pith. sign in

arxiv: 2604.07292 · v2 · pith:QBMGZVLJnew · submitted 2026-04-08 · 💻 cs.LG

Graph Neural ODE Digital Twins for Control-Oriented Reactor Thermal-Hydraulic Forecasting Under Partial Observability

Akzhol Almukhametov , Doyeong Lim , Rui Hu , Yang Liu This is my paper

Pith reviewed 2026-05-21 09:22 UTC · model grok-4.3

classification 💻 cs.LG
keywords graph neural networksneural ODEthermal hydraulicspartial observabilitydigital twinreactor modelingphysics-informed ML
0
0 comments X

The pith

A graph neural ODE surrogate reconstructs and forecasts thermal-hydraulic states at uninstrumented reactor locations from limited sensor data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper develops a physics-informed graph neural network combined with a neural ordinary differential equation to predict temperature and flow states across a reactor system. It handles partial observability by initializing missing nodes based on the sensor graph topology and then evolving the dynamics continuously in time. This approach allows accurate predictions far into the future while running much faster than real-time simulations. A fine-tuning step on experimental data shows the model learns physically consistent scaling laws rather than just memorizing trajectories. If correct, this enables real-time control and uncertainty quantification for advanced nuclear reactors using sparse instrumentation.

Core claim

The GNN-ODE surrogate achieves an average MAE of 0.91 K at 60 s and 2.18 K at 300 s for uninstrumented nodes, with R² up to 0.995 for missing-node state reconstruction. After fine-tuning on experimental data with only 30 sequences, it recovers a Reynolds-number exponent consistent with established correlations, indicating it has learned constitutive relations beyond trajectory fitting.

What carries the argument

A directed sensor graph with flow and heat transfer-aware message passing, advanced in continuous time by a controlled Neural ODE, plus a topology-guided missing-node initializer.

If this is right

  • Accurate state reconstruction at locations without sensors enables plant-wide monitoring from sparse instrumentation.
  • Millisecond-scale inference supports 64-member ensemble forecasts for uncertainty quantification in control applications.
  • Fine-tuning on real data recovers physically meaningful parameters like the Reynolds-number exponent in heat transfer correlations.
  • The autoregressive rollout maintains fidelity over hundreds of seconds for control-oriented forecasting.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Such models could reduce the need for dense sensor arrays in future reactor designs by leveraging graph connectivity.
  • Extending the framework to other multiphysics systems might allow digital twins for chemical plants or power grids with partial measurements.
  • Testing on different reactor geometries would verify if the hydraulic connectivity encoding generalizes without retraining.

Load-bearing premise

The directed sensor graph whose edges encode hydraulic connectivity is sufficient to accurately reconstruct and evolve states at uninstrumented locations from the start of each simulation rollout.

What would settle it

A direct comparison where the model is tested on a transient with a sensor failure pattern not seen in training, checking if the temperature predictions at missing nodes deviate significantly from ground truth beyond the reported MAE.

Figures

Figures reproduced from arXiv: 2604.07292 by Akzhol Almukhametov, Doyeong Lim, Rui Hu, Yang Liu.

Figure 1
Figure 1. Figure 1: Architecture of the proposed physics-informed GNN-ODE surrogate for thermal-hydraulic [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: CAD model of the experimental thermal–hydraulic facility illustrating the three-loop [PITH_FULL_IMAGE:figures/full_fig_p012_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: SAM-based digital twin model of the experimental thermal-fluid facility used for synthetic [PITH_FULL_IMAGE:figures/full_fig_p014_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Horizontal, compact representation of the 3-loop thermal system graph topology. [PITH_FULL_IMAGE:figures/full_fig_p014_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Forecasting comparison across the four transient scenarios listed in Table 3. The red [PITH_FULL_IMAGE:figures/full_fig_p018_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Long-horizon rollout Mean Absolute Error (MAE) versus forecast horizon on held-out [PITH_FULL_IMAGE:figures/full_fig_p020_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Surrogate predictions versus experimental measurements for observable facility nodes [PITH_FULL_IMAGE:figures/full_fig_p022_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Inferred thermal trajectories for permanently uninstrumented (hidden) nodes during [PITH_FULL_IMAGE:figures/full_fig_p023_8.png] view at source ↗
read the original abstract

