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.

MadMiner is a Python package that implements a powerful family of multivariate inference techniques that leverage matrix element information and machine learning. This multivariate approach neither requires the reduction of high-dimensional data to summary statistics nor any simplifications to the underlying physics or detector response. In this paper, we address some of the challenges arising from deploying MadMiner in a real-scale HEP analysis with the goal of offering a new tool in HEP that is easily accessible. The proposed approach encapsulates a typical MadMiner pipeline into a parametrized yadage workflow described in YAML files. The general workflow is split into two yadage sub-workflows, one dealing with the physics simulations and the other with the ML inference. After that, the workflow is deployed using REANA, a reproducible research data analysis platform that takes care of flexibility, scalability, reusability, and reproducibility features. To test the performance of our method, we performed scaling experiments for a MadMiner workflow on the National Energy Research Scientific Computer (NERSC) cluster with an HT-Condor back-end. All the stages of the physics sub-workflow had a linear dependency between resources or wall time and the number of events generated. This trend has allowed us to run a typical MadMiner workflow, consisting of 11M events, in 5 hours compared to days in the original study.

We study the use of transformers to reconstruct the compositions of tensor products of two-dimensional rational conformal field theories (RCFTs) based on their low-energy spectra. The task is challenging due to its combinatorial nature. The constituent theories are characterized by their central charges and affine Lie algebra labels. We achieve 98

Accurate assessment of systematic uncertainties is an increasingly vital task in physics studies, where large, high-dimensional datasets, like those collected at the Large Hadron Collider, hold the key to new discoveries. Common approaches to assessing systematic uncertainties rely on simplifications, such as assuming that the impact of the various sources of uncertainty factorizes. In this paper, we provide realistic example scenarios in which this assumption fails. We introduce an algorithm that uses Gaussian process (GP) regression to estimate the impact of systematic uncertainties without assuming factorization. The GP models are enhanced with derivative information, which increases the accuracy of the regression without increasing the number of samples. We also present a novel sampling strategy based on Bayesian experimental design, which is shown to be more efficient than random and grid sampling in our example scenarios. We apply this approach to the estimation of the efficiency as a function of 2 and 4 jet energy scale parameters, demonstrating significant improvements over a more traditional approach that assumes factorization: the mean squared errors are reduced by factors of 80–120 in the 2D case, and 6–13 in the 4D case.

We extend the re-simulation-based self-supervised learning approach to learning representations of hadronic jets in colliders by exploiting the Markov property of the standard simulation chain. Instead of masking, cropping, or other forms of data augmentation, this approach simulates pairs of events where the initial portion of the simulation is shared, but the subsequent stages of the simulation evolve independently. When paired with a contrastive loss function, this naturally leads to representations that capture the physics in the initial stages of the simulation. In particular, we force the hard scattering and parton shower to be shared and let the hadronization and interaction with the detector evolve independently. We then evaluate the utility of these representations on downstream tasks.

The IRIS-HEP software institute, as a contributor to the broader HEP Python ecosystem, is developing scalable analysis infrastructure and software tools to address the upcoming HL-LHC computing challenges with new approaches and paradigms, driven by our vision of what HL-LHC analysis will require. The institute uses a "Grand Challenge" format, constructing a series of increasingly large, complex, and realistic exercises to show the vision of HL-LHC analysis. Recently, the focus has been demonstrating the IRIS-HEP analysis infrastructure at scale and evaluating technology readiness for production. As a part of the Analysis Grand Challenge activities, the institute executed a "200 Gbps Challenge", aiming to show sustained data rates into the event processing of multiple analysis pipelines. The challenge integrated teams internal and external to the institute, including operations and facilities, analysis software tools, innovative data delivery and management services, and scalable analysis infrastructure. The challenge showcases the prototypes - including software, services, and facilities - built to process around 200 TB of data in both the CMS NanoAOD and ATLAS PHYSLITE data formats with test pipelines. The teams were able to sustain the 200 Gbps target across multiple pipelines. The pipelines focusing on event rate were able to process at over 30 MHz. These target rates are demanding; the activity revealed considerations for future testing at this scale and changes necessary for physicists to work at this scale in the future. The 200 Gbps Challenge has established a baseline on today's facilities, setting the stage for the next exercise at twice the scale.

