Experimental particle physics seeks to understand the universe by probing its fundamental particles and forces and exploring how they govern the large-scale processes that shape cosmic evolution. This whitepaper presents a vision for how Artificial Intelligence (AI) can accelerate discovery in this field. We outline grand challenges that must be addressed to enable transformative breakthroughs and describe how current and planned experimental facilities can implement this vision to advance our understanding of the vast and complex physical world from the smallest to the largest scales. We show how facilities currently under construction, such as the HL-LHC, DUNE and soon EIC, can both benefit from and serve as proving grounds for this vision, while also enabling a longer-term goal for how future experiments – like FCC-ee at CERN, IceCube-Gen2, a Muon Collider in the U.S., and smaller to mid-scale projects – can be fully AI-native. We describe how a truly national-scale collaboration, jointly managed across large funding partners, and involving both DOE laboratories and universities, can make this happen.

One of the forthcoming major challenges in particle physics is the experimental determination of the Higgs trilinear self-coupling. While efforts have largely focused on on-shell double- and single-Higgs production in proton-proton collisions, off-shell Higgs production has also been proposed as a valuable complementary probe. In this article, we design a hybrid neural simulation-based inference (NSBI) approach to construct a likelihood of the Higgs signal incorporating modifications from the Standard Model effective field theory (SMEFT), relevant background processes, and quantum interference effects. It leverages the training efficiency of matrix-element-enhanced techniques, which are vital for robust SMEFT applications, while also incorporating the practical advantages of classification-based methods for effective background estimates. We demonstrate that our NSBI approach achieves sensitivity close to the theoretical optimum and provide expected constraints for the high-luminosity upgrade of the Large Hadron Collider. While we primarily concentrate on the Higgs trilinear self-coupling, we also consider constraints on other SMEFT operators that affect off-shell Higgs production.

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.

Particle physics experiments rely on the (generalised) likelihood ratio test (LRT) for searches and measurements, which consist of composite hypothesis tests. However, this test is not guaranteed to be optimal, as the Neyman–Pearson lemma pertains only to simple hypothesis tests. Any choice of test statistic thus implicitly determines how statistical power varies across the parameter space. An improvement in the core statistical testing methodology for general settings with composite tests would have widespread ramifications across experiments. We discuss an alternate test statistic that provides the data analyzer an ability to focus the power of the test on physics-motivated regions of the parameter space. We demonstrate the improvement from this technique compared to the LRT on a Higgs →ττ dataset simulated by the ATLAS experiment and a dark matter dataset inspired by the LZ experiment. We also employ machine learning to efficiently calibrate critical values for a family of tests, which are then inverted to obtain statistically valid confidence intervals.

The Large Hadron Collider (LHC) is sensitive to signals of beyond the Standard Model physics through a variety of channels including missing energy and resonance searches. In most searches, the new physics and the Standard Model backgrounds are assumed to be invariant in time, up to systematic effects from the experiment. However, new physics with a time variation would provide an additional handle to separate signal from background. Such a time variation may come from ultralight dark matter coupling to an oscillating background field. In this paper, we consider an interaction of dark matter with quarks and an additional heavy particle, and show that the sensitivity of a search that uses timing information at the LHC can be up to a factor of two stronger compared to one that does not use time information.

The measurements performed by particle physics experiments must account for the imperfect response of the detectors used to observe the interactions. One approach, unfolding, statistically adjusts the experimental data for detector effects. Recently, generative machine learning models have shown promise for performing unbinned unfolding in a high number of dimensions. However, all current generative approaches are limited to unfolding a fixed set of observables, making them unable to perform full-event unfolding in the variable dimensional environment of collider data. A novel modification to the variational latent diffusion model (VLD) approach to generative unfolding is presented, which allows for unfolding of high- and variable-dimensional feature spaces. The performance of this method is evaluated in the context of semi-leptonic top quark pair production at the Large Hadron Collider.

This competition in high-energy physics (HEP) and machine learning was the first to strongly emphasise uncertainties in (H → τ^+ τ^-) cross-section measurement. Participants were tasked with developing advanced analysis techniques capable of dealing with uncertainties in the input training data and providing credible confidence intervals. The accuracy of these intervals was evaluated using pseudo-experiments to assess correct coverage. The dataset is now published in Zenodo, and the winning submissions are fully documented.

The HiggsML Uncertainty Challenge is a machine learning competition aimed at improving uncertainty-aware AI techniques in high-energy physics. Part of the FAIR Universe initiative, focuses on estimating the Higgs boson signal strength while accounting for systematic uncertainties affecting collider experiments. Unlike traditional classification tasks, participants must construct confidence intervals that properly cover systematic distortions. The HiggsML Uncertainty Challenge establishes a benchmark for uncertainty-aware AI, with applications in high-energy physics and beyond. The competition is hosted on Codabench, an open AI benchmarking platform, and uses highperformance computing resources at NERSC Perlmutter for scalable and reproducible model evaluation. The dataset and evaluation framework will remain publicly available for continued research.