Real-time supervisory control of advanced reactors requires accurate forecasting of plant-wide thermal-hydraulic states, including locations where physical sensors are unavailable. Meeting this need calls for surrogate models that combine predictive fidelity, millisecond-scale inference, and robustness to partial observability. In this work, we present a physics-informed message-passing Graph Neural Network coupled with a Neural Ordinary Differential Equation (GNN-ODE) to addresses all three requirements simultaneously. We represent the whole system as a directed sensor graph whose edges encode hydraulic connectivity through flow/heat transfer-aware message passing, and we advance the latent dynamics in continuous time via a controlled Neural ODE. A topology-guided missing-node initializer reconstructs uninstrumented states at rollout start; prediction then proceeds fully autoregressively. The GNN-ODE surrogate achieves satisfactory results for the system dynamics prediction. On held-out simulation transients, the surrogate achieves an average MAE of 0.91 K at 60 s and 2.18 K at 300 s for uninstrumented nodes, with $R^2$ up to 0.995 for missing-node state reconstruction. Inference runs at approximately 105 times faster than simulated time on a single GPU, enabling 64-member ensemble rollouts for uncertainty quantification. To assess sim-to-real transfer, we adapt the pretrained surrogate to experimental facility data using layerwise discriminative fine-tuning with only 30 training sequences. The learned flow-dependent heat-transfer scaling recovers a Reynolds-number exponent consistent with established correlations, indicating constitutive learning beyond trajectory fitting. The model tracks a steep power change transient and produces accurate trajectories at uninstrumented locations.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents a physics-informed Graph Neural Network coupled to a Neural ODE (GNN-ODE) surrogate for real-time forecasting of reactor thermal-hydraulic states under partial observability. The system is modeled as a directed sensor graph whose edges encode hydraulic connectivity via flow/heat-transfer-aware message passing; a topology-guided missing-node initializer reconstructs uninstrumented states at rollout start, after which the controlled Neural ODE evolves the latent dynamics autoregressively. On held-out simulation transients the model reports average MAE of 0.91 K at 60 s and 2.18 K at 300 s for uninstrumented nodes (R² up to 0.995), runs ~105× faster than real time, and after layer-wise fine-tuning on only 30 experimental sequences recovers a Reynolds-number exponent consistent with established heat-transfer correlations.

Significance. If the performance numbers and sim-to-real constitutive recovery hold, the work supplies a concrete route to millisecond-scale, physics-consistent digital twins that can operate with sparse instrumentation—an important capability for supervisory control of advanced reactors. The explicit recovery of a physically plausible Reynolds exponent after limited fine-tuning supplies external grounding that goes beyond trajectory fitting and strengthens the claim of constitutive learning.

major comments (2)
  1. [Abstract / Results] Abstract and results section: the central MAE (0.91 K / 2.18 K) and R² (0.995) figures are presented without error bars, without comparison to non-graph or non-ODE baselines, and without explicit description of the train/validation/test split or the distribution of missing-node patterns. These omissions make it impossible to judge whether the reported accuracy is robust or merely an artifact of the particular missing-node configurations used in testing.
  2. [Methods (initializer and graph construction)] Methods (topology-guided missing-node initializer): the initializer and subsequent message-passing are defined on a fixed directed graph whose edges follow hydraulic connectivity. If the initializer is trained only on the same distribution of missing patterns that appear in the test set, clustered or path-wise missing nodes could produce inaccurate initial latent states that the Neural ODE cannot correct within the reported rollout horizons. A controlled experiment that varies the spatial clustering of missing sensors is required to substantiate the partial-observability claim.
minor comments (2)
  1. [Abstract] The phrase “satisfactory results” in the abstract is vague; replace with the quantitative metrics already given later in the text.
  2. [Results (inference timing)] Clarify whether the 105× speed-up is measured wall-clock or includes data-transfer overhead, and state the GPU model used.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the positive assessment of our work's significance and for the constructive comments. We address each major point below and have revised the manuscript to strengthen the presentation of results and robustness claims.

read point-by-point responses

  1. Referee: [Abstract / Results] Abstract and results section: the central MAE (0.91 K / 2.18 K) and R² (0.995) figures are presented without error bars, without comparison to non-graph or non-ODE baselines, and without explicit description of the train/validation/test split or the distribution of missing-node patterns. These omissions make it impossible to judge whether the reported accuracy is robust or merely an artifact of the particular missing-node configurations used in testing.

