In this paper, we present a new algorithm, MiniFool, that implements physics-inspired adversarial attacks for testing neural network-based classification tasks in particle and astroparticle physics. While we initially developed the algorithm for the search for astrophysical tau neutrinos with the IceCube Neutrino Observatory, we apply it to further data from other science domains, thus demonstrating its general applicability. Here, we apply the algorithm to the well-known MNIST data set and furthermore, to Open Data data from the CMS experiment at the Large Hadron Collider. The algorithm is based on minimizing a cost function that combines a $χ^2$ based test-statistic with the deviation from the desired target score. The test statistic quantifies the probability of the perturbations applied to the data based on the experimental uncertainties. For our studied use cases, we find that the likelihood of a flipped classification differs for both the initially correctly and incorrectly classified events. When testing changes of the classifications as a function of an attack parameter that scales the experimental uncertainties, the robustness of the network decision can be quantified. Furthermore, this allows testing the robustness of the classification of unlabeled experimental data.

Located in China, Juno is a 17-country collaboration that will try to detect neutrinos and antineutrinos to learn more about their mass. Juno's sphere (bottom left) and photomultipliers (top right) for neutrino detection. Located 700 meters underground near the city of Jiangmen in southern China, a giant sphere--35 meters in diameter and filled with more than 20,000 tons of liquid--has just started a mission that will last for decades. This is Juno, the Jiangmen Underground Neutrino Observatory, a new, large-scale experiment studying some of the most mysterious and elusive particles known to science. Neutrinos are the most abundant particles in the universe with mass.

Breakthroughs, discoveries, and DIY tips sent every weekday. Billions of light-years away, a cosmic jet bearing a striking resemblance to the eye of Sauron from the Lord of the Rings is swirling at the heart of a very active galaxy. The unique cosmic body was spotted thanks to 15 years of observations using the Earth-based Very Long Baseline Ar-ray and is helping scientists better understand the anatomy of cosmic jets,powerful beams of plasma and energy that come from black holes, neutron stars, and other celestial bodies. The unique attributes of this "Eye of Sauron" cosmic jet is detailed in a study published August 12 in the journal Astronomy & Astrophysics. "When we reconstructed the image, it looked absolutely stunning," Yuri Kovalev, study co-author and astrophysicist at the Max Planck Institute for Radio Astronomy, said in a statement.

We introduce CLAPP (CLASS LLM Agent for Pair Programming), an interactive AI assistant designed to support researchers working with the Einstein-Boltzmann solver CLASS. CLAPP leverages large language models (LLMs) and domain-specific retrieval to provide conversational coding support for CLASS-answering questions, generating code, debugging errors, and producing plots. Its architecture combines multi-agent LLM orchestration, semantic search across CLASS documentation, and a live Python execution environment. Deployed as a user-friendly web application, CLAPP lowers the entry barrier for scientists unfamiliar with AI tools and enables more productive human-AI collaboration in computational and numerical cosmology. The app is available at https://classclapp.streamlit.app

Particle physics theories, such as those which explain neutrino flavor mixing, arise from a vast landscape of model-building possibilities. A model's construction typically relies on the intuition of theorists. It also requires considerable effort to identify appropriate symmetry groups, assign field representations, and extract predictions for comparison with experimental data. We develop an Autonomous Model Builder (AMBer), a framework in which a reinforcement learning agent interacts with a streamlined physics software pipeline to search these spaces efficiently. AMBer selects symmetry groups, particle content, and group representation assignments to construct viable models while minimizing the number of free parameters introduced. We validate our approach in well-studied regions of theory space and extend the exploration to a novel, previously unexamined symmetry group. While demonstrated in the context of neutrino flavor theories, this approach of reinforcement learning with physics software feedback may be extended to other theoretical model-building problems in the future.

Breakthroughs, discoveries, and DIY tips sent every weekday. For nearly two decades, balloons carrying highly sensitive atmospheric instruments have drifted more than 25 miles above one of the world's most remote regions. The floating array is the Antarctic Impulsive Transient Antenna (ANITA) experiment, a project overseen by an international group of researchers tasked with measuring some of the universe's oldest and hardest-to-detect cosmic rays. Specifically, the team is hunting for neutrinos--particles with no charge that also possess the smallest known subatomic mass. But according to their recent report, ANITA has repeatedly picked up some truly weird signals that defy explanation.

