AI_CDT_DecisionMaking Details Precision measurements of CP violation in b-hadron decays are one of the most powerful indirect probes of physics
beyond the Standard Model (SM). Some decays proceed only through loop ("penguin") diagrams, such as Bs0 → K0 anti-K0 (a b→s transition) and its U-spin partner B0 → K0 anti-K0 (b→d). These are particularly sensitive to New Physics as the new heavy particles can enter the loop and shift CP-violating observables away from their precisely predicted SM values. The U-spin relation between the modes also allows hadronic uncertainties to be controlled. LHCb's Run 3 dataset, collected with an upgraded detector and a fully software trigger, provides the data samples required for a step change in precision. However, unbiased extraction of physics parameters from a time-dependent amplitude analysis of these vector-vector decays is increasingly limited not by statistics but by two problems that machine learning is well suited to. This project will address both. Detector acceptance. The efficiency to reconstruct and select a decay varies non-uniformly across a multi-dimensional phase space. The correlations between these are hard to capture with traditional binned or moment-based parameterisations. The student will develop ML-based models of the acceptance, for example normalising flows and other neural density estimators trained on simulation. These models are continuous and differentiable, and can be embedded directly in the likelihood fit. A central goal is principled uncertainty quantification. The uncertainty of the learned acceptance, from finite simulation and from differences between simulation and data, will be propagated into the final physics parameters rather than treated as an ad hoc systematic. Flavour tagging. A time-dependent CP analysis needs to know whether each meson was produced as a B or an anti-B. Tagging power is currently only a few percent, and any improvement is directly equivalent to more data. The student will build inclusive taggers using modern architectures: graph neural networks and transformers operating on the full set of reconstructed particles in the event. Taggers are trained on simulation but deployed on real data, so a key strand is domain transfer. Domain-adaptation techniques (e.g., adversarial training, distribution matching) and data-driven calibration on control channels will keep the tagger's predicted mistag probabilities accurate and unbiased on data. These components will be validated in the full time-dependent amplitude analysis of Bs0 and B0 → K0 anti-K0, and potentially further U-spin related modes. These are the flagship modes of Prof Kenzie’s research group so the expectation is that the CDT student would join the effort of the group and integrate the findings of their project into a real world scenario. The physics output will be world-leading measurements of CP-violating phases and polarisation-dependent observables in b→s and b→d penguin transitions. The methods themselves are general. Acceptance modelling and flavour tagging underpin essentially all LHCb amplitude and CP-violation analyses, so the tools developed here are expected to be adopted widely across the collaboration. The student will join the Cambridge LHCb group and work within the LHCb collaboration at CERN. They will gain experience of large-scale data, high-performance computing and the rigorous validation standards required for publication in particle physics. Student Desirable Background: Physics background with experience in the use of Machine Learning and programming. By submitting an application for a University of Cambridge project, you consent to your documents being shared with the relevant supervisory team at the partner institution. If you have questions about this process aidecisionscdt@manchester.ac.uk before applying. How to apply: Please apply under the University of Manchester application portal and select 'PhD in Artificial Intelligence' ( OAA Application form ). When applying, you must include the project’s full name, your supervisor’s name, funding status, academic history, and two referees’ contact details. Applications with missing documents will not be processed. Late or incomplete submissions will not be considered, and the university is not responsible for missed deadlines. After you have applied you will be asked to upload the following supporting documents: Final Transcript and certificates of all awarded university level qualifications Interim Transcript of any university level qualifications in progress CV Supporting statement: A mandatory one- to two-page statement explaining your motivation for postgraduate research, why you chose Manchester, relevant academic or work experience, key research findings, and the techniques or skills you've gained. Applications will be put on hold if this is not provided. Contact details for two referees (Please ensure referee email addresses are official university or workplace accounts, as we may need to verify the references.) English Language Certificate (if applicable) Equality, diversity and inclusion is fundamental to the success of The University of Manchester, and is at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. ( Equality, diversity and inclusion | The University of Manchester ) We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status. We also support applications from those returning from a career break or other roles. We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs. Our selection process is free from bias, and we are committed to ensuring fair and equal opportunities for all applicants. We are dedicated to supporting work-life balance and offer flexible working arrangements to accommodate individual needs, including a part-time study option. Join us and help grow the UK’s national capability in artificial intelligence, part of the UK’s modern industrial strategy . Everyone is welcome if you are passionate about uncertainty quantification, decision making with humans in the loop and decision making for machine learning systems and their applications in Science and Engineering, and looking to develop your research and innovation skills at the doctoral level to further your career in the AI sector. Funding Notes The UKRI AI CDT in Decision Making for Complex Systems is part of the TechFirst offering stipends of £30,000 for students eligible for home fee status. The start date is September 2027. The Project will be based in University of Cambridge. References The LHCb experiment at CERN: https://lhcb.web.cern.ch . Previous related work of Kenzie’s group: Inclusive Flavour Tagging at LHCb: https://link.springer.com/article/10.1007/JHEP11(2025)041 Run1 Time-Dependent measurement: https://link.springer.com/article/10.1007/JHEP03(2018)140 Run1 + Run2 Time-Integrated measurement: https://journals.aps.org/prd/abstract/10.1103/cd57-xr8f