We consider a generalization of the classifier-based density-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative. The problem with most loss functions used for this task is that they implicitly define a relationship between the optimal classifier and the target quasiprobabilistic density ratio which is discontinuous or not surjective. We address these problems by introducing a convex loss function that is well-suited for both probabilistic and quasiprobabilistic density ratio estimation. To quantify performance, an extended version of the Sliced-Wasserstein distance is introduced which is compatible with quasiprobability distributions. We demonstrate our approach on a real-world example from particle physics, of di-Higgs production in association with jets via gluon-gluon fusion, and achieve state-of-the-art results.

We introduce a framework for generating highly multimodal datasets with explicitly calculable mutual information between modalities. This enables the construction of benchmark datasets that provide a novel testbed for systematic studies of mutual information estimators and multimodal self-supervised learning techniques. Our framework constructs realistic datasets with known mutual information using a flow-based generative model and a structured causal framework for generating correlated latent variables.

Motivated by real-world situations found in high energy particle physics, we consider a generalization of the likelihood-ratio estimation task to a quasiprobabilistic setting where probability densities can be negative, and to importance sampling where the importance weights can be negative. The presence of negative densities and negative weights, pose an array of challenges to traditional neural likelihood ratio (LR) estimation methods. We address these challenges by introducing a novel loss function. In addition, we introduce a new model architecture based on the decomposition of a LR using signed mixture models, providing a second strategy for overcoming these challenges. Finally, we demonstrate our approach on a pedagogical example and a real-world example from particle physics.

The planar three-gluon form factor for the chiral stress tensor operator in planar maximally supersymmetric Yang-Mills theory is an analog of the Higgs-to-three-gluon scattering amplitude in QCD. The amplitude (symbol) bootstrap program has provided a wealth of high-loop perturbative data about this form factor, with results up to eight loops available. The symbol of the form factor at L loops is given by words of length 2L in six letters with associated integer coefficients. In this paper, we analyze this data, describing patterns of zero coefficients and relations between coefficients. We find many sequences of words whose coefficients are given by closed-form expressions which we expect to be valid at any loop order. Moreover, motivated by our previous machine-learning analysis, we identify simple recursion relations that relate the coefficient of a word to the coefficients of particular lower-loop words. These results open an exciting door for understanding scattering amplitudes at all loop orders.

Anomaly, or out-of-distribution, detection is a promising tool for aiding discoveries of new particles or processes in particle physics. In this work, we identify and address two overlooked opportunities to improve anomaly detection for high-energy physics. First, rather than train a generative model on the single most dominant background process, we build detection algorithms using representation learning from multiple background types, thus taking advantage of more information to improve estimation of what is relevant for detection. Second, we generalize decorrelation to the multi-background setting, thus directly enforcing a more complete definition of robustness for anomaly detection. We demonstrate the benefit of the proposed robust multi-background anomaly detection algorithms on a high-dimensional dataset of particle decays at the Large Hadron Collider.

The Review summarizes much of particle physics and cosmology. Using data from previous editions, plus 2,717 new measurements from 869 papers, we list, evaluate, and average measured properties of gauge bosons and the recently discovered Higgs boson, leptons, quarks, mesons, and baryons. We summarize searches for hypothetical particles such as supersymmetric particles, heavy bosons, axions, dark photons, etc. Particle properties and search limits are listed in Summary Tables. We give numerous tables, figures, formulae, and reviews of topics such as Higgs Boson Physics, Supersymmetry, Grand Unified Theories, Neutrino Mixing, Dark Energy, Dark Matter, Cosmology, Particle Detectors, Colliders, Probability and Statistics. Most of the 120 reviews are updated, including many that are heavily revised. The Review is divided into two volumes. Volume 1 includes the Summary Tables and 97 review articles. Volume 2 consists of the Particle Listings and contains also 23 reviews that address specific aspects of the data presented in the Listings. The complete Review (both volumes) is published online on the website of the Particle Data Group (pdg.lbl.gov) and in a journal. Volume 1 is available in print as the PDG Book. A Particle Physics Booklet with the Summary Tables and essential tables, figures, and equations from selected review articles is available in print, as a web version optimized for use on phones, and as an Android app.