    Authors: We agree that error bars, baseline comparisons, and explicit details on splits and missing-node distributions are needed for a complete evaluation. In the revised manuscript we now report MAE and R² with standard deviations computed over five independent random seeds. We have added two baselines: an MLP-ODE (non-graph) and a GNN without the Neural ODE component. The Methods section has been expanded to describe the 70/15/15 train/validation/test split on transients and the test-set missing-node distribution, which includes random, clustered, and path-wise patterns at proportions representative of the evaluation scenarios. revision: yes

  2. Referee: [Methods (initializer and graph construction)] Methods (topology-guided missing-node initializer): the initializer and subsequent message-passing are defined on a fixed directed graph whose edges follow hydraulic connectivity. If the initializer is trained only on the same distribution of missing patterns that appear in the test set, clustered or path-wise missing nodes could produce inaccurate initial latent states that the Neural ODE cannot correct within the reported rollout horizons. A controlled experiment that varies the spatial clustering of missing sensors is required to substantiate the partial-observability claim.

    Authors: We acknowledge that an explicit controlled study on spatial clustering would provide stronger evidence for robustness under partial observability. Although the original test set already contained a mixture of missing patterns, we have added a new controlled experiment in the revision. This experiment systematically varies the degree of spatial clustering of missing sensors (isolated, moderate clusters, and fully path-wise) while keeping the total number of missing nodes fixed, and reports the resulting MAE at 60 s and 300 s. The results show graceful degradation and confirm that the Neural ODE component recovers accuracy over the rollout horizon even for clustered missingness. revision: yes

Circularity Check

0 steps flagged

No significant circularity; claims rest on held-out evaluation and external correlation match

full rationale

The paper trains the GNN-ODE on simulation data and reports MAE/R² on held-out transients for uninstrumented nodes; the sim-to-real step uses fine-tuning on 30 experimental sequences and validates by recovering a Reynolds-number exponent that matches established correlations outside the fitted trajectories. The topology-guided initializer is an architectural component whose reconstruction accuracy is measured on separate test patterns rather than defined to equal the target states. No equations reduce by construction to inputs, no load-bearing self-citation chains appear, and the constitutive-learning claim is supported by an independent physical benchmark rather than renaming or self-definition. The derivation therefore remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 1 invented entities

The central claim rests on representing the reactor as a directed graph whose edges carry hydraulic information and on the ability of a neural ODE to evolve latent states continuously; these modeling choices are introduced without independent verification beyond the reported trajectory matches.

free parameters (1)
  • heat-transfer scaling parameters
    Learned during fine-tuning to match experimental transients; the recovered Reynolds exponent is presented as consistent with literature but is still data-driven.
axioms (1)
  • domain assumption The plant can be faithfully represented as a directed sensor graph whose edges encode hydraulic connectivity and heat-transfer relations
    Invoked to justify message-passing and the topology-guided initializer.
invented entities (1)
  • topology-guided missing-node initializer no independent evidence
    purpose: Reconstruct initial states at uninstrumented locations so autoregressive rollout can begin
    New component introduced to handle partial observability; no external falsifiable test is described.

pith-pipeline@v0.9.0 · 5833 in / 1503 out tokens · 38147 ms · 2026-05-21T09:22:35.997399+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

50 extracted references · 50 canonical work pages · 4 internal anchors

  1. [1]

    International Energy Agency.World Energy Outlook 2022. Tech. rep. Paris: IEA, 2022.url: https://www.iea.org/reports/world-energy-outlook-2022

    work page 2022

  2. [2]

    Economics and finance of small modular reactors: A systematic review and research agenda

    Benito Mignacca and Giorgio Locatelli. “Economics and finance of small modular reactors: A systematic review and research agenda”. In:Renewable and Sustainable Energy Reviews118 (2020), p. 109519.doi:10.1016/j.rser.2019.109519

    work page doi:10.1016/j.rser.2019.109519 2020

  3. [3]

    Assessment of technoeconomic opportunities in automation for nu- clear microreactors

