pith. sign in

arxiv: 2604.17066 · v1 · submitted 2026-04-18 · 💻 cs.LG · math.PR

Reference-state System Reliability method for scalable uncertainty quantification of coherent systems

Ji-Eun Byun , Hyeuk Ryu , Junho Song This is my paper

Pith reviewed 2026-05-10 06:45 UTC · model grok-4.3

classification 💻 cs.LG math.PR
keywords coherent systemssystem reliabilityuncertainty quantificationMonte Carlo simulationreference statesscalable computationnetwork reliability
0
0 comments X

The pith

The Reference-state System Reliability method evaluates large coherent systems by classifying Monte Carlo samples against reference states using batched matrix operations.

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

The paper introduces the Reference-state System Reliability (RSR) method to overcome scalability limits of decomposition-based approaches for computing state probabilities in coherent systems such as infrastructure networks and supply chains. RSR still marks boundaries with reference states in component-state space but explores that space by classifying Monte Carlo samples rather than splitting it into disjoint regions, so cost depends far less on the number of reference states. Samples and reference states are stored as matrices and compared with batched operations, letting the method exploit fast matrix hardware developed for machine learning. This yields concrete performance: a 119-node, 295-edge graph is evaluated in under 10 seconds, and the approach reaches hundreds of thousands of reference states while extending directly to multi-state systems. A reader would care because these sizes are typical of real infrastructure problems that existing reference-state methods cannot handle in practical time.

Core claim

RSR characterises the boundary between different system states using reference states in the component-state space but explores the space by classifying Monte Carlo samples instead of decomposing it into disjoint hypercubes, making computational cost significantly less sensitive to the number of reference states and allowing direct use of high-throughput matrix computing.

What carries the argument

Reference-state classification of Monte Carlo samples stored and compared as matrices with batched operations, replacing hypercube decomposition for exploring the component-state space.

If this is right

  • RSR evaluates the system-state probability of a 119-node, 295-edge graph within 10 seconds.
  • RSR scales to problems involving hundreds of thousands of reference states.
  • RSR extends naturally to multi-state systems.
  • RSR convergence slows when the number of boundary reference states grows exceedingly large.

Where Pith is reading between the lines

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

  • The matrix formulation could be paired with learned low-dimensional representations of state boundaries to mitigate slowdown at very high reference-state counts.
  • Similar sample-classification logic may transfer to other high-dimensional probabilistic problems such as stochastic optimization or dynamic reliability.
  • Hardware acceleration already tuned for matrix workloads could make RSR suitable for online risk monitoring of operational networks.

Load-bearing premise

Classifying Monte Carlo samples against reference states produces unbiased system-state probabilities equivalent to those obtained by full decomposition regardless of the choice or density of reference states.

What would settle it

Running RSR and an exact full-decomposition method side-by-side on a small coherent system whose exact state probabilities are known, then checking whether the two sets of probabilities agree within Monte Carlo error as the number and placement of reference states are varied.

Figures

Figures reproduced from arXiv: 2604.17066 by Hyeuk Ryu, Ji-Eun Byun, Junho Song.

