pith. sign in

arxiv: 2606.12103 · v1 · pith:5QFRC5R7new · submitted 2026-06-10 · 💻 cs.DC

The PM-EdgeMap: Towards Real-Time Process Mining on the Edge-Cloud Continuum

Hendrik Reiter , Christian Imenkamp , Olaf Landsiedel , Andrea Maldonado , Patrick Rathje , Wilhelm Hasselbring This is my paper

Pith reviewed 2026-06-27 08:19 UTC · model grok-4.3

classification 💻 cs.DC
keywords process miningedge computingconformance checkingsmart factoriescyber-physical systemsreal-time analysisedge-cloud continuum
0
0 comments X

The pith

Edge computing supports real-time process mining to guide autonomous factory control.

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

The paper aims to establish that process mining algorithms can run effectively on edge devices close to sensors instead of relying solely on distant cloud servers. It introduces a formalism that captures the structure of event datasets and the edge-cloud network layout. A case study then applies an edge-hosted conformance checking method to test the setup. If the approach holds, factories could generate immediate process insights from ongoing sensor streams and use them for faster local decisions. This directly addresses the need for greater autonomy in cyber-physical production systems.

Core claim

The authors establish the feasibility of real-time process mining on the edge-cloud continuum by defining a formalism that describes relevant datasets and computing topologies, then validating the idea through a case study of an edge-based conformance checking algorithm whose outcomes indicate benefits for enhanced autonomous control in smart factories.

What carries the argument

The formalism for describing relevant datasets and the computing topology, which enables systematic evaluation of edge versus cloud placements for process mining tasks.

Load-bearing premise

That results from a single edge-based conformance checking case study will hold for other process mining tasks and for the range of datasets and network conditions found in actual smart factories.

What would settle it

A direct measurement showing that the edge conformance checking algorithm exceeds acceptable latency bounds when run on representative factory event streams would disprove the feasibility claim.

Figures

Figures reproduced from arXiv: 2606.12103 by Andrea Maldonado, Christian Imenkamp, Hendrik Reiter, Olaf Landsiedel, Patrick Rathje, Wilhelm Hasselbring.

Figure 1
Figure 1. Figure 1: The three process mining topologies differ in computing and communication allocation, with Distributed PM leveraging data sources’ inherent resources. Within the edge-cloud continuum, various topological instantiations [22, 4] exist and each topology comes with specific characteristics: Mobile Cloud Com￾puting (MCC) as shown in Figure 1a refers to mobile devices or sensors of￾floading computationally inten… view at source ↗
Figure 2
Figure 2. Figure 2: Sketch of the algorithm execution for checking the conformance for an incoming event. The invoked node sends requests to other participants to check whether they observed events with the same case id and request their conformance. During the training phase, a significant departure from traditional approaches is observed. Instead of mining a single, global process model, each instance of the algorithm, typi… view at source ↗
read the original abstract

Smart factories are evolving into Cyber-Physical Systems (CPS), demanding increased autonomy. This necessitates real-time decision making, facilitated by insights derived from sensor data. Process mining offers a valuable approach to gain such insights and guide actions. The edge computing paradigm supports this real-time requirement by enabling network communication between sensors and leveraging nearby computing resources. This paper investigates the implications of performing real-time process mining algorithms on the edge. Within this paper, we first propose a formalism to describe relevant datasets and the computing topology. We then evaluate the edge computing approach through a case study involving an edge-based conformance checking algorithm. The results demonstrate the feasibility and benefits of edge-based real-time process mining for enhanced autonomous control in smart factories.

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 / 1 minor

Summary. The manuscript proposes the PM-EdgeMap formalism to describe process mining datasets and edge-cloud computing topologies for Cyber-Physical Systems in smart factories. It then evaluates the approach via a single case study of an edge-based conformance checking algorithm, claiming that the results demonstrate the feasibility and benefits of real-time edge process mining for enhanced autonomous control.

