SEARCH · Engineering Papers

Results for “Partially explicit”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2

All sources NASA NTRS DOE OSTI

DOE OSTI2025

Explicit block encodings of boundary value problems for many-body elliptic operators

Simulation of physical systems is one of the most promising use cases of future digital quantum computers. In this work we systematically analyze the quantum circuit complexities of block encoding the discretized elliptic operators that arise extensively in numerical simulations for partial differential equations, including high-dimensional instances for many-body simulations. When restricted to rectangular domains with separable boundary conditions, we provide explicit circuits to block encode the many-body Laplacian with separable periodic, Dirichlet, Neumann, and Robin boundary conditions, using standard discretization techniques from low-order finite difference methods. To obtain high-precision, we introduce a scheme based on periodic extensions to solve Dirichlet and Neumann boundary value problems using a high-order finite difference method, with only a constant increase in total circuit depth and subnormalization factor. We then present a scheme to implement block encodings of differential operators acting on more arbitrary domains, inspired by Cartesian immersed boundary methods. We then block encode the many-body convective operator, which describes interacting particles experiencing a force generated by a pair-wise potential given as an inverse power law of the interparticle distance. This work provides concrete recipes that are readily translated into quantum circuits, with depth logarithmic in the total Hilbert space dimension, that block encode operators arising broadly in applications involving the quantum simulation of quantum and classical many-body mechanics.

Kharazi, Tyler [University of California, Berkeley↗

DOE OSTI2024

Fast permeability measurement for tight reservoir cores using only initial data of the one chamber pressure pulse decay test

Here, in this study, a mathematical model for fast determination of the permeabilities of tight rocks using measurements taken from the initial period of the One Chamber Pressure Pulse Decay (OC-PPD) test is presented. The model applies to measurements taken both before and after the pressure pulse front has reached the downstream end of the specimen. The analytical solutions for the pressure decay in the upstream chamber are derived based on a parabolic arc approximation of pore pressure distribution along the test specimen. This approximation allows converting the initial–boundary value problem of fluid diffusion in the specimen, governed by partial differential equations, to a system of ordinary differential equations that can be easily solved by explicit formulae. Thus, an explicit formula for the pressure decay rate is obtained, which enables inverse analysis of the initial experimental data to estimate the rock permeability. The proposed method expedites the pulse decay test as it does not require the system to reach equilibrium. The method is validated with three sets of experimental data of the OC-PPD test using helium as the diffusing fluid, for which the relative error of the permeability is found to be less than 6%. This method is particularly useful if the equilibrium time of the pulse decay test for rock specimens with permeabilities in the range of nano-Darcy takes hours or days.

early-time solution↗

DOE OSTI2024

Multiscale modeling of HBV infection integrating intra- and intercellular viral propagation to analyze extracellular viral markers

Chronic infection with hepatitis B virus (HBV) is caused by the persistence of closed circular DNA (cccDNA) in the nucleus of infected hepatocytes. Despite available therapeutic anti-HBV agents, eliminating the cccDNA remains challenging. Thus, quantifying and understanding the dynamics of cccDNA are essential for developing effective treatment strategies and new drugs. However, such study requires repeated liver biopsy to measure the intrahepatic cccDNA, which is basically not accepted because liver biopsy is potentially morbid and not common during hepatitis B treatment. We here aimed to develop a noninvasive method for quantifying cccDNA in the liver using surrogate markers in peripheral blood. We constructed a multiscale mathematical model that explicitly incorporates both intracellular and intercellular HBV infection processes. The model, based on age-structured partial differential equations, integrates experimental data from in vitro and in vivo investigations. By applying this model, we roughly predicted the amount and dynamics of intrahepatic cccDNA within a certain range using specific viral markers in serum samples, including HBV DNA, HBsAg, HBeAg, and HBcrAg. Our study represents a significant step towards advancing the understanding of chronic HBV infection. The noninvasive quantification of cccDNA using our proposed method holds promise for improving clinical analyses and treatment strategies. By comprehensively describing the interactions of all components involved in HBV infection, our multiscale mathematical model provides a valuable framework for further research and the development of targeted interventions.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2025

Surrogate modeling of Cellular-Potts agent-based models as a segmentation task using the U-Net neural network architecture

