pith. sign in

arxiv: 2606.31614 · v1 · pith:GFOLHYD2new · submitted 2026-06-30 · 📡 eess.SY · cs.AI· cs.SY

Automating Cause-Effect Specification with Knowledge Graphs and Large Language Models

Javal Vyas , Milapji Singh Gill , Mehmet Mercang\"oz This is my paper

Pith reviewed 2026-07-01 03:59 UTC · model grok-4.3

classification 📡 eess.SY cs.AIcs.SY
keywords cause-effect matricesknowledge graphslarge language modelsSWRL rulesprocess safetymodular process plantsalarm rationalizationsemantic framework
0
0 comments X

The pith

Combining a knowledge graph with a constrained large language model automates the generation of cause-and-effect specifications.

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

The paper develops a semantic-AI framework that builds a knowledge graph from a modular alignment ontology to capture process structure, operating modes, faults, symptoms, causes, and mitigation actions in machine-interpretable form. A constrained large language model then converts this information into operator-ready safety narratives and SWRL rules while staying within the ontology and vocabulary limits. The workflow is shown on a modular process plant to produce engineering semantics, diagnostic relations, and machine-verifiable specifications. This matters because traditional creation of interlocks, alarm tables, and cause-and-effect matrices remains manual and inconsistency-prone. If the approach works, it grounds generated artifacts directly in the semantic model rather than free-form documents.

Core claim

The paper claims that a knowledge graph built on an established modular alignment ontology, when paired with a constrained large language model, can transform represented process information into machine-verifiable SWRL rules and safety narratives, as shown in the generation of C&E logic for a modular process plant with less manual intervention than conventional document-driven approaches.

What carries the argument

The semantic-AI framework that combines a knowledge graph representing process structure, faults, symptoms, causes, and mitigation actions with a constrained LLM layer for transforming information into SWRL rules and narratives under strict ontology and vocabulary constraints.

If this is right

  • Interlocks, alarm rationalization tables, and cause-and-effect matrices can be produced directly from the unified knowledge representation.
  • Diagnostic relations and mitigation actions become expressible as machine-verifiable SWRL rules.
  • Generated specifications remain grounded in the semantic model, supporting consistency across artifacts.
  • The demonstrated workflow on a modular process plant indicates the method can reduce manual effort for similar structured systems.

Where Pith is reading between the lines

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

  • If the same ontology can be populated from plant design files, the framework could generate initial safety documentation at the start of a project rather than after design completion.
  • Adding sensor or historian data to the knowledge graph might let the same constrained LLM produce updated cause-effect logic when process conditions change.
  • The approach could be tested on non-modular plants by relaxing the ontology constraints and measuring the increase in required corrections.

Load-bearing premise

The established modular alignment ontology is assumed to be complete enough to represent all relevant process structure, faults, symptoms, causes, and mitigation actions so that the constrained LLM can reliably produce correct SWRL rules and narratives without additional human correction.

What would settle it

Apply the workflow to a new modular process plant, then compare the generated SWRL rules and narratives against independently created expert versions and count how many require human correction before they are correct.

Figures

Figures reproduced from arXiv: 2606.31614 by Javal Vyas, Mehmet Mercang\"oz, Milapji Singh Gill.

Figure 1
Figure 1. Figure 1: Overview of the proposed C&E extraction pipeline. [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Reused alignment ontology showing how process, structural, behavioural, condition, and diagnostic concepts are [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Modular process plant used as the case study in this [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
read the original abstract

Engineering specifications such as interlocks, alarm rationalization tables, and cause-and-effect (C&E) matrices remain central to process control and safety, yet their creation is still predominantly manual, document-driven, and prone to inconsistency. This paper presents a semantic-AI framework that automates the generation of C&E logic by combining a knowledge graph (KG) with a constrained large language model (LLM) layer. The KG builds on an established modular alignment ontology to represent process structure, operating modes, faults, symptoms, causes, and mitigation actions in a machine-interpretable form. The LLM then transforms this information into operator-ready safety narratives and Semantic Web Rule Language (SWRL) rules under strict ontology and vocabulary constraints, grounding the generated artifacts in the underlying semantic model. The workflow is demonstrated on a modular process plant, showing how engineering semantics, diagnostic relations, and machine-verifiable specifications can be generated from a unified knowledge representation with reduced manual effort.