Significance. If the empirical claims hold, the work would address a timely intersection of process mining and edge computing for real-time CPS autonomy. The introduction of a formalism for modeling datasets and topologies is a constructive contribution that could support more systematic future studies in distributed process mining.

major comments (2)
  1. [Abstract / Case Study evaluation] Abstract: the assertion that 'the results demonstrate the feasibility and benefits' is load-bearing for the central claim, yet the provided description of the case study supplies no quantitative metrics (latency, throughput, accuracy, resource usage), error analysis, or explicit edge-vs-cloud baselines, preventing evaluation of whether the data support the feasibility conclusion.
  2. [Case Study] Case Study section: reliance on a single conformance-checking workload leaves the representativeness assumption untested; no additional datasets, topologies, or workload variations are reported to establish that the formalism and edge approach generalize beyond this instance.
minor comments (1)
  1. [Abstract] The abstract could more explicitly separate the contributions of the formalism from those of the empirical case study.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address the major comments point by point below and commit to revisions that strengthen the empirical support and clarify limitations without overstating the current results.

read point-by-point responses

  1. Referee: [Abstract / Case Study evaluation] Abstract: the assertion that 'the results demonstrate the feasibility and benefits' is load-bearing for the central claim, yet the provided description of the case study supplies no quantitative metrics (latency, throughput, accuracy, resource usage), error analysis, or explicit edge-vs-cloud baselines, preventing evaluation of whether the data support the feasibility conclusion.

    Authors: We agree that the abstract claim requires more explicit quantitative backing than is currently detailed in the case study description. The revised manuscript will expand the case study section to report concrete metrics including latency, throughput, accuracy, and resource usage, along with error analysis and direct edge-versus-cloud comparisons drawn from the experiments performed. This will allow readers to evaluate the feasibility conclusion directly from the data. revision: yes

  2. Referee: [Case Study] Case Study section: reliance on a single conformance-checking workload leaves the representativeness assumption untested; no additional datasets, topologies, or workload variations are reported to establish that the formalism and edge approach generalize beyond this instance.

    Authors: We acknowledge the limitation of relying on a single workload for the case study. The PM-EdgeMap formalism itself is workload-agnostic by design, but the evaluation section will be revised to explicitly discuss this scope limitation, justify the choice of conformance checking as a representative real-time CPS task in smart factories, and outline how the formalism can be applied to other workloads and topologies. If additional variations can be incorporated without new experiments, they will be added; otherwise the text will be updated to avoid implying broader generalization than the evidence supports. revision: partial

Circularity Check

0 steps flagged

No circularity: empirical case study with independent formalism and evaluation

full rationale

The paper proposes a formalism for datasets and topologies then evaluates via one conformance-checking case study. No equations, fitted parameters, predictions, or self-citation chains are present that reduce any claim to its own inputs by construction. The central feasibility claim rests on the reported case-study outcomes, which are externally falsifiable and not derived from the formalism itself.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract supplies no information on free parameters, background axioms, or newly postulated entities.

pith-pipeline@v0.9.1-grok · 5662 in / 778 out tokens · 19395 ms · 2026-06-27T08:19:47.348787+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

30 extracted references · 26 canonical work pages

  1. [1]

    van der Aalst, W.M.P.: Process Mining: A 360 Degree Overview, pp. 3—-

  2. [2]

    Novice type error diagnosis with natural language models

    Springer International Publishing (2022). https://doi.org/10.1007/978-3-031- 08848-3_1

    work page doi:10.1007/978-3-031- 2022

  3. [3]

    In: 2021 IEEE International Conference on Smart Data Ser- vices (SMDS)

    van der Aalst, W.M.: Federated process mining: Exploiting event data across orga- nizational boundaries. In: 2021 IEEE International Conference on Smart Data Ser- vices (SMDS). IEEE (Sep 2021). https://doi.org/10.1109/smds53860.2021.00011

    work page doi:10.1109/smds53860.2021.00011 2021

  4. [4]

    Eindhoven University of Technology180 (2002)

    Adan, I., Resing, J.: Queueing theory. Eindhoven University of Technology180 (2002)

    2002

  5. [5]

    Internet of Things27, 101272 (Oct 2024)

    Al-Dulaimy, A., Jansen, M., Johansson, B., Trivedi, A., Iosup, A., Ashjaei, M., Galletta, A., Kimovski, D., Prodan, R., Tserpes, K., Kousiouris, G., Giannakos, C., Brandic, I., Ali, N., Bondi, A.B., Papadopoulos, A.V.: The computing con- tinuum: From iot to the cloud. Internet of Things27, 101272 (Oct 2024). https://doi.org/10.1016/j.iot.2024.101272

    work page doi:10.1016/j.iot.2024.101272 2024

  6. [6]

    Andersen, J., Rathje, P., Imenkamp, C., Koschmider, A., Landsiedel, O.: EdgeMiner: Distributed Process Mining at the Data Sources, p. 705–713. Association for Computing Machinery, New York, NY, USA (2025), https://doi.org/10.1145/3672608.3707873

    work page doi:10.1145/3672608.3707873 2025

  7. [7]

