EuCAIFCon 2026

Session

🔀 Inference & Uncertainty

24 Aug 2026, 16:00

HS1

Conveners

🔀 Inference & Uncertainty

• Jonas Spinner (Durham University)

🔀 Inference & Uncertainty

• James Alvey (University of Cambridge)

🔀 Inference & Uncertainty

• Theo Heimel (UCLouvain)

🔀 Inference & Uncertainty

• Humberto Reyes-Gonzalez (RWTH Aachen University)

🔀 Inference & Uncertainty

• Skyler Degenkolb (Universität Heidelberg)

25. Joint spectral and population inference of Galactic pulsars and extragalactic sources in the Fermi-LAT sky with simulation-based inference

Christopher Eckner (Instituto de Astrofísica de Canarias (IAC))

24/08/2026, 16:00

Inference & Uncertainty

Since its mission started more than 17 years ago, the Fermi Large Area Telescope (LAT) has significantly advanced our view of the GeV gamma-ray sky, yet several key questions remain - such as the nature of the isotropic diffuse background, the properties of the Galactic pulsar population, and the origin of the GeV excess towards the Galactic Centre. Addressing these challenges requires...

119. Simulation-Based Inference of Unresolved Neutrino Source Populations in the Galactic Plane

Youyou Li (GRAPPA, University of Amsterdam)

24/08/2026, 16:10

Inference & Uncertainty

The high-energy neutrino emission observed from the Galactic plane by IceCube may contain contributions from both truly diffuse emission produced by cosmic-ray interactions with interstellar gas and a population of individually unresolved hadronic accelerators. Traditional likelihood-based inference is impractical here, since it would require explicit marginalization over the unknown number,...

161. Simulation-Based inference for massive black hole binary from mock LISA data

Gianmarco Puleo (Scuola Internazionale Superiore di Studi Avanzati (SISSA))

24/08/2026, 16:20

Inference & Uncertainty

The Laser Interferometer Space Antenna (LISA) will observe gravitational waves produced by several massive black hole binary (MBHB) mergers per year. While the likelihood can be written in closed form under idealised stationary, Gaussian noise assumptions, including realistic effects — instrumental glitches, gaps in the data, and non-stationary noise — make it intractable or computationally...

102. Multimodal Generative Modelling of the Galaxy Population with pop-cosmos

Sinan Deger (University of Cambridge)

24/08/2026, 16:30

Inference & Uncertainty

Panchromatic surveys such as COSMOS have expanded our understanding of how galaxies evolve through cosmic time immensely. Surveys such as the Vera C. Rubin Observatory's LSST are promising an unprecedented view of this evolutionary paradigm provided the massive data challenge they pose is answered. We have been developing pop-cosmos, a comprehensive galaxy population model housing a...

177. Fast Inferential Diffusion Models for Neural Simulation-based Inference

Stephen Jiggins (DESY)

24/08/2026, 16:50

Inference & Uncertainty

Neural simulation-based inference (NSBI) has emerged as a powerful methodology for unbinned likelihood analyses in high-energy physics (HEP), with recent ATLAS [1] results at the Large Hadron Collider (LHC) demonstrating substantial sensitivity gains over binned methods. The dominant NSBI variant in HEP, Neural Likelihood-Ratio Estimation (NLRE), owes its popularity to the simplicity of the...

60. Two Phase Rapid Simulation Based Inference with Differentiable Simulators

Andre Scaffidi (SISSA)

24/08/2026, 17:00

Simulations & Generative Models

I will introduce introduce Rapid Simulation Based Inference (RSBI), a diffusion-based variational approach to likelihood-free Bayesian inference that achieves high sampling efficiency under large prior-to-posterior volumes with multi-modal posterior structure.
RSBI builds on advances in Schrödinger Bridge diffusion sampling to handle multi-modal posteriors, with the likelihood initially...

130. Probabilistic prediction of kilonova light curves from observed binary neutron star coalescences

Ik Siong Heng (University of Glasgow)

24/08/2026, 17:10

Inference & Uncertainty

Kilonovae are the optical counterparts to gravitational wave signals from binary neutron stars. Combining gravitational wave and kilonova observations provide insight into the equation of state of neutron stars. Kilonova detection is challenging and only a few kilonova candidates have been detected to date, with AT2017gfo being the only one associated with a gravitational wave event GW170817....

134. How to Trust Learned Loop Amplitudes

Henning Bahl

25/08/2026, 11:00

Inference & Uncertainty

Higher-order theory predictions are crucial for the precision LHC program, but the time-consuming amplitude evaluation challenges the corresponding Monte-Carlo simulations. Machine-learned amplitude surrogates can resolve this problem, if we can guarantee their precision over the entire phase space. First, we show that our surrogates provide a calibrated learned uncertainty, even for...