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 presents a semantic-AI framework for automating cause-and-effect (C&E) specification in process control and safety. It combines a knowledge graph built on an established modular alignment ontology (representing process structure, operating modes, faults, symptoms, causes, and mitigation actions) with a constrained large language model to generate operator-ready safety narratives and SWRL rules. The workflow is demonstrated on a modular process plant, with the central claim being generation of engineering semantics, diagnostic relations, and machine-verifiable specifications from a unified representation with reduced manual effort.

Significance. If the claims hold with validation, the framework could meaningfully reduce manual effort and inconsistency in creating safety-critical documents such as interlocks and alarm rationalization tables. The grounding in an existing ontology and use of constrained LLM generation are positive elements that support reproducibility and verifiability. However, the current presentation supplies no quantitative evidence, limiting assessment of real-world significance.

major comments (2)
  1. [Demonstration] Demonstration section: the workflow is described as producing SWRL rules and narratives on a modular process plant, but no details are supplied on constraint enforcement during LLM generation, validation of the generated rules against actual plant behavior, error rates, or any comparison to manual baselines. This directly undermines the central claim of reliable automation with reduced manual effort.
  2. [Framework description] Ontology and LLM layer: the framework assumes the modular alignment ontology is complete enough to represent all relevant process elements so that the constrained LLM produces correct outputs without human correction, yet no test of this assumption, coverage analysis, or failure cases is reported.
minor comments (1)
  1. [Abstract] Abstract: adding one or two concrete outcomes (e.g., number of rules generated or qualitative observations from the plant demonstration) would strengthen the summary of results.

Simulated Author's Rebuttal

2 responses · 1 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below, clarifying the scope of the demonstration and proposing targeted revisions where the presentation can be strengthened without misrepresenting the work.

read point-by-point responses

  1. Referee: [Demonstration] Demonstration section: the workflow is described as producing SWRL rules and narratives on a modular process plant, but no details are supplied on constraint enforcement during LLM generation, validation of the generated rules against actual plant behavior, error rates, or any comparison to manual baselines. This directly undermines the central claim of reliable automation with reduced manual effort.

    Authors: The demonstration illustrates the workflow on a modular process plant example, showing generation of narratives and SWRL rules from the knowledge graph under ontology constraints. We agree that the manuscript would benefit from expanded description of the constraint mechanisms (e.g., vocabulary-restricted prompting and ontology grounding). We will revise the demonstration section to provide these details and to qualify the claim of reduced manual effort as illustrative of the approach rather than a quantified result. Quantitative validation against plant behavior, error rates, and baseline comparisons were not part of the reported study. revision: partial

  2. Referee: [Framework description] Ontology and LLM layer: the framework assumes the modular alignment ontology is complete enough to represent all relevant process elements so that the constrained LLM produces correct outputs without human correction, yet no test of this assumption, coverage analysis, or failure cases is reported.

    Authors: The framework employs an established modular alignment ontology and demonstrates its use for the selected process elements without requiring post-generation correction in the example. We acknowledge that an explicit discussion of coverage and potential failure modes is absent. We will add a limitations subsection addressing the ontology assumptions and scenarios where additional human oversight may be needed. revision: yes

standing simulated objections not resolved
  • Quantitative metrics including error rates, validation against actual plant behavior, and comparisons to manual baselines, as these were not collected or reported in the original work.

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper describes a semantic-AI framework that composes an existing modular alignment ontology into a knowledge graph, then applies a constrained LLM to generate SWRL rules and narratives. No equations, fitted parameters, derivations, or self-citation chains appear in the abstract or described workflow. The demonstration on a modular process plant is presented as an application rather than a self-referential prediction or definition. The central claim therefore remains a composition of independent components with no load-bearing step that reduces to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Review performed on abstract only; full methods, data, and validation details unavailable, so ledger entries are limited to what is stated in the abstract.

axioms (1)
  • domain assumption An established modular alignment ontology exists and is sufficient to represent process structure, operating modes, faults, symptoms, causes, and mitigation actions in machine-interpretable form.
    Paper states it builds on this ontology without providing independent verification or completeness arguments.

pith-pipeline@v0.9.1-grok · 5704 in / 1326 out tokens · 50997 ms · 2026-07-01T03:59:20.239375+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

58 extracted references · 17 canonical work pages

  1. [1]

    Model-based analysis of the feasibility envelope for autonomous operation of a portable direct methanol fuel-cell system , keywords =

    Zenith, Federico and Weinzierl, Christine and Krewer, Ulrike , year =. Model-based analysis of the feasibility envelope for autonomous operation of a portable direct methanol fuel-cell system , keywords =. Chemical Engineering Science , shorthand =. doi:10.1016/j.ces.2010.03.055 , number =

    work page doi:10.1016/j.ces.2010.03.055 2010

  2. [2]

