pith. sign in

arxiv: 2507.08717 · v3 · submitted 2025-07-11 · 💻 cs.NI

Knowledge Graph-Based approach for Sustainable 6G End-to-End System Design

Akshay Jain , Sylvaine Kerboeuf , Sokratis Barmpounakis , Crist\'obal Vinagre Z. , Stefan Wendt , Dinh Thai Bui , Pol Alemany , Riccardo Nicolicchia
show 12 more authors
Jos\'e Mar\'ia Jorquera Valero Dani Korpi Mohammad Hossein Moghaddam Mikko A. Uusitalo Patrik Rugeland Abdelkader Outtagarts Karthik Upadhya Panagiotis Demestichas Raul Mu\~noz Manuel Gil P\'erez Daniel Adanza Ricard Vilalta
This is my paper

Pith reviewed 2026-05-19 05:15 UTC · model grok-4.3

classification 💻 cs.NI
keywords knowledge graph6G system designsustainabilitytechnological enablersend-to-end designkey performance indicatorskey valueskey value indicators
0
0 comments X p. Extension

The pith

Knowledge graphs can select technological enablers for 6G systems by linking performance targets, sustainability indicators, enabler abilities, maturity levels, and dependencies.

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

The paper presents a method that builds a knowledge graph to guide the end-to-end design of 6G networks. The graph takes as inputs the performance demands of a use case, its sustainability requirements expressed as key values and key value indicators, the ability of candidate technologies to meet those demands, their maturity, and the links between them. This matters because earlier cellular generations optimized mainly for speed and latency while 6G must also hit concrete sustainability goals amid dozens of possible technologies. The authors apply the graph to one concrete use case and obtain a set of 82 selected enablers, then supply limited proof-of-concept measurements for a subset of them.

Core claim

The authors argue that encoding use-case KPIs, sustainability key values and indicators, each enabler's capacity to satisfy them, its maturity, and the dependencies among enablers inside a single knowledge graph produces a reproducible way to choose the technologies needed for a sustainable 6G end-to-end system.

What carries the argument

A knowledge graph that records relations among performance targets, sustainability indicators, enabler capabilities, maturity, and inter-enabler dependencies, then uses those relations to select a coherent set of technologies.

If this is right

  • Designers obtain a systematic list of enablers that jointly address both performance and sustainability objectives.
  • Subjective sustainability aspects become traceable through explicit key values and indicators attached to each enabler.
  • Maturity and dependency information reduces the risk of selecting incompatible or immature technologies.
  • The same graph structure can be reused for other use cases by swapping the input requirements.

Where Pith is reading between the lines

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

  • The graph could surface hidden trade-offs between enablers that only appear when sustainability and performance are considered together.
  • Updating the graph with new measurement data would allow designs to evolve as enablers improve or sustainability metrics tighten.
  • The method implies that graph-based reasoning may scale to the full 6G design space where manual comparison becomes impractical.

Load-bearing premise

Sustainability requirements, including subjective social ones, can be turned into well-defined key values and indicators that each technological enabler can be scored against without major bias or missing connections.

What would settle it

Showing that the enablers chosen by the graph for the demonstrated use case fail to meet the stated sustainability targets when implemented together would undermine the method.

Figures

Figures reproduced from arXiv: 2507.08717 by Abdelkader Outtagarts, Akshay Jain, Crist\'obal Vinagre Z., Daniel Adanza, Dani Korpi, Dinh Thai Bui, Jos\'e Mar\'ia Jorquera Valero, Karthik Upadhya, Manuel Gil P\'erez, Mikko A. Uusitalo, Mohammad Hossein Moghaddam, Panagiotis Demestichas, Patrik Rugeland, Pol Alemany, Raul Mu\~noz, Ricard Vilalta, Riccardo Nicolicchia, Sokratis Barmpounakis, Stefan Wendt, Sylvaine Kerboeuf.