Recognizing symmetries in data allows for significant boosts in neural network training, which is especially important where training data are limited. In many cases, however, the exact underlying symmetry is present only in an idealized dataset, and is broken in actual data, due to asymmetries in the detector, or varying response resolution as a function of particle momentum. Standard approaches, such as data augmentation or equivariant networks fail to represent the nature of the full, broken symmetry, effectively overconstraining the response of the neural network. We propose a learning model which balances the generality and asymptotic performance of unconstrained networks with the rapid learning of constrained networks. This is achieved through a dual-subnet structure, where one network is constrained by the symmetry and the other is not, along with a learned symmetry factor. In a simplified toy example that demonstrates violation of Lorentz invariance, our model learns as rapidly as symmetry-constrained networks but escapes its performance limitations.

The FAIR Universe – HiggsML Uncertainty Challenge focuses on measuring the physics properties of elementary particles with imperfect simulators due to differences in modelling systematic errors. Additionally, the challenge is leveraging a large-compute-scale AI platform for sharing datasets, training models, and hosting machine learning competitions. Our challenge brings together the physics and machine learning communities to advance our understanding and methodologies in handling systematic (epistemic) uncertainties within AI techniques.

Neutron stars provide a unique opportunity to study strongly interacting matter under extreme density conditions. The intricacies of matter inside neutron stars and their equation of state are not directly visible, but determine bulk properties, such as mass and radius, which affect the star's thermal X-ray emissions. However, the telescope spectra of these emissions are also affected by the stellar distance, hydrogen column, and effective surface temperature, which are not always well-constrained. Uncertainties on these nuisance parameters must be accounted for when making a robust estimation of the equation of state. In this study, we develop a novel methodology that, for the first time, can infer the full posterior distribution of both the equation of state and nuisance parameters directly from telescope observations. This method relies on the use of neural likelihood estimation, in which normalizing flows use samples of simulated telescope data to learn the likelihood of the neutron star spectra as a function of these parameters, coupled with Hamiltonian Monte Carlo methods to efficiently sample from the corresponding posterior distribution. Our approach surpasses the accuracy of previous methods, improves the interpretability of the results by providing access to the full posterior distribution, and naturally scales to a growing number of neutron star observations expected in the coming years.

The simulation of detector response is a vital aspect of data analysis in particle physics, but current Monte Carlo methods are computationally expensive. Machine learning methods, which learn a mapping from incident particle to detector response, are much faster but require a model for every detector element with unique geometry. Complex geometries may require many models, each with their own training samples and hyperparameter tuning tasks. A promising approach is the use of geometry-aware models, which condition the response on the geometry, but current efforts typically require cumbersome full geometry specification. We present a geometry-aware model that takes advantage of the regularity of detector segments, requiring only the definition of cell sizes across regular segments. This model outperforms the current state of the art by over 70 metric.

High-luminosity particle collider experiments such as the ones planned at the High-Luminosity Large Hadron Collider require ever-greater vertexing precision of the tracking detectors, necessitating reductions in the material budget of the detectors. Traditionally, the fractional radiation length (x/X-0) of detectors is either estimated using known properties of the constituent materials, or measured in dedicated runs of the final detector. In this paper, we present a method of direct measurement of the material budget of a CMS prototype module designed for the Phase-2 upgrade of the CMS detector using a 40-65 MeV positron beam. A total of 630 million events were collected at the Paul Scherrer Institut PiE1 experimental area using a three-plane telescope consisting of the prototype module as the central plane, surrounded by two MALTA monolithic pixel detectors. Fractional radiation lengths were extracted from scattering angle distributions using the Highland approximation for multiple scattering. A statistical technique recovered runs suffering from trigger desynchronisation, and several corrections were introduced to compensate for local inefficiencies related to geometric and beam shape constraints. Two regions of the module were surveyed and yielded average x/X-0 values of (0.72 +/- 0.05)% and (0.95 +/- 0.09)%, which are compatible with empirical estimates for these regions computed from known material properties of 0.753% and 0.892%, respectively. Two types of higher-granularity maps of the fractional radiation length were produced, subdivided either into rectangular regions of uniform size, or polygonal-shaped regions of uniform material composition. The results bode well for the CMS Phase-2 upgrade modules, which will play a key role in the minimisation of the material of the upgraded detector.

This report presents a short summary of the activities of the "Standard Model" working group for the "Physics at TeV Colliders" workshop (Les Houches, France, 12-30 June, 2023).