    I. N. de Candido et al. “Assessment of technoeconomic opportunities in automation for nu- clear microreactors”. In:Nuclear Science and Engineering(2024), pp. 1–20.doi:10.1080/ 00295639.2024.2372511

    work page arXiv 2024

  4. [4]

    UO 2-fueled microreactors: Near-term solutions to emerging markets

    K. Shirvan et al. “UO 2-fueled microreactors: Near-term solutions to emerging markets”. In: Nuclear Engineering and Design412 (2023), p. 112470.doi:10.1016/j.nucengdes.2023. 112470

    work page doi:10.1016/j.nucengdes.2023 2023

  5. [5]

    Ponciroli et al.Design and Prototyping of Advanced Control Systems for Advanced Reactors Operating in the Future Electric Grid

    R. Ponciroli et al.Design and Prototyping of Advanced Control Systems for Advanced Reactors Operating in the Future Electric Grid. Final Report ANL/NSE-24/40. Argonne, IL: Argonne National Laboratory, 2024

    work page 2024

  6. [6]

    Design of a supervisory control system for autonomous operation of advanced reactors

    Akshay J Dave et al. “Design of a supervisory control system for autonomous operation of advanced reactors”. In:Annals of Nuclear Energy182 (2023), p. 109593

    work page 2023

  7. [7]

    A safe reinforcement learning algorithm for supervisory control of power plants

    Yixuan Sun et al. “A safe reinforcement learning algorithm for supervisory control of power plants”. In:Knowledge-Based Systems301 (2024), p. 112312

    work page 2024

  8. [8]

    Model Predictive Control of an SP-100 Space Reactor Using Support Vector Regression and Genetic Optimization

    M. G. Na and B. R. Upadhyaya. “Model Predictive Control of an SP-100 Space Reactor Using Support Vector Regression and Genetic Optimization”. In:IEEE Transactions on Nuclear Science53.4 (2006), pp. 2319–2326.doi:10.1109/TNS.2006.878018

    work page doi:10.1109/tns.2006.878018 2006

  9. [9]

    A unified deep learning anomaly detection and classi fication approach for smart grid environments,

    Y. Chen and A. Ray. “Deep Reinforcement Learning Control of a Boiling Water Reactor”. In:IEEE Transactions on Nuclear Science69.8 (2022), pp. 1820–1832.doi:10.1109/TNS. 2022.3187662. 24

    work page doi:10.1109/tns 2022

  10. [10]

    The AGN-201 Digital Twin: A test bed for remotely monitoring nuclear reactors

    Ryan Stewart et al. “The AGN-201 Digital Twin: A test bed for remotely monitoring nuclear reactors”. In:Annals of Nuclear Energy213 (2025), p. 111041

    work page 2025

  11. [11]

    Development of whole system digital twins for advanced reactors: leveraging graph neural networks and SAM simulations

    Yang Liu et al. “Development of whole system digital twins for advanced reactors: leveraging graph neural networks and SAM simulations”. In:Nuclear Technology211.9 (2025), pp. 2206– 2223

    work page 2025

  12. [12]

    Current status of digital twin architecture and application in nuclear energy field

    Hu Mengyan et al. “Current status of digital twin architecture and application in nuclear energy field”. In:Annals of Nuclear Energy202 (2024), p. 110491

    work page 2024

  13. [13]

    A Digital Twin-Based Simulator for Small Modular and Mi- croreactors

    Zavier Ndum Ndum et al. “A Digital Twin-Based Simulator for Small Modular and Mi- croreactors”. In:Proceedings of the 2024 Winter Simulation Conference (WSC). IEEE. Or- lando, FL, USA, 2024, pp. 2963–2974.isbn: 979-8-3315-3420-2.url:https : / / informs - sim.org/wsc24papers/con179.pdf

    work page 2024

  14. [14]

    A deep-learning reduced-order model for thermal hydraulic characteristics rapid estimation of steam generators

    Shaopeng He et al. “A deep-learning reduced-order model for thermal hydraulic characteristics rapid estimation of steam generators”. In:International Journal of Heat and Mass Transfer 198 (2022), p. 123424

    work page 2022

  15. [15]

    Physics informed neural networks for surrogate modeling of accidental scenarios in nuclear power plants

