and gas costs by up to 12-fold compared to the baseline. Similarly, the informed step size approach reduces execution time by up to 6-fold and gas costs by up to 26-fold compared to a non-informed variation using a step size of$1{,}000$.

Abstract Creative thinking is desirable in many professions. This article reports new research that followed a design science approach to develop and investigate a co‐creative tool called Sport Sparks in one profession – the coaching of professional football players. In response to a coach entering a text description of a coaching challenge (e.g., struggling to maintain the fitness of an athlete) into the tool, the tool automatically generated potentially novel ideas (e.g., reducing game time and changing their nutrition) that the coach could select and/or adapt and evolve into a simple action plan (e.g., which links nutrition to increased game time). This Sport Sparks tool was designed to be an example of human‐centred artificial intelligence that aspires to empower humans, to deliver high levels of human control as well as automation, and empower people rather than emulate their expertise. It was engineered with rule‐based reasoning to automate the generation of potential new ideas that coaches could select and refine during interactions which provide high user control over this automation. The potential of such a co‐creative tool, and value of the guidelines, were demonstrated during the tool's evaluation by coaching practitioners at a Premier League football club. The practitioners used the tool to generate new ideas to coaching challenges, and reported evidence of different forms of creative thinking, although some also reported the need for more support for creative collaborations and solution planning. The paper ends by discussing future directions for both the Sport Sparks tool and other co‐creative AI tools.

Sport Sparks™ is a new digital tool that has been researched and developed to augment the creative thinking of sports coaches when resolving challenges experienced by athletes. Most sports coaches work across multiple training sites and have limited opportunities and resources for creative thinking. The Sport Sparks™ tool was designed to provide ready-to-use guidance for creative thinking, via mobile devices, that is generated using automated natural language processing, rule-based reasoning and creative search. This short technical demonstration paper summarises and demonstrates with examples the different strategies and features implemented in Sport Sparks™ to augment coach creative thinking.