    Andersen, J., Rathje, P., Landsiedel, O.: Check My Flow: Distributed Confor- mance Checking at the Source, p. 101–112. Springer Nature Switzerland (2025). https://doi.org/10.1007/978-3-031-78666-2\_8

    work page doi:10.1007/978-3-031-78666-2 2025

  8. [8]

    Machine Learning and Knowledge Extraction6(1), 283–315 (Feb 2024)

    Arzovs, A., Judvaitis, J., Nesenbergs, K., Selavo, L.: Distributed learning in the iot–edge–cloud continuum. Machine Learning and Knowledge Extraction6(1), 283–315 (Feb 2024). https://doi.org/10.3390/make6010015

    work page doi:10.3390/make6010015 2024

  9. [9]

    Internet of Things13, 100346 (Mar 2021)

    Ashouri, M., Davidsson, P., Spalazzese, R.: Quality attributes in edge computing for the Internet of Things a systematic mapping study. Internet of Things13, 100346 (Mar 2021). https://doi.org/10.1016/j.iot.2020.100346

    work page doi:10.1016/j.iot.2020.100346 2021

  10. [10]

    IEEE Systems Journal18(1), 120–133 (Mar 2024)

    Babayigit, B., Abubaker, M.: Industrial internet of things: A review of improve- ments over traditional scada systems for industrial automation. IEEE Systems Journal18(1), 120–133 (Mar 2024). https://doi.org/10.1109/jsyst.2023.3270620

    work page doi:10.1109/jsyst.2023.3270620 2024

  11. [11]

    The impact of control technology 12(1), 161–166 (2011)

    Baheti, R., Gill, H.: Cyber-physical systems. The impact of control technology 12(1), 161–166 (2011)

    2011

  12. [12]

    Bayar, A., Şener, U., Kayabay, K., Eren, P.E.: Edge Computing Applications in In- dustrial IoT: A Literature Review, p. 124–131. Springer Nature Switzerland (2023). https://doi.org/10.1007/978-3-031-29315-3_11

    work page doi:10.1007/978-3-031-29315-3_11 2023

  13. [13]

    Burattin, A.: Streaming Process Mining, p. 349–372. Springer International Pub- lishing (2022). https://doi.org/10.1007/978-3-031-08848-3_11

    work page doi:10.1007/978-3-031-08848-3_11 2022

  14. [14]

    Burattin, A., van Zelst, S.J., Armas-Cervantes, A., van Dongen, B.F., Carmona, J.: Online Conformance Checking Using Behavioural Patterns, p. 250–267. Springer International Publishing (2018). https://doi.org/10.1007/978-3-319-98648-7_15

    work page doi:10.1007/978-3-319-98648-7_15 2018

  15. [15]

    Chalapathi, G.S.S., Chamola, V., Vaish, A., Buyya, R.: Industrial Inter- net of Things (IIoT) Applications of Edge and Fog Computing: A Review and Future Directions, p. 293–325. Springer International Publishing (2021). https://doi.org/10.1007/978-3-030-57328-7_12

    work page doi:10.1007/978-3-030-57328-7_12 2021

  16. [16]

    IEEE Transactions on Services Computing9(3), 469–481 (May 2016)

    Evermann, J.: Scalable process discovery using map-reduce. IEEE Transactions on Services Computing9(3), 469–481 (May 2016). https://doi.org/10.1109/tsc.2014.2367525

    work page doi:10.1109/tsc.2014.2367525 2016

  17. [17]

    In: 2016 IEEE International Confer- ence on Cloud Computing Technology and Science (CloudCom)

    Evermann, J., Rehse, J.R., Fettke, P.: Process discovery from event stream data in the cloud - a scalable, distributed implementation of the flexible heuristics miner Real-Time Process Mining on the Edge-Cloud Continuum 15 on the amazon kinesis cloud infrastructure. In: 2016 IEEE International Confer- ence on Cloud Computing Technology and Science (CloudC...

    work page doi:10.1109/cloudcom.2016.0111 2016

  18. [18]

    Empirical Software Engineering27(6) (Aug 2022)

    Henning, S., Hasselbring, W.: A configurable method for benchmarking scalability of cloud-native applications. Empirical Software Engineering27(6) (Aug 2022). https://doi.org/10.1007/s10664-022-10162-1

    work page doi:10.1007/s10664-022-10162-1 2022

  19. [19]

    IEEE Systems, Man, and Cybernetics Magazine6(4), 34–44 (Oct 2020)