    2016 , title =

    Annual Reviews in Control , shorthand =. 2016 , title =. doi:10.1016/j.arcontrol.2016.09.015 , abstract =

    work page doi:10.1016/j.arcontrol.2016.09.015 2016

  3. [3]

    Mani , year =

    Alhazmi, Khalid and Albalawi, Fahad and Sarathy, S. Mani , year =. A reinforcement learning-based economic model predictive control framework for autonomous operation of chemical reactors , keywords =. Chemical Engineering Journal , shorthand =. doi:10.1016/j.cej.2021.130993 , abstract =

    work page doi:10.1016/j.cej.2021.130993 2021

  4. [4]

    CEAS Aeronautical Journal , doi =

    Gill, Milapji Singh and Fay, Alexander , year =. CEAS Aeronautical Journal , doi =

  5. [5]

    , year =

    Meng, Lexuan and Dragicevic, Tomislav and Guerrero, Josep M. , year =. Adaptive Control Design for Autonomous Operation of Multiple Energy Storage Systems in Power Smoothing Applications , pages =. IEEE Transactions on Industrial Electronics , shortjournal =. doi:10.1109/TIE.2017.2756584 , number =

    work page doi:10.1109/tie.2017.2756584 2017

  6. [6]

    2025 , doi =

    Gill, Milapji Singh and Jeleniewski, Tom and Gehlhoff, Felix and Fay, Alexander , title =. 2025 , doi =

    2025

  7. [7]

    Distributed Control Strategy for Autonomous Operation of Hybrid AC/DC Microgrid , keywords =

    Baek, Jongbok and Choi, Wooin and Chae, Suyong , year =. Distributed Control Strategy for Autonomous Operation of Hybrid AC/DC Microgrid , keywords =. Energies , shorthand =. doi:10.3390/en10030373 , number =

    work page doi:10.3390/en10030373

  8. [8]

    2021 5th International Conference on System Reliability and Safety (ICSRS) , year =

    Lee, Daeil and Kim, Hyojin and Choi, Younhee and Kim, Jonghyun , title =. 2021 5th International Conference on System Reliability and Safety (ICSRS) , year =. doi:10.1109/ICSRS53853.2021.9660722 , shorthand =

    work page doi:10.1109/icsrs53853.2021.9660722 2021

  9. [9]

    and Craig, Ian K

    Olivier, Laurentz E. and Craig, Ian K. , year =. Model-based fault-tolerant control with robustness to unanticipated faults , pages =. IFAC-PapersOnLine , shorthand =. doi:10.1016/j.ifacol.2017.08.401 , number =

    work page doi:10.1016/j.ifacol.2017.08.401 2017

  10. [10]

    Manee and R

    V. Manee and R. Baratti and J. Romagnoli , title =. Chemical Engineering Research and Design , volume =. 2022 , url =

    2022

  11. [11]

    TechRxiv Preprint , year =

    Georgi Tancev , title =. TechRxiv Preprint , year =

  12. [12]

    Xun Tang and Yuhe Tian and V. S. D. , title =. Processes , publisher =. 2024 , url =

    2024

  13. [13]

    Control-Informed Reinforcement Learning for Chemical Processes , journal =

    Maximilian Bloor and Akhil Ahmed and Niki Kotecha and Mehmet Mercang. Control-Informed Reinforcement Learning for Chemical Processes , journal =. 2024 , url =

    2024

  14. [14]

    Kwon , title =

    Niranjan Sitapure and Joseph S. Kwon , title =. arXiv preprint , year =

  15. [15]

    2023 IEEE 49th IECON , year =

    Westermann, Tom and Gill, Milapji Singh and Fay, Alexander , title =. 2023 IEEE 49th IECON , year =. doi:10.1109/IECON51785.2023.10312156 , file =

    work page doi:10.1109/iecon51785.2023.10312156 2023

  16. [16]

    2023 IEEE 28th ETFA , year =

    Gill, Milapji Singh and Westermann, Tom and Schieseck, Marvin and Fay, Alexander , title =. 2023 IEEE 28th ETFA , year =. doi:10.1109/ETFA54631.2023.10275612 , file =

    work page doi:10.1109/etfa54631.2023.10275612 2023

  17. [17]

    2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), 2024 , year =

    Gill, Milapji Singh and Westermann, Tom and Steindl, Gernot and Gehlhoff, Felix and Fay, Alexander , title =. 2024 IEEE 29th ETFA , year =. doi:10.1109/ETFA61755.2024.10710898 , file =

    work page doi:10.1109/etfa61755.2024.10710898 2024

  18. [18]

    Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice , publisher =

    Fakih, Mohamad and Dharmaji, Rahul and Moghaddas, Yasamin and Quiros, Gustavo and Ogundare, Oluwatosin and Al Faruque, Mohammad Abdullah , year =. Proceedings of the 46th International Conference on Software Engineering: Software Engineering in Practice , publisher =

  19. [19]

    2023 , copyright =

    Pre-Trained Large Language Models for Industrial Control , publisher =. 2023 , copyright =. doi:10.48550/ARXIV.2308.03028 , author =

    work page doi:10.48550/arxiv.2308.03028 2023

  20. [20]

    LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems , url =

    Fakih, Mohamad and Dharmaji, Rahul and Moghaddas, Yasamin and Quiros, Gustavo and Ogundare, Oluwatosin and Al Faruque, Mohammad Abdullah , year =. LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems , url =. doi:10.1145/3639477.3639743 , booktitle =

    work page doi:10.1145/3639477.3639743

  21. [21]

    2026 , volume=

    Liu, Zihan and Zeng, Ruinan and Wang, Dongxia and Peng, Gengyun and Liu, Xiaoxia and Liu, Qiang and Liu, Peiyu and Wang, Wenhai and Wang, Jingyi , journal=. 2026 , volume=

    2026

  22. [22]

    2024 , copyright =

    Control Industrial Automation System with Large Language Models , publisher =. 2024 , copyright =. doi:10.48550/ARXIV.2409.18009 , author =

    work page doi:10.48550/arxiv.2409.18009 2024

  23. [23]

    Towards autonomous system: flexible modular production system enhanced with large language model agents , year=

    Xia, Yuchen and Shenoy, Manthan and Jazdi, Nasser and Weyrich, Michael , booktitle=. Towards autonomous system: flexible modular production system enhanced with large language model agents , year=

  24. [24]

    2024 , eprint=

    ControlAgent: Automating Control System Design via Novel Integration of LLM Agents and Domain Expertise , author=. 2024 , eprint=

    2024

  25. [25]

    Proceedings of the 1st International Workshop on Designing and Building Hybrid Human--AI Systems (SYNERGY 2024) , volume=

    Towards an llm-based intelligent assistant for industry 5.0 , author=. Proceedings of the 1st International Workshop on Designing and Building Hybrid Human--AI Systems (SYNERGY 2024) , volume=

    2024

  26. [26]

    Resiliency Analysis of LLM generated models for Industrial Automation , year=

    Ogundare, Oluwatosin and Araya, Gustavo Quiros and Akrotirianakis, Ioannis and Shukla, Ankit , booktitle=. Resiliency Analysis of LLM generated models for Industrial Automation , year=

  27. [27]

    2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA) , year =

    An. 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA) , year =

    2022

  28. [28]

    Tao, Laifa and Huang, Qixuan and Wu, Xianjun and Zhang, Weiwei and Wu, Yunlong and Li, Bin and Lu, Chen and Hai, Xingshuo , date =

  29. [29]

    , title =

    Balhorn, Lukas Schulze and Caballero, Marc and Schweidtmann, Artur M. , title =. 2024 , doi =

    2024

  30. [30]

    2026 , issn =

    Multi-agent systems for chemical engineering: a review and perspective , journal =. 2026 , issn =. doi:https://doi.org/10.1016/j.coche.2025.101209 , author =

    work page doi:10.1016/j.coche.2025.101209 2026

  31. [31]

    2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), 2024 , year =

    Xia, Yuchen and Jazdi, Nasser and Weyrich, Michael , title =. 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA), 2024 , year =. doi:10.1109/ETFA61755.2024.10710996 , file =

    work page doi:10.1109/etfa61755.2024.10710996 2024

  32. [32]

    and Wagner, Lukas P

    Reinpold, Lasse M. and Wagner, Lukas P. and Gehlhoff, Felix and Ramonat, Malte and Kilthau, Maximilian and Gill, Milapji S. and Reif, Jonathan T. and Henkel, Vincent and Scholz, Lena and Fay, Alexander , year =. Journal of Intelligent Manufacturing , doi =

  33. [33]

    Digital Twin in manufacturing: A categorical literature review and classification , pages =

    Kritzinger, Werner and Karner, Matthias and Traar, Georg and Henjes, Jan and Sihn, Wilfried , year =. Digital Twin in manufacturing: A categorical literature review and classification , pages =

  34. [34]