Figure 1
Figure 1. Figure 1: Illustrative network system in which the six edges may fail. The system takes state 0 if nodes 1 and 6 (grey-coloured) are disconnected and 1 otherwise. (a) Original graph. (b) Fully operational network (Φ = 1). (c) Failure of edge 5 with Φ = 1. (d) Failure of edge 1 leading to Φ = 0. (a) (b) (c) [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Example component-state vectors dominated by the reference state x3 = (x 0 1 , x1 2 , . . . , x1 6 ) in Fig. 1d. Panels show additional component degradations relative to x3: (a) edge 4, (b) edge 6, and (c) edges 5 and 6, all of which are dominated by x3. 2.3. Decomposition-based approaches for coherent systems 2.3.1. Key idea The usefulness of reference states has long been recognised for reliability anal… view at source ↗
Figure 3
Figure 3. Figure 3: Illustrative decomposition process in the component-state space of random variables X1 and X2, each with five states. Three reference states are assumed to be known, resulting in seven hypercubes. (a) The component-state space with the three reference states; shaded regions indicate subspace dominated by references. (b)–(d) Step-by-step decomposition of the component-state space as reference states are pro… view at source ↗
Figure 4
Figure 4. Figure 4: Example random graphs and application of the BRC algorithm [2]. (a) Graph 1 with 59 nodes and 262 edges and (b) Graph 2 with 119 nodes and 295 edges, where origin and destination nodes are marked by red crosses. Panels (c)–(f) show the results of applying the BRC algorithm for connectivity probability estimation. Specifically, (c) number of branches, (d) memory usage, measured by Resident Set Size (RSS), (… view at source ↗
Figure 5
Figure 5. Figure 5: Reported number of reference states in [ [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Illustration of the (x1, x2)-state space with reference states and samples. The orange cross and blue circles represent lower and upper reference states, respectively, while red diamonds indicate sample points in x-space. The corresponding matrix representations of x ≤0 1 , x ≥1 1 , x ≥1 2 , as well as two selected samples x1 and x2, are given in Eqs. (10)–(14). 3.3. Reference-state sample classification t… view at source ↗
Figure 7
Figure 7. Figure 7: Illustration of reference-state sample classification via batched computation. The flattened sample matrix Hflat is multiplied by the flattened reference-state matrices RL flat and RU flat. If, for a sample h, there exists a reference state r such that Vh,r = 0, then h is classified into the corresponding index set for I L or I U ; otherwise, it remains unclassified in I u. The corresponding formal algorit… view at source ↗
Figure 8
Figure 8. Figure 8: Illustration of component-wise boundary search, continuing from the sample classification in [PITH_FULL_IMAGE:figures/full_fig_p020_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: RSR algorithm. Stage 1 identifies the boundary reference-state sets L and U, while Stage 2 evaluates the system probabilities P(S ≤ m′ ) and P(S ≥ m′ + 1). Common operations are shown in grey, while Stage 1–specific and Stage 2–specific operations are highlighted in orange and red, respectively. The dashed arrow indicates the use of Stage 1 outcomes as additional inputs to Stage 2. Rounded rectangles, rect… view at source ↗
Figure 10
Figure 10. Figure 10: Comparison of RSR and BRC for the single-OD connectivity on random graphs shown in [PITH_FULL_IMAGE:figures/full_fig_p025_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: RSR implementation for single-OD and global connectivity on the random graphs shown in [PITH_FULL_IMAGE:figures/full_fig_p027_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: RSR implementation with and without the componentwise boundary search. The results are shown for single-OD on the random graph in Figure 4a. Black solid lines and light blue dashed lines respectively correspond to with and without the componentwise boundary search. Black lines represent the identical data shown in Figures 10b–10d. (a) Memory usage measured by RSS, (b) cumulative computational time, and (c… view at source ↗
Figure 13
Figure 13. Figure 13: Comparison of computational performance by desktop and high-performance computing on NCI Gadi (GPU queue, 2 GPUs, 24 CPU cores, 96 workers). (a) Memory usage measured by RSS, (b) cumulative computational time, and (c) unclassified probability, all shown as functions of the number of reference states. Black lines represent single-OD connectivity and are identical to the data shown in Figures 10b–10d, with … view at source ↗
read the original abstract

Coherent systems are representative of many practical applications, ranging from infrastructure networks to supply chains. Probabilistic evaluation of such systems remains challenging, however, because existing decomposition-based methods scale poorly as the number of components grows. To address this limitation, this study proposes the Reference-state System Reliability (RSR) method. Like existing approaches, RSR characterises the boundary between different system states using reference states in the component-state space. Where it departs from these methods is in how the state space is explored: rather than using reference states to decompose the space into disjoint hypercubes, RSR uses them to classify Monte Carlo samples, making computational cost significantly less sensitive to the number of reference states. To make this classification efficient, samples and reference states are stored as matrices and compared using batched matrix operations, allowing RSR to exploit the advances in high-throughput matrix computing driven by modern machine learning. We demonstrate that RSR evaluates the system-state probability of a graph with 119 nodes and 295 edges within 10~seconds, highlighting its potential for real-time risk assessment of large-scale systems. We further show that RSR scales to problems involving hundreds of thousands of reference states -- well beyond the reach of existing methods -- and extends naturally to multi-state systems. Nevertheless, when the number of boundary reference states grows exceedingly large, RSR's convergence slows down, a limitation shared with existing reference-state-based approaches that motivates future research into learning-based representations of system-state boundaries.