Multi-dimensional parameter spaces are commonly encountered in astroparticle physics theories that attempt to capture novel phenomena. However, they often possess complicated posterior geometries that are expensive to traverse using techniques traditional to this community. Effectively sampling these spaces is crucial to bridge the gap between experiment and theory. Several recent innovations, which are only beginning to make their way into this field, have made navigating such complex posteriors possible. These include GPU acceleration, automatic differentiation, and neural-network-guided reparameterization. We apply these advancements to astroparticle physics experimental results in the context of novel neutrino physics and benchmark their performances against traditional nested sampling techniques. Compared to nested sampling alone, we find that these techniques increase performance for both nested sampling and Hamiltonian Monte Carlo, accelerating inference by factors of $\sim 100$ and $\sim 60$, respectively. As nested sampling also evaluates the Bayesian evidence, these advancements can be exploited to improve model comparison performance while retaining compatibility with existing implementations that are widely used in the natural sciences.

Neutrinos can undergo fast flavor conversions (FFCs) within extremely dense astrophysical environments such as core-collapse supernovae (CCSNe) and neutron star mergers (NSMs). In this study, we explore FFCs in a \emph{multi-energy} neutrino gas, revealing that when the FFC growth rate significantly exceeds that of the vacuum Hamiltonian, all neutrinos (regardless of energy) share a common survival probability dictated by the energy-integrated neutrino spectrum. We then employ physics-informed neural networks (PINNs) to predict the asymptotic outcomes of FFCs within such a multi-energy neutrino gas. These predictions are based on the first two moments of neutrino angular distributions for each energy bin, typically available in state-of-the-art CCSN and NSM simulations. Our PINNs achieve errors as low as $\lesssim6\%$ and $\lesssim 18\%$ for predicting the number of neutrinos in the electron channel and the relative absolute error in the neutrino moments, respectively.

In this work we introduce $\nu^2$-Flows, an extension of the $\nu$-Flows method to final states containing multiple neutrinos. The architecture can natively scale for all combinations of object types and multiplicities in the final state for any desired neutrino multiplicities. In $t\bar{t}$ dilepton events, the momenta of both neutrinos and correlations between them are reconstructed more accurately than when using the most popular standard analytical techniques, and solutions are found for all events. Inference time is significantly faster than competing methods, and can be reduced further by evaluating in parallel on graphics processing units. We apply $\nu^2$-Flows to $t\bar{t}$ dilepton events and show that the per-bin uncertainties in unfolded distributions is much closer to the limit of performance set by perfect neutrino reconstruction than standard techniques. For the chosen double differential observables $\nu^2$-Flows results in improved statistical precision for each bin by a factor of 1.5 to 2 in comparison to the Neutrino Weighting method and up to a factor of four in comparison to the Ellipse approach.

Measuring the sum of the three active neutrino masses, $M_\nu$, is one of the most important challenges in modern cosmology. Massive neutrinos imprint characteristic signatures on several cosmological observables in particular on the large-scale structure of the Universe. In order to maximize the information that can be retrieved from galaxy surveys, accurate theoretical predictions in the non-linear regime are needed. Currently, one way to achieve those predictions is by running cosmological numerical simulations. Unfortunately, producing those simulations requires high computational resources -- several hundred to thousand core-hours for each neutrino mass case. In this work, we propose a new method, based on a deep learning network, to quickly generate simulations with massive neutrinos from standard $\Lambda$CDM simulations without neutrinos. We computed multiple relevant statistical measures of deep-learning generated simulations, and conclude that our approach is an accurate alternative to the traditional N-body techniques. In particular the power spectrum is within $\simeq 6\%$ down to non-linear scales $k=0.7$~\rm h/Mpc. Finally, our method allows us to generate massive neutrino simulations 10,000 times faster than the traditional methods.