The Cellular-Potts model is a powerful and ubiquitous framework for developing computational models for simulating complex multicellular biological systems. Cellular-Potts models (CPMs) are often computationally expensive due to the explicit modeling of interactions among large numbers of individual model agents and diffusive fields described by partial differential equations (PDEs). In this work, we develop a convolutional neural network (CNN) surrogate model using a U-Net architecture that accounts for periodic boundary conditions. We use this model to accelerate the evaluation of a mechanistic CPM previously used to investigate in vitro vasculogenesis. The surrogate model was trained to predict 100 computational steps ahead (Monte-Carlo steps, MCS), accelerating simulation evaluations by a factor of 562 times compared to single-core CPM code execution on CPU. Over short timescales of up to 3 recursive evaluations, or 300 MCS, our model captures the emergent behaviors demonstrated by the original Cellular-Potts model such as vessel sprouting, extension and anastomosis, and contraction of vascular lacunae. This approach demonstrates the potential for deep learning to serve as a step toward efficient surrogate models for CPM simulations, enabling faster evaluation of computationally expensive CPM simulations of biological processes.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

A Primer on Nuclear "Recoil" Data

For many years the ENDF-6 format has existed to contain evaluated nuclear data. One primary driver for the format and the data is neutron transport calculations. Evaluated data can be processed by a code like NJOY into either continuous energy form (ACE format) for Monte Carlo codes like MCNP or into multi-group form (NDI tables) for deterministic codes like Partisn. The reaction cross sections are found in the MF 3 section of the ENDF-6 format. If the reaction produces one or more neutrons as outputs, then secondary neutron data must also be given in MF 4,5 or 6 sections of the format. Energy and angular distributions for the output neutrons must be given in one of several available formats. The most general formats are found in MF 6. MF 4 is for angular distributions, MF 5 is for Energy distributions, and MF 6 contains both. In recent years, more interest has developed in the other output particles (i.e., the “recoil” particles) from neutron induced reactions. This has been driven by interest in charged particle transport and in more specialized partial kermas. ( A separate total neutron kerma has been available for a long time.) Partial kermas are a breakdown of the Kinetic Energy Released into the MAterial by output particle or by neutron reaction. The sum of the partial kermas should be equal to the total kerma on a group-wise basis. The ENDF-6 format is general enough for these new data requirements. Ideally, evaluated data would exist for every output particle (including the secondary neutrons) from every neutron-induced reaction. In the MF 6 format section, data for multi-particle outputs may be entered using the LAW =1 option. This option explicitly allows energy and angular output distributions for each particle produced in the reaction. Such information should preserve the balance between partial kermas and the total kerma at the groupwise level as well as the individual particle averaged energies. For simpler 2-body reactions, LAW = 2 is available. This allows the evaluation to specify only enough data to specify the 2-body reaction fully. Such a simplification does not exist for 3 (or more) body breakups. A simplified form of LAW 2, i.e., LAW 3, also exists to generate approximate recoil output distributions in the absence of full data. However, evaluated data does not generally exist at this fine granularity for reactions involving more than 2 output particles ( e.g., the 3-body break-up reaction). When the multi-body detailed output distribution data is not available, LAW=6 may be employed in NJOY. LAW 6 produces approximate output distributions for all the particles produced in the reaction. Just like in the 2-body case, the smaller particles will generally carry off more energy. At any particular energy, the balance between the sum of the partial kermas and the total kerma will not necessarily be preserved. However, the average energy of each output particle from a reaction is preserved.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2026

Integrated machine learning-molecular dynamics framework for electrolyte property prediction

Electrochemical stability windows determine the operating range of battery electrolytes, yet accurate prediction remains challenging because stability emerges from statistical ensembles of local solvation environments rather than single ground-state molecular structures. Traditional density functional theory calculations on energy-minimized clusters cannot capture the thermal variations in local coordination environments and geometries that govern decomposition, while SMILES-based machine learning methods lack explicit representation of three-dimensional solvation structure and ion pairing. Here, we introduce a structure-aware machine learning framework that predicts frontier orbital energies (HOMO and LUMO) directly from molecular dynamics-sampled solvation configurations, achieving sub-0.6 eV accuracy at computational costs 3–4 orders of magnitude lower than first-principles methods. Across twelve representative battery electrolytes, we demonstrate that solvent-separated and contact ion pairs exhibit strong size- and local chemistry dependent electronic stability, with variations in coordination shifts of HOMO or LUMO level by 2–3 eV, and that extended solvation structure and partially desolvated environment further modulate stability by up to 3 eV. By encoding the statistical nature of electrochemical failure through ensemble sampling of explicit solvation geometries, our approach enables high-throughput screening and rational design of next-generation battery electrolytes with mechanistic understanding of structure–property relationships.