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

3 major / 2 minor

Summary. The paper proposes the Reference-state System Reliability (RSR) method for probabilistic evaluation of coherent systems. Instead of decomposing the component-state space into disjoint hypercubes using reference states (minimal path or cut vectors), RSR classifies Monte Carlo samples against a set of reference states via batched matrix comparisons. This reformulation is claimed to reduce sensitivity to the number of reference states, enabling evaluation of a 119-node/295-edge graph in under 10 seconds and scaling to hundreds of thousands of reference states, while extending to multi-state systems.

Significance. If the classification step is shown to be unbiased and equivalent to exact decomposition, the method would offer a practical advance for real-time risk assessment of large infrastructure and supply-chain networks by leveraging high-throughput matrix operations from modern hardware. The reported scaling behavior and multi-state extension are potentially valuable, though they rest on the unverified assumption that reference-state classification reproduces the exact system-state probabilities.

major comments (3)
  1. [§3] §3 (Method): The central claim that Monte Carlo sample classification against reference states yields the same system-state probabilities as hypercube decomposition is asserted without derivation or proof. No equation demonstrates that the estimator (1/N)∑I(classified state) equals the decomposed probability sum, nor is there a condition guaranteeing that the chosen reference states form a complete boundary (i.e., every sample is assigned its true coherent-system state).
  2. [§4] §4 (Numerical experiments): Only wall-clock timing is reported for the 119-node graph (under 10 s) and scaling to ~10^5 reference states. No accuracy comparison to exact decomposition on small instances, no bias/variance analysis, and no verification that classification error remains zero when reference states are incomplete or sparse.
  3. [Abstract, §3.2] Abstract and §3.2: The statement that RSR is 'equivalent' to existing reference-state methods for probability computation lacks supporting analysis of misclassification risk. The noted slowdown for very large boundary sets is acknowledged but not quantified with respect to reference-state density or completeness.
minor comments (2)
  1. [§3] Notation for reference states (minimal path/cut vectors) and the batched comparison operator could be introduced with a small illustrative example in §3 to improve readability.
  2. [§4] The manuscript would benefit from a short table comparing RSR runtime and accuracy against at least one standard decomposition method on a small benchmark network.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed comments, which have helped us strengthen the manuscript. We agree that a formal derivation of equivalence and additional empirical validation were needed. We have revised the paper by adding a mathematical proof of equivalence in a new subsection, expanding the numerical experiments with accuracy and bias analyses on small instances, and qualifying the equivalence claims with supporting analysis of misclassification risk. All major comments are addressed below.

read point-by-point responses

  1. Referee: [§3] §3 (Method): The central claim that Monte Carlo sample classification against reference states yields the same system-state probabilities as hypercube decomposition is asserted without derivation or proof. No equation demonstrates that the estimator (1/N)∑I(classified state) equals the decomposed probability sum, nor is there a condition guaranteeing that the chosen reference states form a complete boundary (i.e., every sample is assigned its true coherent-system state).

    Authors: We agree that the original manuscript lacked an explicit derivation. In the revised version, we have added a new subsection 3.1.1 that provides the missing proof. We show that, when the reference states form a complete boundary (i.e., the set of all minimal path vectors for each system state), the classification rule based on component-wise comparisons assigns every Monte Carlo sample to its exact coherent-system state. Consequently, the Monte Carlo estimator (1/N)∑I(classified state) is unbiased and equals the probability obtained from the standard hypercube decomposition. We also state the completeness condition explicitly and note that it is the same requirement used by existing reference-state methods. revision: yes

  2. Referee: [§4] §4 (Numerical experiments): Only wall-clock timing is reported for the 119-node graph (under 10 s) and scaling to ~10^5 reference states. No accuracy comparison to exact decomposition on small instances, no bias/variance analysis, and no verification that classification error remains zero when reference states are incomplete or sparse.