89. Local Conformal Predictions for Calibrated Surrogates

Mr Suprio Dubey (Institute for Theoretical Physics and Mannheim Institute for Intelligent Systems in Medicine, Heidelberg University)

25/08/2026, 11:10

Inference & Uncertainty

Neural network surrogates for LHC scattering amplitudes require trustworthy uncertainty estimates, a challenging task given the non-Gaussian systematics. We target it using conformal prediction, a distribution-free post-processing to complement trained surrogates with calibrated uncertainties. We find that standard conformal predictions struggle to provide locally calibrated uncertainties....

115. Learning to validate generative models

Humberto Reyes-Gonzalez (RWTH Aachen University)

25/08/2026, 11:20

Inference & Uncertainty

Generative models are becoming an integral component of scientific workflows, yet their reliable deployment requires a rigorous understanding of their limitations through statistically robust validation. In particular, high-dimensional settings demand powerful goodness-of-fit tests that provide well-defined statistical interpretations and enable hypothesis testing. In this contribution, we...

34. Forecasting Generative Amplification

Sascha Diefenbacher (ITP Heidelberg)

25/08/2026, 11:30

Inference & Uncertainty

Generative networks are perfect tools to enhance the speed and precision of LHC simulations. It is important to understand their statistical precision, especially when generating events beyond the size of the training dataset. We present two complementary methods to estimate the amplification factor without large holdout datasets. Averaging amplification uses Bayesian networks or ensembling to...

128. Shapes are not enough: CONSERVAttack and its use for finding vulnerabilities and uncertainties in machine learning applications

Timo Saala (University of Bonn (DE))

25/08/2026, 11:50

Inference & Uncertainty

In High Energy Physics, as in many other fields of science, the application of machine learning techniques has been crucial in advancing our understanding of fundamental phenomena. Increasingly, deep learning models are applied to analyze both simulated and experimental data. In most experiments, a rigorous regime of testing for physically motivated systematic uncertainties is in place. The...

40. Variational Positive-Unlabeled Learning with Observational Bias: Uncertainty-Aware Discovery in Incomplete Binary Data

Gabriele Pignalberi (Sapienza Università di Roma and INFN)

25/08/2026, 12:00

Inference & Uncertainty

Many scientific datasets are fundamentally incomplete: only a biased subset of true positives is ever observed, while the remainder stay unlabeled. This Positive-Unlabeled (PU) setting arises whenever detection efficiency is imperfect and covariate-dependent—a structure shared across many fields in fundamental science. In hadron collider experiments, hardware triggers record only a biased...

54. Machine learning method for enforcing variable independence in background estimation with LHC data: ABCDisCoTEC

Cesare Cazzaniga (DESY)

25/08/2026, 12:10

Inference & Uncertainty

Estimating the size and shape of backgrounds is a key part in the vast majority of HEP analyses. The ABCD method provides a reliable way to extract this information directly from the experimental data, thus avoiding reliance on simulation. It relies on the assumption that two, statistically independent variables can be constructed, in order to compute the expected background contribution in...

200. Know What You Don't Flow

Lorenz Vogel (Institute for Theoretical Physics (ITP), Heidelberg University, Germany)

25/08/2026, 12:20

Inference & Uncertainty

Calibrated learned uncertainties are a key requirement also for generative neural networks in LHC physics. For a toy model with an explicit likelihood we show how a heteroscedastic and a Bayesian normalizing flow learn the systematic and statistical uncertainties on the underlying phase space density. Without an explicit likelihood we train the heteroscedastic loss on a classifier-reweighted...

5. NS-UNO: Neutron-Star EoS Inference from an Unconstrained Number of Observations

Valéria Carvalho (Universidade de Coimbra and Nicolaus copernicus astronomical center)

26/08/2026, 14:00

Simulations & Generative Models

Future multimessenger observations of neutron stars (NS) are expected to substantially increase both the number and precision of astrophysical constraints on the equation of state (EoS) of dense matter. This motivates inference frameworks capable of accommodating a variable, non fixed number of observations while preserving the posterior information associated with each measurement.
In this...

58. Generative inference of the neutron-star equation of state

Iuliia Panteleeva

26/08/2026, 14:10

Simulations & Generative Models

Neutron-star observations encode the equation of state of cold, dense matter, but reconstructing it is an ill-posed inverse problem, and standard analyses assume fixed functional forms that restrict and unevenly weight the admissible equations of state. We reconstruct the equation of state with a denoising diffusion model trained on a large synthetic ensemble of sound-speed profiles spanning...