Energy - Storage↗

DOE OSTI2022

Gluon-mediated inclusive Deep Inelastic Scattering from Regge to Bjorken kinematics

We revisit high energy factorization for gluon mediated inclusive Deep Inelastic Scattering (DIS) for which we propose a new semi-classical approach that accounts systematically for the longitudinal extent of the target in contrast with the shockwave limit. In this framework, based on a partial twist expansion, we derive a factorization formula that involves a new gauge invariant unintegrated gluon distribution which depends explicitly on the Feynman x variable. It is shown that both the Regge and Bjorken limits are recovered in this approach. We reproduce in particular the full one loop inclusive DIS cross-section in the leading twist approximation and the all-twist dipole factorization formula in the strict x = 0 limit. Although quantum evolution is not discussed explicitly in this work, we argue that the proper treatment of the x dependence of the gluon distribution encompasses the kinematic constraint that must be imposed on the phase-space of gluon fluctuations in the target to ensure stability of small-x evolution.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2023

A Coverage Self-Consistent Microkinetic Model for Vapor-Phase Formic Acid Decomposition over Pd/C Catalysts

An iterative approach utilizing density functional theory (DFT, PW91-GGA)-informed mean-field microkinetic models and reaction kinetics experiments is used to determine the reaction mechanism and the active site for formic acid (HCOOH, FA) decomposition over a Pd/C catalyst. Models parametrized using DFT energetics on clean Pd(100) and Pd(111) required large corrections to the DFT energetics for capturing our experimental data. Further, both Pd(111) and Pd(100) models predicted a high coverage of adsorbed CO (CO*), inconsistent with the assumption of a clean surface at which the rate parameters for these models were calculated. To better represent the active site under reaction conditions and explicitly account for the presence of CO*, subsequent microkinetic models were formulated using DFT energetics that were calculated on partially (5/9 ML) CO*-covered Pd (111) and (100) facets. Upon parameter adjustment, the resultant 5/9 ML CO*-covered Pd(100) model, although consistent in terms of CO* coverage, was unable to capture the dehydration path measured in the experiments and was, therefore, deemed not to offer an accurate representation of the active site for FA decomposition over Pd/C. In contrast, a partially CO*-covered Pd(111) model was better at representing the catalytic active site, as in addition to being consistent in terms of CO* coverages, it required small adjustments of the DFT parameters to accurately capture the experimental data set (both dehydrogenation and dehydration). Our results suggest that the reaction occurs via the spectroscopically elusive carboxyl (COOH*) intermediate and that spectator CO*-assisted decomposition pathways play an important role under typical experimental conditions. In addition, our study highlights the importance of striving for coverage self-consistent microkinetic models and for including spectator-assisted mechanisms in order to develop an improved picture of the active site under reaction conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

An improved framework for the dynamic likelihood filtering approach to data assimilation

Here, we propose improvements to the Dynamic Likelihood Filter (DLF), a Bayesian data assimilation filtering approach, specifically tailored to wave problems. The DLF approach was developed to address the common challenge in the application of data assimilation to hyperbolic problems in the geosciences and in engineering, where observation systems are sparse in space and time. When these observations have low uncertainties, as compared to model uncertainties, the DLF exploits the inherent nature of information and uncertainties to propagate along characteristics to produce estimates that are phase aware as well as amplitude aware, as would be the case in the traditional data assimilation approach. Along characteristics, the stochastic partial differential equations underlying the linear or nonlinear stochastic dynamics are differential equations. This study focuses on developing the explicit challenges of relating dynamics and uncertainties in the Eulerian and Lagrangian frames via dynamic Gaussian processes. It also implements the approach using the ensemble Kalman filter (EnKF) and compares the DLF approach to the conventional one with respect to wave amplitude and phase estimates in linear and nonlinear wave problems. Numerical comparisons show that the DLF/EnKF outperforms the EnKF estimates, when applied to linear and nonlinear wave problems. This advantage is particularly noticeable when sparse, low uncertainty observations are used.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Stability-preserving Lossy Compression for Large-scale Partial Differential Equations

