arXiv subjects

William Sutcliffe

Publications and source records attributed to William Sutcliffe.

6 recordsLinked to original sources

arXiv2026

Joint Treatment Effect Estimation from Incomplete Healthcare Data: Temporal Causal Normalizing Flows with LLM-driven Evolutionary MNAR Imputation

Target trial emulation (TTE) enables causal questions to be studied with observational data when randomized controlled trials (RCTs) are infeasible. Yet treatment-effect methods often address causal estimation, missingness, and temporal structure separately, limiting their robustness in electronic health records (EHRs), where time-varying confounding and missing-not-at-random (MNAR) biomarkers can reach 50%--80%. We propose a two-stage pipeline for treatment effect estimation from incomplete longitudinal EHRs. First, CausalFlow-T, a directed acyclic graph (DAG)-constrained normalizing flow with long short-term memory (LSTM)-encoded patient history, performs exact invertible counterfactual inference, avoiding approximation errors from variational inference and separating confounding through explicit causal structure. Ablations on four synthetic and one semi-synthetic benchmark with known counterfactuals show that DAG constraints and exact inference address distinct failure modes: neither compensates for the other. Second, because CausalFlow-T requires completed inputs, we introduce an LLM-driven evolutionary imputer that proposes executable imputation operators rather than individual entries, and evaluate it with three large language model (LLM) backends, including two open-source models. Across 30%--80% MNAR missingness, this imputer achieves the best pooled rank over biomarker and causal metrics, leading in point-wise accuracy and temporal extrapolation while preserving average treatment effect (ATE) recovery as statistical baselines degrade. On Swiss primary-care EHRs from adults with type 2 diabetes initiating a GLP-1 receptor agonist or SGLT-2 inhibitor, the pipeline estimates a per-protocol weight-loss difference of -0.98 kg [95% CI -1.01, -0.96] favoring GLP-1 receptor agonists, consistent with randomized evidence and obtained from realistically incomplete real-world EHRs.

cs.LG↗

arXiv2025

Leveraging Reinforcement Learning, Genetic Algorithms and Transformers for background determination in particle physics

Experimental studies of beauty hadron decays face significant challenges due to a wide range of backgrounds arising from the numerous possible decay channels with similar final states. For a particular signal decay, the process for ascertaining the most relevant background processes necessitates a detailed analysis of final state particles, potential misidentifications, and kinematic overlaps, which, due to computational limitations, is restricted to the simulation of only the most relevant backgrounds. Moreover, this process typically relies on the physicist's intuition and expertise, as no systematic method exists. This paper has two primary goals. First, from a particle physics perspective, we present a novel approach that utilises Reinforcement Learning (RL) to overcome the aforementioned challenges by systematically determining the critical backgrounds affecting beauty hadron decay measurements. While beauty hadron physics serves as the case study in this work, the proposed strategy is broadly adaptable to other types of particle physics measurements. Second, from a Machine Learning perspective, we introduce a novel algorithm which exploits the synergy between RL and Genetic Algorithms (GAs) for environments with highly sparse rewards and a large trajectory space. This strategy leverages GAs to efficiently explore the trajectory space and identify successful trajectories, which are used to guide the RL agent's training. Our method also incorporates a transformer architecture for the RL agent to handle token sequences representing decays.

cs.LG↗

arXiv2025

Towards replacing detector simulation with heterogeneous GNNs in flavour physics analyses

Driven by the increasing volume of recorded data, the demand for simulation from experiments based at the Large Hadron Collider will rise sharply in the coming years. Addressing this demand solely with existing computationally intensive workflows is not feasible. This paper introduces a new fast simulation tool designed to address this demand at the LHCb experiment. This tool emulates the detector response to arbitrary multibody decay topologies at LHCb. Rather than memorising specific decay channels, the model learns generalisable patterns within the response, allowing it to interpolate to channels not present in the training data. Novel heterogeneous graph neural network architectures are employed that are designed to embed the physical characteristics of the task directly into the network structure. We demonstrate the performance of the tool across a range of decay topologies, showing the networks can correctly model the relationships between complex variables. The architectures and methods presented are generic and could readily be adapted to emulate workflows at other simulation-intensive particle physics experiments.

hep-ex↗

arXiv2025

Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks

The growing luminosity frontier at the Large Hadron Collider is challenging the reconstruction and analysis of particle collision events. Increased particle multiplicities are straining latency and storage requirements at the data acquisition stage, while new complications are emerging, including higher background levels and more frequent particle vertex misassociations. This in turn necessitates the development of more holistic and scalable reconstruction methods that take advantage of recent advances in machine learning. We propose a novel Heterogeneous Graph Neural Network (HGNN) architecture featuring unique representations for diverse particle collision relationships and integrated graph pruning layers for scalability. Trained with a multi-task paradigm in an environment mimicking the LHCb experiment, this HGNN significantly improves beauty hadron reconstruction performance. Notably, it concurrently performs particle vertex association and graph pruning within a single framework. We quantify reconstruction and pruning performance, demonstrate enhanced inference time scaling with event complexity, and mitigate potential performance loss using a weighted message passing scheme.

physics.data-an↗

arXiv2022

Snowmass White Paper: Belle II physics reach and plans for the next decade and beyond

Belle II is an experiment operating at the intensity frontier. Over the next decades, it will record the decay of billions of bottom mesons, charm hadrons, and tau leptons produced in 10 GeV electron-positron collisions at the SuperKEKB high-luminosity collider at KEK. These data, collected in low-background and kinematically known conditions, will allow us to measure hundreds of parameters that test the standard model (SM) and probe for the existence of new particles, at mass scales orders of magnitudes higher than those studied at the energy frontier. We project our sensitivities for measurements that are of primary relevance and where Belle II will be unique or world leading for data corresponding to 1 to 50 ab$^{-1}$. Belle II will uniquely probe non-SM contributions in sensitive $b \to q\bar q s$ decays and charmless $b \to q\bar q d(u)$ decays, semileptonic $b \to s ν\barν$ and $s τ^+ τ^-$ decays, fully leptonic $b \to \ell ν$ decays, and select $c \to u$ processes. Belle II will lead exploration of non-SM physics in $b \to c τν$ and $b \to s γ$ decays and will most precisely determine the quark-mixing parameters $|V_{ub}|$ and $|V_{cb}|$. Belle II will measure many parameters in $τ$ physics to precisions that will be world leading for the foreseeable future, including the electric and magnetic dipole moments, branching fractions for charged-lepton-flavor-violating decays, and quantities that test lepton-flavor universality. Belle II will perform unique searches for dark-sector particles with masses in the MeV-GeV range. We will also pursue a broad spectroscopy program for conventional and multiquark $c \bar c$ and $b \bar b$ states and provide essential inputs to sharpen the interpretation of muon magnetic-anomaly results. Our exploration of uncharted regions of non-SM parameter space with high precision will reveal non-SM particles or set stringent constraints on their existence, guiding future endeavors.

hep-ex↗

arXiv2019

The Full Event Interpretation -- An exclusive tagging algorithm for the Belle II experiment

The Full Event Interpretation is presented: a new exclusive tagging algorithm used by the high-energy physics experiment Belle II. The experimental setup of Belle II allows the precise measurement of otherwise inaccessible $B$ meson decay-modes. The Full Event Interpretation algorithm enables many of these measurements. The algorithm relies on machine learning to automatically identify plausible $B$ meson decay chains based on the data recorded by the detector. Compared to similar algorithms employed by previous experiments, the Full Event Interpretation provides a greater efficiency, yielding a larger effective sample size usable in the measurement.

hep-ex↗