191. Simulation-Based Inference in the Search for the Neutron's Permanent Electric Dipole Moment

Husain Mustansir Manasawala (Universität Heidelberg)

26/08/2026, 14:20

Inference & Uncertainty

Precision tests of fundamental symmetries frequently rely on multi-stage experimental setups where distinct physical mechanisms shape a common observable via an intractable likelihood. Conditional invertible neural networks, trained on high-fidelity forward simulations, learn to reconstruct the full multidimensional posteriors over the parameter space directly from detector-level observables....

20. Neural Simulation-Based Inference for the keV-Scale Sterile Neutrino Search with TRISTAN at KATRIN

Luca Fallböhmer (Max-Planck-Institute for Nuclear Physics)

26/08/2026, 14:30

Simulations & Generative Models

Following the completion of its neutrino mass measurement program at the end of 2025, the KATRIN experiment aims to probe keV-scale sterile neutrinos by analyzing the full tritium beta decay spectrum with a novel detector system, TRISTAN. Leveraging KATRIN’s high source activity, this search is sensitive to mixing amplitudes at the parts-per-million level. However, extracting a potential...

184. Accelerating Cosmological Inference: A Re-usable Library of JAX-based Machine Learning Emulators for Next-Generation Surveys

Dily Duan Yi Ong (University of Cambridge)

26/08/2026, 14:50

Inference & Uncertainty

The era of precision cosmology has revealed persistent tensions between independent measurements of fundamental parameters within the concordance model, most notably the Hubble constant ($H_0$), the clustering amplitude ($\sigma_8$), and spatial curvature ($\Omega_K$). The study of these discrepancies between independent datasets, which are theoretically predicted to agree, is known as tension...

114. Physics-Guided Diffusion Models for Observable Reconstruction from Sparse and Noisy Data

Herzallah Alharazin (Ruhr Universität Bochum)

26/08/2026, 15:00

Inference & Uncertainty

Extracting continuous physical quantities from sparse and noisy data is a ubiquitous inverse problem across theoretical physics. In this talk, I will present a physics-guided generative framework based on denoising diffusion probabilistic models that reformulates function reconstruction as a conditional generation (inpainting) problem. Rather than relying on a prescribed functional ansatz, the...

192. Simulation-Based Inference for Antenna Gain Calibration in 21 cm Cosmology

Joy Sanghavi (UvA)

26/08/2026, 15:10

Inference & Uncertainty

The 21 cm signal from neutral hydrogen is a key probe of the Epoch of Reionization (EoR), marking the universe’s transition from a cold, neutral state to a predominantly hot, ionized one, driven by the formation of the first stars and galaxies. Extracting this faint 21 cm signal from radio interferometric data requires precise gain calibration. However, traditional calibration methods are...

136. Recovering end-to-end SBI performance through probabilistic reconstruction

Vitus Past (Technische Universität München)

26/08/2026, 16:00

Inference & Uncertainty

Simulation-based inference (SBI) has become a key tool for hypothesis testing in high-energy particle physics, enabling likelihood ratio estimation directly from simulated data without requiring tractable likelihoods. In practice, SBI is often applied to high-level variables reconstructed from detector measurements as point estimates, discarding hypothesis-dependent information contained in...

144. Pairton: Iterative Reconstruction of Short-Lived Particles

Andreas Hermansen (Universite de Geneve)

26/08/2026, 16:10

Inference & Uncertainty

In high-energy collider physics, the reconstruction of complicated event topologies, such as fully hadronic $t\bar{t}$ decays, is a difficult challenge for many analyses due to the large combinatorial backgrounds. While previous machine learning methods have advanced this task, they struggle to learn the exact joint distribution, and instead learn various independent marginal approximations....

81. Visible Energy Reconstruction in KM3NeT/ARCA using Graph Neural Networks

Dr Evangelia Drakopoulou (NCSR "Demokritos")

26/08/2026, 16:20

Inference & Uncertainty

Accurate energy reconstruction is a key challenge in neutrino telescopes, where the total neutrino energy is not fully contained in the detector and relying only on the reconstructed muon energy neglects the contribution from hadronic showers. We present a Graph Neural Network (GNN)-based approach for visible energy reconstruction in KM3NeT/ARCA using the DynEdge architecture within the...

57. Estimating Neutrino Oscillation Parameters using Structured hierarchical transformers

Antonin Vacheret (CNRS - LPC Caen)

26/08/2026, 16:30

Inference & Uncertainty

Neutrino oscillations encode fundamental information about neutrino masses and mixing parameters, offering a unique window into physics beyond the Standard Model. Estimating these parameters from oscillation probability maps is, however, computationally challenging due to the maps’ high dimensionality and nonlinear dependence on the underlying physics. Traditional inference methods, such as...