    Federico Antonello, Jacopo Buongiorno, and Enrico Zio. “Physics informed neural networks for surrogate modeling of accidental scenarios in nuclear power plants”. In:Nuclear Engineer- ing and Technology55.9 (2023), pp. 3409–3416

    work page 2023

  16. [16]

    Brin et al., ‘Comparing ChatGPT and GPT -4 performance in USMLE soft skill assessments’, Sci Rep, vol

    K. Prantikos, S. Chatzidakis, L.H. Tsoukalas, et al. “Physics-informed neural network with transfer learning (TL-PINN) based on domain similarity measure for prediction of nuclear reactor transients.” In:Scientific Reports13 (2023), p. 16840.doi:10.1038/s41598-023- 43325-1

    work page doi:10.1038/s41598-023- 2023

  17. [17]

    Nuclear microreactor transient and load-following control with deep rein- forcement learning

    Leo Tunkle et al. “Nuclear microreactor transient and load-following control with deep rein- forcement learning”. In:Energy Conversion and Management: X27 (2025), p. 101090.doi: 10.1016/j.ecmx.2025.101090

    work page doi:10.1016/j.ecmx.2025.101090 2025

  18. [18]

    A Reinforcement Learning Approach to Augment Conventional PID Control in Nuclear Power Plant Transient Operation

    Aidan Rigby et al. “A Reinforcement Learning Approach to Augment Conventional PID Control in Nuclear Power Plant Transient Operation”. In:Nuclear Technology(2025), pp. 1– 19

    work page 2025

  19. [19]

    Development and assessment of a nearly autonomous management and control system for advanced reactors

    Linyu Lin et al. “Development and assessment of a nearly autonomous management and control system for advanced reactors”. In:Annals of Nuclear Energy150 (2021), p. 107861

    work page 2021

  20. [20]

    Neural Ordinary Differential Equations

    Tian Qi Chen et al. “Neural Ordinary Differential Equations”. In:Proceedings of the 32nd International Conference on Neural Information Processing Systems (NeurIPS 2018). 2018, pp. 6571–6583

    work page 2018

  21. [21]

    NeuroMANCER: Neural Modules with Adaptive Nonlinear Constraints and Efficient Regularizations

    Jan Drgona et al. “NeuroMANCER: Neural Modules with Adaptive Nonlinear Constraints and Efficient Regularizations”. In: (2023).url:https://github.com/pnnl/neuromancer

    work page 2023

  22. [22]

    Stable and safe human-aligned reinforcement learning through neural ordinary differential equations

    Liqun Zhao et al. “Stable and safe human-aligned reinforcement learning through neural ordinary differential equations”. In:arXiv preprint arXiv:2401.13148(2024).url:https: //arxiv.org/abs/2401.13148

    work page arXiv 2024

  23. [23]

    Robust Model Predictive Control With Neural Ordinary Differential Equa- tions for Nonlinear Systems

    Xuyu Shen et al. “Robust Model Predictive Control With Neural Ordinary Differential Equa- tions for Nonlinear Systems”. In:Optimal Control Applications and Methods(2025)

    work page 2025

  24. [24]

    Autonomous Control of Small-Scale Advanced Reactors via Digital Twin-Enabled Neural ODE Models

    Doyeong Lim et al. “Autonomous Control of Small-Scale Advanced Reactors via Digital Twin-Enabled Neural ODE Models”. In:Nuclear Science and Engineering((In Press))

    work page

  25. [25]

    The graph neural network model.IEEE Transactions on Neural Networks, 20(1):61–80, 2009.doi:10.1109/TNN.2008.2005605

    Franco Scarselli et al. “The Graph Neural Network Model”. In:IEEE Transactions on Neural Networks20.1 (2009), pp. 61–80.doi:10.1109/TNN.2008.2005605. 25

    work page doi:10.1109/tnn.2008.2005605 2009

  26. [26]

    Semi-Supervised Classification with Graph Convolutional Networks

    Thomas N Kipf and Max Welling. “Semi-Supervised Classification with Graph Convolutional Networks”. In:arXiv preprint arXiv:1609.02907(2016)

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  27. [27]

    Graph attention Network-Based model for multiple fault detection and identification of sensors in nuclear power plant

    Shuqi Liu et al. “Graph attention Network-Based model for multiple fault detection and identification of sensors in nuclear power plant”. In:Nuclear Engineering and Design419 (2024), p. 112949

    work page 2024

  28. [28]