Figure 1
Figure 1. Figure 1: FIGURE 1 [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FIGURE 2 [PITH_FULL_IMAGE:figures/full_fig_p008_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIGURE 3 [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIGURE 4 [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: FIGURE 5 [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: FIGURE 6 [PITH_FULL_IMAGE:figures/full_fig_p012_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: FIGURE 7 [PITH_FULL_IMAGE:figures/full_fig_p012_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: FIGURE 8 [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: FIGURE 9 [PITH_FULL_IMAGE:figures/full_fig_p014_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: FIGURE 10 [PITH_FULL_IMAGE:figures/full_fig_p016_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: FIGURE 11 [PITH_FULL_IMAGE:figures/full_fig_p016_11.png] view at source ↗
Figure 13
Figure 13. Figure 13: FIGURE 13 [PITH_FULL_IMAGE:figures/full_fig_p017_13.png] view at source ↗
read the original abstract

Previous generations of cellular communication, such as 5G, have been designed with the objective of improving key performance indicators (KPIs) such as throughput, latency, etc. However, to meet the evolving KPI demands and the ambitious sustainability targets for the Information and Communication Technology (ICT) industry, 6G will need to be designed differently. 6G will need to consider both the performance and sustainability targets for the various use cases it will serve. In addition, 6G will have various candidate technological enablers, making the design space of the system even more complex. Furthermore, due to the subjective nature of sustainability indicators, especially social sustainability, the literature still lacks clear methods to link them with technical enablers and 6G system design. Hence, in this article a novel method for 6G end-to-end (E2E) system design based on Knowledge graphs (KG) has been introduced. It considers as its input: the use case KPIs, use case sustainability requirements expressed as Key Values (KV) and KV Indicators (KVIs), the ability of the technological enablers to satisfy these KPIs and KVIs, the 6G system design principles defined in Hexa-X-II project, the maturity of a technological enabler and the dependencies between the various enablers. The KG method also introduces a novel approach for determining the key values addressed by a technological enabler. The effectiveness of the KG method was demonstrated by its application in designing the 6G E2E system for the cooperating mobile robot use case defined in the Hexa-X-II project, where 82 enablers were selected. Lastly, results from proof-of-concept demonstrations for a subset of the selected enablers have also been provided, which reinforce the efficacy of the KG method for designing a sustainable 6G system.

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 / 1 minor

Summary. The paper introduces a novel knowledge graph-based method for sustainable 6G end-to-end system design. The method integrates use case KPIs, sustainability requirements as Key Values (KVs) and KV Indicators (KVIs), technological enablers' abilities to meet these metrics, Hexa-X-II design principles, enabler maturity, and dependencies among enablers. It features a new technique to determine key values addressed by enablers. Effectiveness is shown via application to the cooperating mobile robot use case, selecting 82 enablers, with accompanying proof-of-concept results for a subset.

Significance. Should the knowledge graph's enabler-to-KVI mappings be shown to be consistent and low-bias, this work could meaningfully advance 6G design by providing a structured, multi-objective framework that explicitly accounts for sustainability alongside performance. It addresses a noted gap in linking subjective social sustainability indicators to technical choices and leverages project-specific principles, offering potential for more holistic and reproducible system designs in future networks.

major comments (3)
  1. [Abstract and method description] The claim that 82 enablers were selected for the cooperating mobile robot use case relies on the KG encoding of enabler abilities to satisfy KVIs. However, the manuscript provides no details on the assessment criteria, numerical scoring, dependency weights, or validation steps (such as expert agreement metrics) used to populate these mappings, particularly for subjective social sustainability KVIs. This undermines the reproducibility of the demonstration and the testability of the sustainability guarantees.
  2. [Proof-of-concept demonstrations] Limited proof-of-concept results are presented to reinforce the method's efficacy, but without quantitative validation metrics, error analysis, or benchmarks against alternative (non-KG) design approaches, the empirical support for the central claim remains weak. The abstract notes these results but does not specify what was measured or how it demonstrates superiority or correctness of the KG-based selection.
  3. [Novel KG approach] The introduction of a novel approach for determining the key values addressed by a technological enabler is highlighted as a contribution. Yet, the specific graph operations, inference rules, or algorithms employed are not described in sufficient detail to allow assessment of their correctness or to distinguish them from standard KG query techniques.
minor comments (1)
  1. [Notation and terminology] Ensure that all acronyms (KPI, KV, KVI, E2E) are defined at first use and consider adding a table summarizing the inputs to the KG for clarity.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback. The comments highlight important areas for improving the manuscript's clarity, reproducibility, and empirical support. We address each major comment below and indicate the revisions we will make.