121. Deep Learning for Real-Time Proton CT Reconstruction

Gábor Bíró (HUN-REN Wigner RCP)

26/08/2026, 16:50

Inference & Uncertainty

Proton computed tomography (pCT) promises a direct, low-dose measurement of the relative stopping power (RSP) map that governs proton-therapy dose calculations. In a tracking-based scanner every proton is recorded individually, and reconstructing the RSP image requires estimating the path each proton actually took through the patient. This is intrinsically hard: multiple Coulomb scattering...

185. Kolmogorov-Arnold Networks for Higgs Boson Classification

Mr Said Abolhassan Razavi

26/08/2026, 17:00

Inference & Uncertainty

Gradient-boosted decision trees such as XGBoost remain the default for tabular high-energy-physics (HEP) classification. We investigate Kolmogorov-Arnold Networks (KAN), which replace fixed activations with learnable B-spline functions on network edges, as an alternative for Higgs boson signal/background separation. We implement KAN from scratch in PyTorch (Cox-de Boor B-splines, adaptive knot...

59. Hybrid GNN-Bayesian Models for Uncertainty-Aware Inference of Rare Events on Spatially Embedded Graphs

Federica Di Bartolomeo (Sapienza Università di Roma)

26/08/2026, 17:10

Inference & Uncertainty

We present a hybrid graph-based Bayesian framework for uncertainty-aware inference of rare events on spatially embedded networks.
Starting from a Multivariate Conditional Autoregressive Model (MCAR) in a hierarchical Bayesian architecture defined on the dual graph of a street network, events counts are described by Poisson likelihoods with structured graph effects, unstructured heterogeneity...

166. Unfolding without Iterations, Adversaries, or Surrogates

Ayodele Ore (ITP, Heidelberg University)

27/08/2026, 11:00

Inference & Uncertainty

Correcting measurements for detector effects is a pressing inverse problem in LHC physics. Current methods solve this problem by relying on iterative refinement, minimax optimization, or a surrogate forward mapping. In this talk, I present Adversary-free Unfolding SanS Iteration or Emulation (AUSSIE), which dispenses with these mechanisms while remaining asymptotically correct. AUSSIE unfolds...

126. Data driven hadronization with HOMER

Susie Kim (ITP, Heidelberg University)

27/08/2026, 11:10

Inference & Uncertainty

Due to the non-perturbative nature of hadronization, its simulation relies on a fragmentation function of a fixed parametric form. We present HOMER, a data-driven alternative based on neural networks that extracts the Lund string fragmentation function directly from data. HOMER addresses the information gap between the latent and observable phase spaces through an iterative reweighting...

145. The PAU Survey: Self-supervised image denoising for flux-preserving photometry

Martin Boerstad Eriksen (IFAE-PIC)

27/08/2026, 11:20

Inference & Uncertainty

Deep photometric surveys increasingly rely on low signal-to-noise imaging to detect and characterise faint galaxies, where noise affects source detection, flux measurements, and redshift estimation. Self-supervised denoising methods are attractive because they do not require ground-truth images, but their application to quantitative photometry demands control over systematic flux biases.
We...

21. Constraining the Cosmic Baryon Density from Fast Radio Bursts with a Non-Parametric Reconstruction of the Hubble Parameter

Dr Klecio Lima (Universidade Federal de Campina Grande)

27/08/2026, 11:40

Inference & Uncertainty

Fast radio bursts (FRBs) provide a promising tool to investigate the baryonic content of the Universe through their dispersion measures. In this work, we constrain the baryon density parameter $\Omega_b h^2$ using a sample of 130 localized FRBs combined with a non-parametric reconstruction of the Hubble parameter $H(z)$ obtained from cosmic chronometer data through the ReFANN neural-network...

50. Neural-field reconstruction of Generalized Parton Distributions

Marija Čuić (Irfu, CEA, Université Paris-Saclay/Aidas)

27/08/2026, 11:50

Inference & Uncertainty

Generalized parton distributions (GPDs) encode the three-dimensional partonic structure of the nucleon and are inferred from exclusive scattering experiments such as deeply virtual Compton scattering. The reconstruction is an underdetermined inverse problem: the measurements — Compton form factors — constrain only one region of the underlying distribution, leaving an unmeasured complementary...

91. Towards the new NNPDF4.1 PDF set

Eva Groenendijk (University of Milan and INFN Milan)

27/08/2026, 12:00

Inference & Uncertainty

Parton distribution functions (PDFs) are a key ingredient for precision predictions at particle colliders, describing the dynamics of quarks and gluons inside the proton. Their determination is a challenging inverse problem, where PDFs are extracted from data via a convolution with theoretical predictions. The NNPDF methodology uses a neural network as a flexible parameterisation and a Monte...