    Spatial-Temporal Graph Conditionalized Normalizing Flows for Nuclear Power Plant Multivariate Anomaly Detection

    Le Zhang et al. “Spatial-Temporal Graph Conditionalized Normalizing Flows for Nuclear Power Plant Multivariate Anomaly Detection”. In:IEEE Transactions on Industrial Infor- matics20.11 (2024), pp. 12945–12954

    work page 2024

  29. [29]

    Graph neural network based multiple accident diagnosis in nuclear power plants: Data optimization to represent the system configuration

    Young Ho Chae et al. “Graph neural network based multiple accident diagnosis in nuclear power plants: Data optimization to represent the system configuration”. In:Nuclear Engi- neering and Technology54.8 (2022), pp. 2859–2870

    work page 2022

  30. [30]

    Interpretability study of a typical fault diagnosis model for nuclear power plant primary circuit based on a graph neural network

    Xin Wang, Hang Wang, and MinJun Peng. “Interpretability study of a typical fault diagnosis model for nuclear power plant primary circuit based on a graph neural network”. In:Reliability Engineering & System Safety261 (2025), p. 111151

    work page 2025

  31. [31]

    Forecasting In-Core Power Distributions in Nuclear Power Plants via a Spatial– Temporal Hierarchical-Directed Network

    W. Lin et al. “Forecasting In-Core Power Distributions in Nuclear Power Plants via a Spatial– Temporal Hierarchical-Directed Network”. In:Progress in Nuclear Energy186 (2026). Spatial– temporal hierarchical-directed network with graph-based spatial modeling, p. 109123.doi: 10.1016/j.pnucene.2025.109123

    work page doi:10.1016/j.pnucene.2025.109123 2026

  32. [32]

    Learning Constrained Parametric Differen- tiable Predictive Control Policies With Guarantees

    J´ an Drgoˇ na, Aaron Tuor, and Draguna Vrabie. “Learning Constrained Parametric Differen- tiable Predictive Control Policies With Guarantees”. In:IEEE Transactions on Systems, Man, and Cybernetics: Systems54.6 (2024), pp. 3596–3607.doi:10.1109/TSMC.2024.3368026

    work page doi:10.1109/tsmc.2024.3368026 2024

  33. [33]

    A 3-D Neutron Distribution Reconstruction Method Based on the Off-Situ Measurement for Reactor

    Pei Cao, Chenglong Cao, and Quan Gan. “A 3-D Neutron Distribution Reconstruction Method Based on the Off-Situ Measurement for Reactor”. In:IEEE Transactions on Nu- clear Science68.12 (2021), pp. 2694–2701.doi:10.1109/TNS.2021.3123381

    work page doi:10.1109/tns.2021.3123381 2021

  34. [34]

    An Explicit Off-Situ Inversion Method for Neutron Fields in Reactor Core Based on Graph Structure

    Pei Cao et al. “An Explicit Off-Situ Inversion Method for Neutron Fields in Reactor Core Based on Graph Structure”. In:IEEE Transactions on Nuclear Science73.3 (2026), pp. 566– 577.doi:10.1109/TNS.2026.3651311

    work page doi:10.1109/tns.2026.3651311 2026

  35. [35]

    Gaussian Error Linear Units (GELUs)

    Dan Hendrycks and Kevin Gimpel. “Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units”. In:CoRRabs/1606.08415 (2016). arXiv:1606.08415.url: http://arxiv.org/abs/1606.08415

    work page internal anchor Pith review Pith/arXiv arXiv 2016

  36. [36]

    Sigmoid-weighted linear units for neural net- work function approximation in reinforcement learning

    Stefan Elfwing, Eiji Uchibe, and Kenji Doya. “Sigmoid-weighted linear units for neural net- work function approximation in reinforcement learning”. In:Neural Networks107 (2018), pp. 3–11

    work page 2018

  37. [37]

    Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

    Samy Bengio et al. “Scheduled Sampling for Sequence Prediction with Recurrent Neural Net- works”. In:Advances in Neural Information Processing Systems (NeurIPS). 2015, pp. 1171– 1179.url:https://arxiv.org/abs/1506.03099

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  38. [38]