Checkpoint/Restart (C/R) strategies are vital for fault tolerance in PDE-based scientific simulations, yet traditional checkpointing incurs significant I/O overhead. Lossy compression offers a scalable solution by reducing checkpoint data size, but conventional methods often lack control over physical invariants (e.g., energy), leading to instability such as oscillations or divergence in Partial Differential Equations (PDE) systems. This paper introduces a stability-preserving compression approach tailored for PDE simulations by explicitly controlling kinetic and potential energy perturbations to ensure stable restarts. Extensive experiments conducted across diverse PDE configurations demonstrate that our method maintains numerical stability with minimal error magnification—even across multiple checkpoint-restart cycles—outperforming state-of-the-art lossy compressors. Parallel evaluations on the Frontier supercomputer show up to 8.4× improvement in checkpoint write performance and 6.3× in read performance, while maintaining relative L2 errors ∼ 2e-6 throughout continued simulation. These results provide practical guidance for balancing compression accuracy, stability, and computational efficiency in large-scale PDE applications.

Gong, Qian [ORNL] (ORCID:0000000235704142)↗

DOE OSTI2025

A New Framework for the Attribution of Air‐Sea CO 2 Exchange

Abstract The air‐sea transfer of carbon dioxide can be viewed as a dynamic system through which atmospheric and oceanic processes push surface waters away from thermodynamic equilibrium, while diffusive gas transfer pulls them back toward local equilibrium. These push/pull processes drive significant sub‐seasonal, seasonal, and interannual variability in air‐sea carbon fluxes, the quantification of which is critical both for diagnosing the ocean response to fossil fuel emissions and for attempts to mitigate anthropogenic climate disruption through intentional modification of surface ocean biogeochemistry. In this study, we present a new approach for attributing air‐sea carbon fluxes to specific mechanisms. The new framework is first applied to a two‐box ocean nutrient and carbon cycle model as an illustrative example. Next, outputs from a regional eddy‐resolving model of the Southern Ocean are analyzed. The roles of multiple physical and biogeochemical processes are identified. The decomposition of the seasonal air‐sea carbon flux shows the dominant role of biological carbon pumps that are partially compensated by the transport convergence. Finally, the framework is used to diagnose the response to mesoscale iron and alkalinity release, explicitly quantifying transport feedback and eventual impacts on net air‐sea carbon flux. Ocean carbon transport has divergent influences between iron and alkalinity release, due to opposing near‐surface gradients of dissolved inorganic carbon. We suggest that our attribution framework may be a useful analytical technique for monitoring natural ocean carbon fluxes and quantifying the impacts of human intervention on the ocean carbon cycle.

Ito, Takamitsu [School of Earth and Atmospheric Sc↗

DOE OSTI2025

Characterization of admissible quasisymmetries

We solve ‘half’ the problem of finding three-dimensional quasisymmetric magnetic fields that do not necessarily satisfy magnetohydrostatic force balance. This involves determining which hidden symmetries are admissible as quasisymmetries, and then showing explicitly how to construct quasisymmetric magnetic fields given an admissible symmetry. The admissibility conditions take the form of a system of overdetermined nonlinear partial differential equations involving second derivatives of the symmetry's infinitesimal generator.