    Authors: We acknowledge this gap in the original experiments. We have substantially expanded §4 with new results on small benchmark coherent systems (including the classic bridge system and random 5- to 10-node graphs) for which exact system-state probabilities can be obtained by full enumeration or standard decomposition. We now report mean absolute error, empirical bias (zero when reference states are complete), and variance of the RSR estimator. We also include controlled experiments with deliberately incomplete or sparse reference-state sets to quantify classification error, confirming that error is zero only under the completeness condition derived in §3.1.1. revision: yes

  3. Referee: [Abstract, §3.2] Abstract and §3.2: The statement that RSR is 'equivalent' to existing reference-state methods for probability computation lacks supporting analysis of misclassification risk. The noted slowdown for very large boundary sets is acknowledged but not quantified with respect to reference-state density or completeness.

    Authors: We have revised both the abstract and §3.2 to remove the unqualified claim of equivalence. The text now states that RSR yields probabilistically equivalent results when the reference-state set is complete, with the supporting derivation and completeness condition provided in the new §3.1.1. We have also added quantitative analysis of the slowdown: new figures and tables show runtime scaling as a function of reference-state count and density, together with a discussion of how incompleteness increases misclassification risk and slows convergence. revision: yes

Circularity Check

0 steps flagged

No significant circularity in the RSR derivation

full rationale

The paper presents RSR as a direct computational reformulation of reference-state boundary characterization, replacing hypercube decomposition with Monte Carlo sample classification via batched matrix comparisons. No derivation step reduces a claimed result to its own inputs by construction, nor does any prediction rely on fitted parameters renamed as outputs. The scalability claims rest on the efficiency of matrix operations and the standard equivalence between sample classification and state probabilities under coherent system assumptions, without load-bearing self-citations, ansatzes smuggled via prior work, or uniqueness theorems imported from the authors. The analysis is self-contained against external benchmarks of Monte Carlo reliability methods.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the unstated assumption that reference states sufficiently cover the state-space boundary for accurate classification and that matrix-based comparison introduces no numerical or sampling bias. No free parameters, axioms, or invented entities are explicitly introduced in the abstract.

pith-pipeline@v0.9.0 · 5566 in / 1155 out tokens · 20411 ms · 2026-05-10T06:45:11.436219+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

53 extracted references · 53 canonical work pages

  1. [1]

    J.-E. Byun, J. Song, Generalized matrix-based Bayesian network for multi-state systems, Reliability Engineering & System Safety 211 (2021) 107468

    work page 2021

  2. [2]

    J.-E. Byun, H. Ryu, D. Straub, Branch-and-bound algorithm for efficient reliability analysis of general coherent systems, Structural Safety 118 (2026) 102653

    work page 2026

  3. [3]

    Chang, C.-T

    P.-C. Chang, C.-T. Yeh, T.-Y. Cheng, V. F. Yu, Reliability assessment for multistate semiconductor global logistics networks with freight charges and carbon taxes considerations, Reliability Engineering & System Safety (2025) 112027. 32

    work page 2025

  4. [4]

    Yeh, Novel binary-addition tree algorithm (bat) for binary-state network reliability problem, Reliability Engineering & System Safety 208 (2021) 107448

    W.-C. Yeh, Novel binary-addition tree algorithm (bat) for binary-state network reliability problem, Reliability Engineering & System Safety 208 (2021) 107448

    work page 2021

  5. [5]

    Zhang, L

    L. Zhang, L. Xing, A. Liu, K. Mao, Multivalued decision diagrams-based trust level analysis for social networks, IEEE Access 7 (2019) 180620–180629

    work page 2019

  6. [6]