Neutrino-induced charged-current single ${\ensuremath{\pi}}^{+}$ production in the $\mathrm{\ensuremath{\Delta}}(1232)$ resonance region is of considerable interest to accelerator-based neutrino oscillation experiments. In this Letter, high statistic differential cross sections are reported for the semiexclusive reaction ${\ensuremath{\nu}}_{\ensuremath{\mu}}A\ensuremath{\rightarrow}{\ensuremath{\mu}}^{\ensuremath{-}}{\ensuremath{\pi}}^{+}+$ nucleon(s) on scintillator, carbon, water, iron, and lead targets recorded by MINERvA using a wideband ${\ensuremath{\nu}}_{\ensuremath{\mu}}$ beam with $⟨{E}_{\ensuremath{\nu}}⟩\ensuremath{\approx}6\text{ }\text{ }\mathrm{GeV}$. Suppression of the cross section at low ${Q}^{2}$ and enhancement of low ${T}_{\ensuremath{\pi}}$ are observed in both light and heavy nuclear targets compared with phenomenological models used in current neutrino interaction generators. The cross sections per nucleon for iron and lead compared with CH across the kinematic variables probed are 0.8 and 0.5 respectively, a scaling which is also not predicted by current generators.

The Large Hadron Collider at CERN will undergo an upgrade in order to increase its luminosity to 7.5 × 10 34 cm -2 s -1 . The increased luminosity during this High-Luminosity running phase, starting around 2029, means a higher rate of proton-proton interactions, hence a larger ionizing dose and particle fluence for the detectors. The current tracking system of the CMS experiment will be fully replaced in order to cope with the new operating conditions. Prototype planar pixel sensors for the CMS Inner Tracker with square 50 μm × 50 μm and rectangular 100 μm × 25 μm pixels read out by the RD53A chip were characterized in the lab and at the DESY-II testbeam facility in order to identify designs that meet the requirements of CMS during the High-Luminosity running phase. A spatial resolution of approximately 3.4 μm (2 μm) is obtained using the modules with 50 μm × 50 μm (100 μm × 25 μm) pixels at the optimal angle of incidence before irradiation. After irradiation to a 1 MeV neutron equivalent fluence of Φ eq = 5.3 × 10 15 cm -2 , a resolution of 9.4 μm is achieved at a bias voltage of 800 V using a module with 50 μm × 50 μm pixel size. All modules retain a hit efficiency in excess of 99% after irradiation to fluences up to 2.1 × 10 16 cm -2 . Further studies of the electrical properties of the modules, especially crosstalk, are also presented in this paper.

Neutron stars provide a unique laboratory for studying matter at extreme pressures and densities. While there is no direct way to explore their interior structure, X-rays emitted from these stars can indirectly provide clues to the equation of state (EOS) of the superdense nuclear matter through the inference of the star's mass and radius. However, inference of EOS directly from a star's X-ray spectra is extremely challenging and is complicated by systematic uncertainties. The current state of the art is to use simulation-based likelihoods in a piece-wise method which relies on certain theoretical assumptions and simplifications about the uncertainties. It first infers the star's mass and radius to reduce the dimensionality of the problem, and from those quantities infer the EOS. We demonstrate a series of enhancements to the state of the art, in terms of realistic uncertainty quantification and a path towards circumventing the need for theoretical assumptions to infer physical properties with machine learning. We also demonstrate novel inference of the EOS directly from the high-dimensional spectra of observed stars, avoiding the intermediate mass-radius step. Our network is conditioned on the sources of uncertainty of each star, allowing for natural and complete propagation of uncertainties to the EOS.

The interiors of neutron stars reach densities and temperatures beyond the limits of terrestrial experiments, providing vital laboratories for probing nuclear physics. While the star's interior is not directly observable, its pressure and density determine the star's macroscopic structure which affects the spectra observed in telescopes. The relationship between the observations and the internal state is complex and partially intractable, presenting difficulties for inference. Previous work has focused on the regression from stellar spectra of parameters describing the internal state. We demonstrate a calculation of the full likelihood of the internal state parameters given observations, accomplished by replacing intractable elements with machine learning models trained on samples of simulated stars. Our machine-learning-derived likelihood allows us to perform maximum a posteriori estimation of the parameters of interest, as well as full scans. We demonstrate the technique by inferring stellar mass and radius from an individual stellar spectrum, as well as equation of state parameters from a set of spectra. Our results are more precise than pure regression models, reducing the width of the parameter residuals by 11.8% in the most realistic scenario. The neural networks will be released as a tool for fast simulation of neutron star properties and observed spectra.

The Large Hadron Collider (LHC) at CERN will undergo major upgrades to increase the instantaneous luminosity up to 5–7.5×10 34 cm -2 s -1 . This High Luminosity upgrade of the LHC (HL-LHC) will deliver a total of 3000–4000 fb -1 of proton-proton collisions at a center-of-mass energy of 13–14 TeV. To cope with these challenging environmental conditions, the strip tracker of the CMS experiment will be upgraded using modules with two closely-spaced silicon sensors to provide information to include tracking in the Level-1 trigger selection. This paper describes the performance, in a test beam experiment, of the first prototype module based on the final version of the CMS Binary Chip front-end ASIC before and after the module was irradiated with neutrons. Results demonstrate that the prototype module satisfies the requirements, providing efficient tracking information, after being irradiated with a total fluence comparable to the one expected through the lifetime of the experiment.