Burby, J. W. (ORCID:0000000317727647)↗

DOE OSTI2024

Using Machine Learning to Predict Cloud Turbulent Entrainment–Mixing Processes

Different turbulent entrainment–mixing mechanisms between clouds and environment are essential to cloud–related processes; however, accurate representation of entrainment–mixing in weather/climate models still poses a challenge. This study exploits the use of machine learning (ML) to address this challenge. Four ML (Light Gradient Boosting Machine [LGB], eXtreme Gradient Boosting, Random Forest, and Support Vector Regression) are examined and compared. It is found that LGB performs best, and thus is selected to understand the impact of entrainment–mixing on microphysics using simulation data from Explicit Mixing Parcel Model. Compared with traditional parameterizations, the trained LGB provides more accurate microphysical properties (number concentration and cloud droplet spectral dispersion). The partial dependences of predicted microphysics on features exhibit a strong alignment with physical mechanisms and expectations, as determined by the interpreting method, thus overcoming the limitations of the “black box” scheme. The underlying mechanisms are that the smaller number concentration and larger spectral dispersion correspond to more inhomogeneous entrainment–mixing. Specifically, number concentration after entrainment–mixing is positively correlated with adiabatic number concentration and liquid water content affected by entrainment–mixing, and inversely correlated with adiabatic volume mean radius. Spectral dispersion after entrainment–mixing is negatively correlated with liquid water content affected by entrainment–mixing, turbulent dissipation rate and relative humidity of entrained air. Sensitivity analysis further suggests that number concentration is mainly determined by cloud microphysical properties whereas spectral dispersion is influenced by both cloud microphysical properties and environmental variables. The results indicate that the LGB scheme has the potential to enhance the representation of entrainment–mixing in weather/climate models.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2022

Time-explicit Darwin PIC algorithm

A new approach to Darwin particle-in-cell plasma simulation is described. Using a finite-element approach, the vector potential is assured to be exactly solenoidal. This allows writing the system of multi-species particles as an action-at-a-distance Hamiltonian system. Applying recently-developed explicit symplectic methods to this gives a time-explicit algorithm with all desired properties. Elliptic systems for the electrostatic and magneto-static portions of the problem are inverted efficiently by an algebraic multi-grid algorithm. The algorithm is implemented in a two-dimensional Cartesian-geometry code and tested by application to Weibel instability and to Alfvén wave dynamics. Results show the effectiveness of this approach. Extensions to arbitrary meshes and to a partially time-implicit scheme are briefly discussed.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2025

Ordinary and exotic mesons in the extended Linear Sigma Model

The extended Linear Sigma Model (eLSM) is a hadronic model based on the global symmetries of QCD and the corresponding explicit, anomalous, and spontaneous breaking patterns. In its basic three-flavor form, its mesonic part contains the dilaton/glueball as well as the nonets of pseudoscalar, scalar, vector, and axial–vector mesons, thus chiral symmetry is linearly realized. In the chiral limit and neglecting the chiral anomaly, only one term – within the dilaton potential – breaks dilatation invariance, and all terms are chirally symmetric. Spontaneous symmetry breaking is implemented by a generalization of the Mexican-hat potential, with explicit symmetry breaking responsible for its tilting. The overall mesonic phenomenology up to ~2 GeV is in agreement with the PDG compilation of masses and partial and total decay widths. The eLSM was enlarged in a straightforward way to include other conventional quark–antiquark nonets (pseudovector and orbitally excited vector mesons, tensor and axial-tensor mesons, radially excited (pseudo)scalar mesons, etc.), as well as two nonets of hybrid mesons, the lightest one with exotic quantum numbers J $\mathscr{PC}$ = 1 -+ not allowed for $\bar{q}q$ objects, such as the resonance π 1 (1600) and the recently discovered η 1 (1855) . In doing so, different types of chiral multiplets are introduced: heterochiral and homochiral multiplets, which differ in the way they transform under chiral transformations. Moreover, besides the scalar glueball that is present from the beginning as dilaton, other glueballs, the tensor, the pseudoscalar and the vector glueballs were coupled to the eLSM: the scalar resonance ƒ 0 (1710) turns out to be mostly gluonic, the tensor glueball couples strongly to vector mesons, and the pseudoscalar glueball couples sizably to $ππη'$ and can be assigned to X (2370) or X (2600). In all cases above, masses and decays can be analyzed allowing for a better understanding of both conventional and non-conventional mesons: whenever data are available, a comparison is performed and, when this is not the case, predictions of decay widths and decay ratios are outlined. The eLSM contains chiral partners on an equal footing and is therefore well suited for studies of chiral symmetry restoration at nonzero temperature and densities: this is done by coupling it to the Polyakov loop. Finally, the QCD phase diagram and the location of the critical endpoint were investigated within this framework.