    Song, W.-H

    J. Song, W.-H. Kang, System reliability and sensitivity under statistical dependence by matrix-based system reliability method, Structural Safety 31 (2009) 148–156

    work page 2009

  7. [7]

    Xu, Y.-f

    B. Xu, Y.-f. Hu, H.-x. Zhang, Y.-p. Zhu, G.-h. Bai, Improved algorithm for d-minimal cuts in reliability evaluation of multi-state flow networks, Reliability Engineering & System Safety (2025) 111707

    work page 2025

  8. [8]

    M. J. Zuo, Z. Tian, H.-Z. Huang, An efficient method for reliability evaluation of multistate networks given all minimal path vectors, IIE Transactions 39 (2007) 811–817

    work page 2007

  9. [9]

    Chang, A path-based simulation approach for multistate flow network reliability estimation without using boundary points, Reliability Engineering & System Safety 249 (2024) 110237

    P.-C. Chang, A path-based simulation approach for multistate flow network reliability estimation without using boundary points, Reliability Engineering & System Safety 249 (2024) 110237

    work page 2024

  10. [10]

    Zhang, G

    S. Zhang, G. Bai, J. Tao, Y. Wang, B. Xu, An algorithm to search for multi-state minimal cuts in multi-state flow networks containing state heterogeneous components, Reliability Engineering & System Safety 256 (2025) 110774

    work page 2025

  11. [11]

    Chen, Y.-K

    S.-G. Chen, Y.-K. Lin, Search for all minimal paths in a general large flow network, IEEE Transactions on Reliability 61 (2012) 949–956

    work page 2012

  12. [12]

    G. Bai, Z. Tian, M. J. Zuo, Reliability evaluation of multistate networks: An improved algorithm using state-space decomposition and experimental comparison, IISE Transactions 50 (2018) 407–418

    work page 2018

  13. [13]

    Lin, C.-F

    Y.-K. Lin, C.-F. Huang, Reliability evaluation of a multi-state network with multiple sinks under individual accuracy rate constraint, Communications in Statistics – Theory and Methods 43 (2014) 4519–4533

    work page 2014

  14. [14]

    Niu, Y.-F

    Y.-F. Niu, Y.-F. Yan, X.-Z. Xu, A new mc-based method for the resource-constrained multi-distribution multi-state flow network reliability optimization problem, Reliability Engineering & System Safety (2025) 111499

    work page 2025

  15. [15]

    Xing, A review of decision diagrams in system reliability modeling and analysis, Applied Mathe- matical Modelling (2025) 116039

    L. Xing, A review of decision diagrams in system reliability modeling and analysis, Applied Mathe- matical Modelling (2025) 116039

    work page 2025

  16. [16]

    Zaitseva, V

    E. Zaitseva, V. Levashenko, Reliability analysis based on aleatory and epistemic uncertainty using binary decision diagrams, International Journal of Intelligent Systems 2025 (2025) 6471577. 33

    work page 2025

  17. [17]

    Zaitseva, V

    E. Zaitseva, V. Levashenko, J. Rabcan, A new method for analysis of multi-state systems based on multi-valued decision diagram under epistemic uncertainty, Reliability Engineering & System Safety 229 (2023) 108868

    work page 2023

  18. [18]

    Y. Mo, F. Zhong, H. Liu, Q. Yang, G.Cui, Efficient ordering heuristicsin binary decision diagram–based fault tree analysis, Quality and Reliability Engineering International 29 (2013) 307–315

    work page 2013

  19. [19]

    P. M. Kozyra, A simulation approach with heuristic rules for reliability estimation of two-terminal multi-state networks based on minimal cuts and parallel computations, Simulation Modelling Practice and Theory 141 (2025) 103095

    work page 2025

  20. [20]

    D.-H. Huang, Network reliability of a stochastic flow network by wrapping linear programming models into a monte-carlo simulation, Reliability Engineering & System Safety 252 (2024) 110427

    work page 2024

  21. [21]

