Kit Fieldhouse | Search arXiv

arXiv2026

AI-Ready Control System for the Fermilab Accelerator Complex

Reliable, high-intensity operation of the Fermilab Accelerator Complex is critical to the success of the Long-Baseline Neutrino Facility and Deep Underground Neutrino Experiment. We describe the requirements and infrastructure necessary to support routine use of artificial intelligence and machine learning (AI/ML) in the accelerator control system. Three capabilities are identified: a machine learning operations (MLOps) framework standardizing the lifecycle of AI/ML automation from data management through deployment and monitoring; a data quality framework defining and enforcing standards required to build trustworthy AI/ML applications; and workflow integration with large language models to assist physicists, engineers, and operators with information retrieval, code development, and routine analysis. Use cases spanning beam diagnostics, beam control, and support system automation illustrate the technical requirements across the complex.

physics.acc-ph↗

arXiv2020

Moves on $k$-graphs preserving Morita equivalence

We initiate the program of extending to higher-rank graphs ($k$-graphs) the geometric classification of directed graph $C^*$-algebras, as completed in the 2016 paper of Eilers, Restorff, Ruiz, and Sorensen [ERRS16]. To be precise, we identify four "moves," or modifications, one can perform on a $k$-graph $\Lambda$, which leave invariant the Morita equivalence class of its $C^*$-algebra $C^*(\Lambda)$. These moves -- insplitting, delay, sink deletion, and reduction -- are inspired by the moves for directed graphs described by Sorensen [S\o13] and Bates-Pask [BP04]. Because of this, our perspective on $k$-graphs focuses on the underlying directed graph. We consequently include two new results, Theorem 2.3 and Lemma 2.9, about the relationship between a $k$-graph and its underlying directed graph.

math.OA↗