Chiral symmetry↗

DOE OSTI2025

Pion-nucleon scattering in baryon chiral perturbation theory combined with the 1/𝑁 𝑐 expansion

This work implements the combined baryon chiral perturbation theory (BChPT) and 1/𝑁 𝑐 expansions for pion-nucleon elastic scattering. The effective theory is based on the baryon sector dynamical spin-flavor 𝑆⁢𝑈⁡(4) symmetry emergent in the large 𝑁 𝑐 limit, whose breaking is controlled by the 1/𝑁 𝑐 expansion. The noncommutativity of the chiral and 1/𝑁 𝑐 expansions in unitarity corrections (loops) requires a linking of both expansions. As it was shown in the case of baryon masses and currents, the natural linking is the 𝜉 expansion, in which 𝒪⁡(𝑝) = 𝒪⁡(1/𝑁 𝑐 ) = 𝒪⁡(𝜉). The spin-flavor symmetry requires that the ground state baryons span an 𝑆⁢𝑈⁡(4) symmetric irreducible representation which implies that in particular 𝑁 and Δ are active degrees of freedom in the effective theory. The scattering amplitude is expanded to the next-to-next-to leading order in the 𝜉 expansion, corresponding to the one-loop contributions with the leading-order Lagrangian. The results are given for generic 𝑁 𝑐 in order to demonstrate the consistency of the framework. The spin-flavor symmetry plays a central role in maintaining the consistency of the effective theory with respect to the 1/𝑁 𝑐 expansion. This consistency manifests itself in an improvement in the convergence of the low energy expansion with respect to the case of the ordinary BChPT without an explicit dynamical Δ, which is known to be inconsistent with the constraints of 𝑁 𝑐 scaling. Fits to the 𝜋⁢𝑁 → 𝜋⁢𝑁, 𝑆, 𝑃, and 𝐷 partial wave amplitudes from the SAID data base are finally used to test the framework and to determine the energy range of its applicability.

Jayakodige, D. [Hampton Univ., Hampton, VA (United↗

DOE OSTI2024

Node-degree aware edge sampling mitigates inflated classification performance in biomedical random walk-based graph representation learning

Motivation: Graph representation learning is a family of related approaches that learn low-dimensional vector representations of nodes and other graph elements called embeddings. Embeddings approximate characteristics of the graph and can be used for a variety of machine-learning tasks such as novel edge prediction. For many biomedical applications, partial knowledge exists about positive edges that represent relationships between pairs of entities, but little to no knowledge is available about negative edges that represent the explicit lack of a relationship between two nodes. For this reason, classification procedures are forced to assume that the vast majority of unlabeled edges are negative. Existing approaches to sampling negative edges for training and evaluating classifiers do so by uniformly sampling pairs of nodes. Results: We show here that this sampling strategy typically leads to sets of positive and negative examples with imbalanced node degree distributions. Using representative heterogeneous biomedical knowledge graph and random walk-based graph machine learning, we show that this strategy substantially impacts classification performance. If users of graph machine-learning models apply the models to prioritize examples that are drawn from approximately the same distribution as the positive examples are, then performance of models as estimated in the validation phase may be artificially inflated. We present a degree-aware node sampling approach that mitigates this effect and is simple to implement. Availability and implementation: Our code and data are publicly available at https://github.com/monarch-initiative/negativeExampleSelection.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2026

Extending Symmetry-Preserving Attention Networks (SPANet) for Jet Assignment in Fully Hadronic $t\bar{t}$ Events

Fully hadronic $t\bar{t}$ reconstruction requires assigning reconstructed jets to the two top-quark decay branches, $t\bar{t}\to(Wb)(Wb)\to(qqb)(qqb)$. This is a combinatorially large, symmetry-rich, and frequently underconstrained set-assignment problem due to detector effects and partial reconstructability. SPANet provides a strong symmetry-preserving baseline for this task, but its standard inference eagerly commits to a single hypothesis and does not explicitly treat branch-level reconstructability decisions. We present a two-stage extension of the SPANet pipeline for fully hadronic $t\bar{t}$ events: (i) SPANet is modified into a proposal model that generates a shortlist of candidate jet assignments; (ii) a custom dual-head set transformer is trained to re-rank these candidates and identify reconstructible branches. Our extension gives modest improvements in candidate-selection efficiency, with SPANet achieving $69.9\%$ and our extension achieving $71.1\%$. Finally, an oracle study of the generated shortlist shows a substantial upper bound of $88.5\%$ on the evaluated fully reconstructable subset, suggesting that the shortlist contains significant residual information that is not fully exploited.

Lisondodi Tada, Mateo [Puerto Rico U., Mayaguez] (↗