    Chang, Simulation approaches for multi-state network reliability estimation: Practical applica- tions, Simulation Modelling Practice and Theory 115 (2022) 102457

    P.-C. Chang, Simulation approaches for multi-state network reliability estimation: Practical applica- tions, Simulation Modelling Practice and Theory 115 (2022) 102457

    work page 2022

  22. [22]

    Niu, J.-F

    Y.-F. Niu, J.-F. Wang, X.-Z. Xu, Q.-X. Xu, Reliability evaluation for a multi-commodity multi-state distribution network under transportation emission consideration, Reliability Engineering & System Safety 254 (2025) 110599

    work page 2025

  23. [23]

    J. Li, J. He, A recursive decomposition algorithm for network seismic reliability evaluation, Earthquake Engineering & Structural Dynamics 31 (2002) 1525–1539

    work page 2002

  24. [24]

    H.-W. Lim, J. Song, Efficient risk assessment of lifeline networks under spatially correlated ground motions using selective recursive decomposition algorithm, Earthquake Engineering & Structural Dy- namics 41 (2012) 1861–1882

    work page 2012

  25. [25]

    D. Lee, J. Song, Multi-scale seismic reliability assessment of networks by centrality-based selective recursive decomposition algorithm, Earthquake Engineering & Structural Dynamics 50 (2021) 2174– 2194

    work page 2021

  26. [26]

    C. C. Jane, Y. W. Laih, A practical algorithm for computing multi-state two-terminal reliability, IEEE Transactions on reliability 57 (2008) 295–302

    work page 2008

  27. [27]

    T. Liu, J. Liu, G. Bai, J. Zhang, L. Wang, A reliability evaluation method for multi-state flow networks considering network configuration adjustment, Reliability Engineering & System Safety 261 (2025) 111158

    work page 2025

  28. [28]

    M. S. Daly, C. Alexopoulos, State-space partition techniques for multiterminal flows in stochastic networks, Networks: An International Journal 48 (2006) 90–111. 34

    work page 2006

  29. [29]

    L. Xing, An efficient binary-decision-diagram-based approach for network reliability and sensitivity analysis, IEEE Transactions on Systems, Man, and Cybernetics – Part A: Systems and Humans 38 (2007) 105–115

    work page 2007

  30. [30]

    W.-C. Yeh, Novel self-adaptive monte carlo simulation based on binary-addition-tree algorithm for binary-state network reliability approximation, Reliability Engineering & System Safety 228 (2022) 108796

    work page 2022

  31. [31]

    Shrestha, L

    A. Shrestha, L. Xing, Y. Dai, Decision diagram based methods and complexity analysis for multi-state systems, IEEE Transactions on Reliability 59 (2009) 145–161

    work page 2009

  32. [32]

    R. Dong, Y. Zhu, Z. Xu, F. Li, Decision diagram based symbolic algorithm for evaluating the reliability of a multistate flow network, Mathematical Problems in Engineering 2016 (2016) 6908120

    work page 2016

  33. [33]

    B. Wu, L. Sun, A novel layer-by-layer recursive decomposition algorithm for calculation of network reliability, Reliability Engineering & System Safety 244 (2024) 109968

    work page 2024

  34. [34]

    H. Imai, K. Sekine, K. Imai, Computational investigations of all-terminal network reliability via bdds, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences 82 (1999) 714–721

    work page 1999

  35. [35]

    J.-E. Byun, D. Straub, Efficient reliability analysis of coherent systems with discrete-state components, in: Proceedings of the 14th International Conference on Applications of Statistics and Probability in Civil Engineering (ICASP14), Dublin, Ireland, 2023

    work page 2023

  36. [36]

    Lee, J.-E

    D. Lee, J.-E. Byun, J. Song, Dual graph-based Bayesian network modeling with Rao-Blackwellization for seismic reliability and complexity quantification of network connectivity, Earthquake Engineering & Structural Dynamics 54 (2025) 2387–2402

    work page 2025

  37. [37]

