Tootfinder

A Metrics-Oriented Architectural Model to Characterize Complexity on Machine Learning-Enabled Systems
Renato Cordeiro Ferreira (University of S\~ao Paulo, Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)
https://arxiv.org/abs/2506.08153

A Metrics-Oriented Architectural Model to Characterize Complexity on Machine Learning-Enabled Systems
How can the complexity of ML-enabled systems be managed effectively? The goal of this research is to investigate how complexity affects ML-Enabled Systems (MLES). To address this question, this research aims to introduce a metrics-based architectural model to characterize the complexity of MLES. The goal is to support architectural decisions, providing a guideline for the inception and growth of these systems. This paper showcases the first step for creating the metrics-based architectural mode…

Definitions of the volume of a big cohomology class
Tiernan Cartwright
https://arxiv.org/abs/2506.09486 https://arxiv.org/pdf/2506.09…

Definitions of the volume of a big cohomology class
We elaborate on how two definitions of the volume of a big cohomology class are consistent. The first definition involves taking the absolutely continuous part of a closed positive current, and the second involves the non-pluripolar product. We also describe how a similar equality holds for the numerical restricted volume introduced by Collins and Tosatti.

JWST Coronagraphic Images of 14 Her c: a Cold Giant Planet in a Dynamically Hot, Multi-planet System
Daniella C. Bardalez Gagliuffi, William O. Balmer, Laurent Pueyo, Timothy D. Brandt, Mark R. Giovinazzi, Sarah Millholland, Brennen Black, Tiger Lu, Malena Rice, James Mang, Caroline Morley, Brianna Lacy, Julien Girard, Elisabeth Matthews, Aarynn Carter, Brendan P. Bowler, Jacqueline K. Faherty, Clemence Fontanive, Emily Rickman

JWST Coronagraphic Images of 14 Her c: a Cold Giant Planet in a Dynamically Hot, Multi-planet System
Most observed multi-planet systems are coplanar, in a dynamically "cold" configuration of concentric orbits like our own Solar System. With the James Webb Space Telescope (JWST) we have detected 14 Her c, the first mature and cold exoplanet directly imaged in a dynamically "hot", multi-planet system. With large eccentricities and a nonzero mutual inclination, the present-day architecture of this system points to a turbulent past and ongoing angular momentum exchange between the planetary orbits…

The Legacy of the Cartwright-Littlewood Collaboration
John Guckenheimer
https://arxiv.org/abs/2506.06889 https://arxiv.org/pdf/2506.0…

The Legacy of the Cartwright-Littlewood Collaboration
Mary L. Cartwright and John E. Littlewood published a short preliminary survey in 1945 describing results of their investigation of the forced van der Pol equation \begin{equation*} \ddot{y}-k(1-y^2)\dot{y}+y = b λk \cos(λt+a) \end{equation*} in which $b,λ,k,a$ are parameters with $k$ large. Their description of dynamical behavior now known as chaos in this dissipative dynamical system was a landmark in dynamical systems theory. Littlewood's monster paper containing the details of their inve…

Is Your Training Pipeline Production-Ready? A Case Study in the Healthcare Domain
Daniel Lawand (University of S\~ao Paulo), Lucas Quaresma (University of S\~ao Paulo), Roberto Bolgheroni (University of S\~ao Paulo), Alfredo Goldman (University of S\~ao Paulo), Renato Cordeiro Ferreira (University of S\~ao Paulo, Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)

Is Your Training Pipeline Production-Ready? A Case Study in the Healthcare Domain
Deploying a Machine Learning (ML) training pipeline into production requires robust software engineering practices. This differs significantly from experimental workflows. This experience report investigates this challenge in SPIRA, a project whose goal is to create an ML-Enabled System (MLES) to pre-diagnose insufficiency respiratory via speech analysis. The first version of SPIRA's training pipeline lacked critical software quality attributes. This paper presents an overview of the MLES, then…

This https://arxiv.org/abs/2309.15793 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_sta…

Targeting relative risk heterogeneity with causal forests
The identification of heterogeneous treatment effects (HTE) across subgroups is of significant interest in clinical trial analysis. Several state-of-the-art HTE estimation methods, including causal forests, apply recursive partitioning for non-parametric identification of relevant covariates and interactions. However, the partitioning criterion is typically based on differences in absolute risk. This can dilute statistical power by masking variation in the relative risk, which is often a more a…

Join the 2025 Maine AI 'unconference' on June 13 in Orono for face-to-face discussions whose topics will be democratically chosen by the attenders. (We've got expert panels too.) Register by this Friday—more at https://www.linkedin.com/posts/jonippolito

MLOps with Microservices: A Case Study on the Maritime Domain
Renato Cordeiro Ferreira (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Rowanne Trapmann (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University), Willem-Jan van den Heuvel (Jheronimus Academy of Data Science, Technical University of Eindhoven, Tilburg University)

MLOps with Microservices: A Case Study on the Maritime Domain
This case study describes challenges and lessons learned on building Ocean Guard: a Machine Learning-Enabled System (MLES) for anomaly detection in the maritime domain. First, the paper presents the system's specification, and architecture. Ocean Guard was designed with a microservices' architecture to enable multiple teams to work on the project in parallel. Then, the paper discusses how the developers adapted contract-based design to MLOps for achieving that goal. As a MLES, Ocean Guard emplo…

Profiles of Critical Flat Ribbon Knots
Jos\'e Ayala
https://arxiv.org/abs/2506.04403 https://arxiv.org/pdf/2506.04403

Profiles of Critical Flat Ribbon Knots
The main open problem in geometric knot theory is to provide a tabulation of knots based on an energy criterion, with the goal of presenting this tabulation in terms of global energy minimisers within isotopy classes, often referred to as ideal knots. Recently, the first examples of minimal length diagrams and their corresponding length values have been determined by Ayala, Kirszenblat, and Rubinstein. This article is motivated by the scarcity of examples despite several decades of intense rese…