    Rui Hu et al.SAM user’s guide. Tech. rep. Argonne National Lab.(ANL), Argonne, IL (United States), 2021

    work page 2021

  39. [39]

    Rui Hu et al.SAM theory manual. Tech. rep. Argonne National Lab.(ANL), Argonne, IL (United States), 2021

    work page 2021

  40. [40]

    An ai-driven thermal-fluid testbed for advanced small modular reac- tors: Integration of digital twin and large language models

    Doyeong Lim et al. “An ai-driven thermal-fluid testbed for advanced small modular reac- tors: Integration of digital twin and large language models”. In:AI Thermal Fluids(2025), p. 100023. 26

    work page 2025

  41. [41]

    Kairos power thermal hydraulics research and development

    Edward Blandford et al. “Kairos power thermal hydraulics research and development”. In: Nuclear Engineering and Design364 (2020), p. 110636

    work page 2020

  42. [42]

    Nuclear Regulatory Commission.Human Performance Tools

    U.S. Nuclear Regulatory Commission.Human Performance Tools. Tech. rep. Accession Num- ber: ML102120052. U.S. Nuclear Regulatory Commission, 2010.url:https://www.nrc.gov/ docs/ML1021/ML102120052.pdf

    work page 2010

  43. [43]

    Department of Energy.Human Performance Improvement Handbook, Volume 1: Con- cepts and Principles

    U.S. Department of Energy.Human Performance Improvement Handbook, Volume 1: Con- cepts and Principles. Tech. rep. DOE-HDBK-1028-2009. U.S. Department of Energy, 2009. url:http://large.stanford.edu/courses/2019/ph241/simone1/docs/doe-hdbk-1028- 2009.pdf

    work page 2009

  44. [44]

    Jeremy Howard and Sebastian Ruder.Universal Language Model Fine-tuning for Text Clas- sification. 2018. arXiv:1801.06146 [cs.CL].url:https://arxiv.org/abs/1801.06146

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  45. [45]

    Analytical Chemistry 36(8), 1627–1639 (1964)

    Abraham Savitzky and Marcel J. E. Golay. “Smoothing and differentiation of data by sim- plified least squares procedures”. In:Analytical Chemistry36.8 (1964), pp. 1627–1639.doi: 10.1021/ac60214a047

    work page doi:10.1021/ac60214a047 1964

  46. [46]

    Temperature and heat flux estimation from sampled transient sensor measurements

    Zaichun Feng et al. “Temperature and heat flux estimation from sampled transient sensor measurements”. In:International Journal of Thermal Sciences49.12 (2010), pp. 2385–2390. doi:10.1016/j.ijthermalsci.2010.08.004

    work page doi:10.1016/j.ijthermalsci.2010.08.004 2010

  47. [47]

    Automating Monte Carlo Simulations in Nuclear Engineering with Domain Knowledge-embedded Large Language Model Agents

    Zavier Ndum Ndum et al. “Automating Monte Carlo Simulations in Nuclear Engineering with Domain Knowledge-embedded Large Language Model Agents”. In:Energy and AI21 (2025), p. 100555.issn: 2666-5468.doi:https://doi.org/10.1016/j.egyai.2025.100555. url:https://www.sciencedirect.com/science/article/pii/S2666546825000874

    work page doi:10.1016/j.egyai.2025.100555 2025

  48. [48]

    Yang Liu et al.Automating Data-Driven Modeling and Analysis for Engineering Applications using Large Language Model Agents. 2025. arXiv:2510 . 01398 [cs.AI].url:https : / / arxiv.org/abs/2510.01398

    work page arXiv 2025

  49. [49]

    Zaid Abulawi et al.AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation. 2026. arXiv:2603 . 24736 [cs.AI].url:https://arxiv.org/abs/2603.24736

    work page arXiv 2026

  50. [50]

    Large Language Model-assisted Digital Twin for Remote Monitor- ing and Control of Advanced Reactors

    Zavier Ndum Ndum et al. “Large Language Model-assisted Digital Twin for Remote Monitor- ing and Control of Advanced Reactors”. In:Progress in Nuclear Energy192 (2026), p. 106172. doi:10.1016/j.pnucene.2025.106172. 27

    work page doi:10.1016/j.pnucene.2025.106172 2026