    Janiesch, C., Koschmider, A., Mecella, M., Weber, B.: The internet of things meets business process management: A manifesto. IEEE Systems, Man, and Cybernetics Magazine6(4), 34–44 (Oct 2020). https://doi.org/10.1109/msmc.2020.3003135

    work page doi:10.1109/msmc.2020.3003135 2020

  20. [20]

    Software: Practice and Experience50(6), 844–867 (Jan 2020)

    Jha, D.N., Alwasel, K., Alshoshan, A., Huang, X., Naha, R.K., Battula, S.K., Garg, S., Puthal, D., James, P., Zomaya, A., Dustdar, S., Ranjan, R.: Iotsim-edge: A simulation framework for modeling the behavior of internet of things and edge computing environments. Software: Practice and Experience50(6), 844–867 (Jan 2020). https://doi.org/10.1002/spe.2787

    work page doi:10.1002/spe.2787 2020

  21. [21]

    In: Proceedings of the Workshop on Fog Computing and the IoT

    Karagiannis, V., Venito, A., Coelho, R., Borkowski, M., Fohler, G.: Edge comput- ing with peer to peer interactions: use cases and impact. In: Proceedings of the Workshop on Fog Computing and the IoT. p. 46–50. CPS-IoT Week ’19, ACM (Apr 2019). https://doi.org/10.1145/3313150.3313226

    work page doi:10.1145/3313150.3313226 2019

  22. [22]

    Computers &; Industrial Engineering149, 106854 (Nov 2020)

    Li, L., Fan, Y., Tse, M., Lin, K.Y.: A review of applications in feder- ated learning. Computers &; Industrial Engineering149, 106854 (Nov 2020). https://doi.org/10.1016/j.cie.2020.106854

    work page doi:10.1016/j.cie.2020.106854 2020

  23. [23]

    Mahmud, R., Kotagiri, R., Buyya, R.: Fog Computing: A Taxonomy, Sur- vey and Future Directions, p. 103–130. Springer Singapore (Oct 2017). https://doi.org/10.1007/978-981-10-5861-5\_5

    work page doi:10.1007/978-981-10-5861-5 2017

  24. [24]

    https://doi.org/10.48550/ARXIV.2209.02702

    Malburg,L.,Grüger,J.,Bergmann,R.:Aniot-enrichedeventlogforprocessmining in smart factories (2022). https://doi.org/10.48550/ARXIV.2209.02702

    work page doi:10.48550/arxiv.2209.02702 2022

  25. [25]

    Technological Forecasting and Social Change190, 122401 (May 2023)

    Qi, Q., Xu, Z., Rani, P.: Big data analytics challenges to implementing the in- telligent industrial internet of things (iiot) systems in sustainable manufacturing operations. Technological Forecasting and Social Change190, 122401 (May 2023). https://doi.org/10.1016/j.techfore.2023.122401

    work page doi:10.1016/j.techfore.2023.122401 2023

  26. [26]

    Information Systems131, 102525 (Jun 2025)

    Rafiei, M., Pourbafrani, M., van der Aalst, W.M.: Federated con- formance checking. Information Systems131, 102525 (Jun 2025). https://doi.org/10.1016/j.is.2025.102525

    work page doi:10.1016/j.is.2025.102525 2025

  27. [27]

    IEEE Access11, 33697–33714 (2023)

    Rafiei, M., Van Der Aalst, W.M.P.: An abstraction-based approach for privacy-aware federated process mining. IEEE Access11, 33697–33714 (2023). https://doi.org/10.1109/access.2023.3263673

    work page doi:10.1109/access.2023.3263673 2023

  28. [28]

    In: ICPM Doctoral Consortium and Demo Track 2024

    Reiter, H., Imenkamp, C., Koschmider, A., Hasselbring, W.: Distributed event fac- tory: A tool for generating event streams on distributed data sources. In: ICPM Doctoral Consortium and Demo Track 2024. Workshop Proceedings (October 2024), https://ceur-ws.org/Vol-3783/paper_323.pdf

    2024

  29. [29]

    Computer50(1), 30–39 (Jan 2017)

    Satyanarayanan, M.: The emergence of edge computing. Computer50(1), 30–39 (Jan 2017). https://doi.org/10.1109/mc.2017.9

    work page doi:10.1109/mc.2017.9 2017

  30. [30]

    IEEE Access10, 100867–100877 (2022)

    Zaidi, S.A.R., Hayajneh, A.M., Hafeez, M., Ahmed, Q.Z.: Unlocking edge intel- ligence through tiny machine learning (tinyml). IEEE Access10, 100867–100877 (2022). https://doi.org/10.1109/access.2022.3207200

    work page doi:10.1109/access.2022.3207200 2022