    Jiang, M

    C. Jiang, M. Sun, L. Wang, Z. Wang, Y.-F. Li, A recursive algorithm for reliability evaluation of multi- state hierarchical systems with stochastic dependent components, Reliability Engineering & System Safety (2025) 111653

    work page 2025

  38. [38]

    Zwirglmaier, J

    K. Zwirglmaier, J. Chan, I. Papaioannou, J. Song, D. Straub, Hybrid Bayesian networks for reliability assessment of infrastructure systems, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part A: Civil Engineering 10 (2024) 04024019

    work page 2024

  39. [39]

    S. Li, J. Wang, S. He, Connectivity probability evaluation of a large-scale highway bridge network using network decomposition, Reliability Engineering & System Safety 236 (2023) 109191. 35

    work page 2023

  40. [40]

    Herrera, C

    M. Herrera, C. Giudicianni, M. Sasidharan, R. Wright, E. Creaco, A. K. Parlikad, Landmark-node based reliability assessment for critical infrastructure networks, Reliability Engineering & System Safety (2025) 111563

    work page 2025

  41. [41]

    H. Miao, W. Liu, J. Li, Seismic reliability analysis of water distribution networks on the basis of the probability density evolution method, Structural Safety 86 (2020) 101960

    work page 2020

  42. [42]

    W. Liu, Z. Li, Z. Song, J. Li, Seismic reliability evaluation of gas supply networks based on the probability density evolution method, Structural Safety 70 (2018) 21–34

    work page 2018

  43. [43]

    Dueñas-Osorio, M

    L. Dueñas-Osorio, M. Vardi, J. Rojo, Quantum-inspired boolean states for bounding engineering net- work reliability assessment, Structural Safety 75 (2018) 110–118

    work page 2018

  44. [44]

    Vaisman, D

    R. Vaisman, D. P. Kroese, I. B. Gertsbakh, Splitting sequential monte carlo for efficient unreliability estimation of highly reliable networks, Structural Safety 63 (2016) 1–10

    work page 2016

  45. [45]

    K. M. Zuev, S. Wu, J. L. Beck, General network reliability problem and its efficient solution by subset simulation, Probabilistic Engineering Mechanics 40 (2015) 25–35

    work page 2015

  46. [46]

    D. Lee, Z. Wang, J. Song, Efficient seismic reliability and fragility analysis of lifeline networks using subset simulation, Reliability Engineering & System Safety 260 (2025) 110947

    work page 2025

  47. [47]

    J. Chan, I. Papaioannou, D. Straub, Bayesian improved cross entropy method for network reliability assessment, Structural Safety 103 (2023) 102344

    work page 2023

  48. [48]

    J. Chan, I. Papaioannou, D. Straub, Bayesian improved cross entropy method with categorical mixture models for network reliability assessment, Reliability Engineering & System Safety 252 (2024) 110432

    work page 2024

  49. [49]

    Kanjilal, I

    O. Kanjilal, I. Papaioannou, D. Straub, Bayesian updating of reliability by cross entropy-based impor- tance sampling, Structural Safety 102 (2023) 102325

    work page 2023

  50. [50]

    C. H. Huang, D. H. Huang, Y. K. Lin, A novel approach to predict network reliability for multistate networks by a deep neural network, Quality Technology & Quantitative Management 19 (2022) 362–378

    work page 2022

  51. [51]

    C. H. Huang, D. H. Huang, Y. K. Lin, Network reliability prediction for random capacitated-flow networks via an artificial neural network, Reliability Engineering & System Safety 237 (2023) 109378

    work page 2023

  52. [52]

    Huang, Y.-K

    C.-H. Huang, Y.-K. Lin, Manufacturing system evaluation in terms of system reliability via long short- term memory, Reliability Engineering & System Safety 251 (2024) 110365

    work page 2024

  53. [53]

    Y.Shi, J.Behrensdorf, J.Zhou, Y.Hu, M.Broggi, M.Beer, Networkreliabilityanalysisthroughsurvival signature and machine learning techniques, Reliability Engineering & System Safety 242 (2024) 109806. 36

    work page 2024