    Tao, Fei and Zhang, He and Liu, Ang and Nee, A. Y. C. , year =. IEEE Transactions on Industrial Informatics , doi =

  35. [35]

    , year =

    Thambirajah, Jegatheeswaran and Benabbas, Lamia and Bauer, Margret and Thornhill, Nina F. , year =

  36. [36]

    2024 , title =

    Markaj, Artan and Mercang. 2024 , title =

    2024

  37. [37]

    2025 , volume=

    Gill, Milapji Singh and Vyas, Javal and Markaj, Artan and Gehlhoff, Felix and Mercangöz, Mehmet , booktitle=. 2025 , volume=

    2025

  38. [38]

    Gill, Milapji Singh and Jeleniewski, Tom and Gehlhoff, Felix and Fay, Alexander , year =

  39. [39]

    , year =

    Rupprecht, Sophia and Gao, Qinghe and Karia, Tanuj and Schweidtmann, Artur M. , year =

  40. [40]

    Lee, Donghyeon and Lee, Jaewook and Shin, Dongil , year =

  41. [41]

    Gowaikar, Shreeyash and Iyengar, Srinivasan and Segal, Sameer and Kalyanaraman, Shivkumar , year =

  42. [42]

    2024 , title =

    Sakhinana, Sagar Srinivas and. 2024 , title =. doi:10.1609/aaaiss.v4i1.31796 , file =

    work page doi:10.1609/aaaiss.v4i1.31796 2024

  43. [43]

    2025 , title =

    Vyas, Javal and Mercang. 2025 , title =

    2025

  44. [44]

    2025 , doi =

    Pajak, Emma and Bahamdan, Abdullah and Hellgardt, Klaus and Ro-Chanona, Antoniodel , title =. 2025 , doi =

    2025

  45. [45]

    Driess, Danny and Xia, Fei and Sajjadi, Mehdi S. M. and Lynch, Corey and Chowdhery, Aakanksha and Ichter, Brian and Wahid, Ayzaan and Tompson, Jonathan and Vuong, Quan and Yu, Tianhe and Huang, Wenlong and Chebotar, Yevgen and Sermanet, Pierre and Duckworth, Daniel and Levine, Sergey and Vanhoucke, Vincent and Hausman, Karol and Toussaint, Marc and Greff,...

  46. [46]

    2022 , title =

    Webert, Heiko and D. 2022 , title =. doi:10.3390/s22062205 , file =

    work page doi:10.3390/s22062205 2022

  47. [47]

    Manca, Gianluca and Fay, Alexander , year =

  48. [48]

    2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA) , year =

    Gill, Milapji Singh and Reiche, Leif-Thore and Fay, Alexander , title =. 2022 IEEE 27th International Conference on Emerging Technologies and Factory Automation (ETFA) , year =

    2022

  49. [49]

    and Caesar, Birte and Gundlach, Claas Steffen and Fay, Alexander , year =

    Hildebrandt, Constantin and Köcher, Aljosha and Kustner, Christof and Lopez-Enriquez, Carlos-Manuel and Muller, Andreas W. and Caesar, Birte and Gundlach, Claas Steffen and Fay, Alexander , year =. IEEE T-ASE , doi =

  50. [50]

    and Schmidt,J

    Single,J. and Schmidt,J. and Denecke,J. , year =

  51. [51]

    Laurenzi, Emanuele and Mathys, Adrian and Martin, Andreas , year =

  52. [52]

    2024 , volume=

    Soularidis, Andreas and Kotis, Konstantinos and Lamolle, Myriam and Mejdoul, Zakaria and Lortal, Gaëlle and Vouros, George , booktitle=. 2024 , volume=

    2024

  53. [53]

    2020 , title =

    17th International Conference on Accelerator and Large Experimental Physics Control Systems. 2020 , title =

    2020

  54. [54]

    I. de Zarz. Sensors , volume =. 2023 , doi =

    2023

  55. [55]

    2025 , volume=

    Xia, Yuchen and Jazdi, Nasser and Zhang, Jize and Shah, Chaitanya and Weyrich, Michael , booktitle=. 2025 , volume=

    2025

  56. [56]

    and Maleh, Y

    Lamaakal, I. and Maleh, Y. and. 2025 , title =

    2025

  57. [57]

    2023 , title =

    de Zarz. 2023 , title =

    2023

  58. [58]

    Control Industrial Automation System with Large Language Model Agents , year=

    Xia, Yuchen and Jazdi, Nasser and Zhang, Jize and Shah, Chaitanya and Weyrich, Michael , booktitle=. Control Industrial Automation System with Large Language Model Agents , year=