Searches for new physics set exclusion limits in parameter spaces of typically up to 2 dimensions. However, the relevant theory parameter space is usually of a higher dimension but only a subspace is covered due to the computing time requirements of signal process simulations. An Active Learning approach is presented to address this limitation. Compared to the usual grid sampling, it reduces the number of parameter space points for which exclusion limits need to be determined. Hence it allows to extend interpretations of searches to higher dimensional parameter spaces and therefore to raise their value, e.g. via the identification of barely excluded subspaces which motivate dedicated new searches. In an iterative procedure, a Gaussian Process is fit to excluded signal cross-sections. Within the region close to the exclusion contour predicted by the Gaussian Process, Poisson disc sampling is used to determine further parameter space points for which the cross-section limits are determined. The procedure is aided by a warm-start phase based on computationally inexpensive, approximate limit estimates such as total signal cross-sections. The procedure is applied to a dark matter search on data collected by the ATLAS detector at the LHC, extending its interpretation from a 2 to a 4-dimensional parameter space while keeping the computational effort at a low level. The result is published in two formats: on one hand there is a publication of the Gaussian Process model. On the other hand, a visualization of the full 4-dimensional contour is presented as a collection of 2-dimensional exclusion contours where the 2 remaining parameters are chosen by the user.

The LPC EFT workshop was held April 25-26, 2024 at the University of Notre Dame. The workshop was organized into five thematic sessions: "how far beyond linear" discusses issues of truncation and validity in interpretation of results with an eye towards practicality; "reconstruction-level results" visits the question of how best to design analyses directly targeting inference of EFT parameters; "logistics of combining likelihoods" addresses the challenges of bringing a diverse array of measurements into a cohesive whole; "unfolded results" tackles the question of designing fiducial measurements for later use in EFT interpretations, and the benefits and limitations of unfolding; and "building a sample library" addresses how best to generate simulation samples for use in data analysis. This document serves as a summary of presentations, subsequent discussions, and actionable items identified over the course of the workshop.

We pursue the use of deep learning methods to improve state-of-the-art computations in theoretical high-energy physics. Planar N = 4 Super Yang-Mills theory is a close cousin to the theory that describes Higgs boson production at the Large Hadron Collider; its scattering amplitudes are large mathematical expressions containing integer coefficients. In this paper, we apply Transformers to predict these coefficients. The problem can be formulated in a language-like representation amenable to standard cross-entropy training objectives. We design two related experiments and show that the model achieves high accuracy (> 98%) on both tasks. Our work shows that Transformers can be applied successfully to problems in theoretical physics that require exact solutions.

Recent applications of machine-learned normalizing flows to sampling in lattice field theory suggest that such methods may be able to mitigate critical slowing down and topological freezing. However, these demonstrations have been at the scale of toy models, and it remains to be determined whether they can be applied to state-of-the-art lattice quantum chromodynamics calculations. Assessing the viability of sampling algorithms for lattice field theory at scale has traditionally been accomplished using simple cost scaling laws, but as we discuss in this work, their utility is limited for flow-based approaches. We conclude that flow-based approaches to sampling are better thought of as a broad family of algorithms with different scaling properties, and that scalability must be assessed experimentally.

Sampling from known probability distributions is a ubiquitous task in computational science, underlying calculations in domains from linguistics to biology and physics. Generative machine-learning (ML) models have emerged as a promising tool in this space, building on the success of this approach in applications such as image, text and audio generation. Often, however, generative tasks in scientific domains have unique structures and features — such as complex symmetries and the requirement of exactness guarantees — that present both challenges and opportunities for ML. This Perspective outlines the advances in ML-based sampling motivated by lattice quantum field theory, in particular for the theory of quantum chromodynamics. Enabling calculations of the structure and interactions of matter from our most fundamental understanding of particle physics, lattice quantum chromodynamics is one of the main consumers of open-science supercomputing worldwide. The design of ML algorithms for this application faces profound challenges, including the necessity of scaling custom ML architectures to the largest supercomputers, but also promises immense benefits, and is spurring a wave of development in ML-based sampling more broadly. In lattice field theory, if this approach can realize its early promise it will be a transformative step towards first-principles physics calculations in particle, nuclear and condensed matter physics that are intractable with traditional approaches.

Machine learning methods based on normalizing flows have been shown to address important challenges, such as critical slowing-down and topological freezing, in the sampling of gauge field configurations in simple lattice field theories. A critical question is whether this success will translate to studies of QCD. This Proceedings presents a status update on advances in this area. In particular, it is illustrated how recently developed algorithmic components may be combined to construct flow-based sampling algorithms for QCD in four dimensions. The prospects and challenges for future use of this approach in at-scale applications are summarized.

First-principle simulations are at the heart of the high-energy physics research program. They link the vast data output of multi-purpose detectors with fundamental theory predictions and interpretation. This review illustrates a wide range of applications of modern machine learning to event generation and simulation-based inference, including conceptional developments driven by the specific requirements of particle physics. New ideas and tools developed at the interface of particle physics and machine learning will improve the speed and precision of forward simulations, handle the complexity of collision data, and enhance inference as an inverse simulation problem.