read point-by-point responses

  1. Referee: [Abstract and method description] The claim that 82 enablers were selected for the cooperating mobile robot use case relies on the KG encoding of enabler abilities to satisfy KVIs. However, the manuscript provides no details on the assessment criteria, numerical scoring, dependency weights, or validation steps (such as expert agreement metrics) used to populate these mappings, particularly for subjective social sustainability KVIs. This undermines the reproducibility of the demonstration and the testability of the sustainability guarantees.

    Authors: We agree that the current manuscript lacks sufficient detail on the specific assessment criteria, scoring, weights, and validation used to populate the enabler-to-KVI mappings. The high-level framework is described, but the concrete steps for handling subjective social sustainability KVIs and ensuring consistency are not elaborated. In the revised version, we will add a dedicated subsection in the methods describing the criteria, any numerical scoring or weighting schemes applied, dependency handling, and validation approaches (such as internal reviews or expert input). This will directly address reproducibility concerns. revision: yes

  2. Referee: [Proof-of-concept demonstrations] Limited proof-of-concept results are presented to reinforce the method's efficacy, but without quantitative validation metrics, error analysis, or benchmarks against alternative (non-KG) design approaches, the empirical support for the central claim remains weak. The abstract notes these results but does not specify what was measured or how it demonstrates superiority or correctness of the KG-based selection.

    Authors: The PoC demonstrations were included primarily to illustrate practical feasibility for a subset of enablers rather than to serve as exhaustive validation. We acknowledge the need for more quantitative support. In revision, we will expand the results section to explicitly state the metrics measured, report available quantitative outcomes and any error analysis performed, and clarify how the outcomes support the KG selection process. While a full benchmark against non-KG methods would require new experiments beyond the current scope, we will add a discussion of this limitation and potential future comparisons. revision: partial

  3. Referee: [Novel KG approach] The introduction of a novel approach for determining the key values addressed by a technological enabler is highlighted as a contribution. Yet, the specific graph operations, inference rules, or algorithms employed are not described in sufficient detail to allow assessment of their correctness or to distinguish them from standard KG query techniques.

    Authors: We will provide a more detailed description of the novel approach in the methods section. This will include the specific graph operations (e.g., traversal patterns and inference mechanisms) used to identify key values addressed by enablers, along with how dependencies, abilities, and Hexa-X-II principles are incorporated. The expanded text will distinguish these from standard KG queries and enable assessment of correctness. revision: yes

Circularity Check

0 steps flagged

No significant circularity; method applies external inputs to construct KG without self-referential reduction

full rationale

The paper introduces a knowledge graph construction that takes as explicit inputs the use case KPIs, sustainability KV/KVIs, enabler abilities, Hexa-X-II design principles, maturity data, and inter-enabler dependencies. The demonstration selects 82 enablers for the cooperating mobile robot use case by applying this construction to those inputs rather than deriving results from fitted parameters, self-defined equations, or predictions that reduce to the inputs by construction. No load-bearing self-citations, uniqueness theorems, or ansatzes are invoked to force the outcome; the central claim is the utility of the KG encoding process itself, which remains open to external validation of the input mappings.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The central claim rests on the ability to encode subjective sustainability values and enabler capabilities as graph relations; no explicit free parameters are introduced in the abstract, but the method implicitly relies on domain assumptions about graph completeness and objective assessment of enabler-KVI links.

axioms (2)
  • domain assumption Sustainability indicators can be expressed as measurable KV and KVIs that technological enablers can be scored against.
    Invoked when the method takes sustainability requirements as input and links them to enablers.
  • domain assumption Dependencies and maturity levels between enablers are known or can be reliably estimated.
    Required for the graph to produce a valid selection of 82 enablers.
invented entities (1)
  • Knowledge graph structure for 6G E2E design no independent evidence
    purpose: To integrate KPIs, KV/KVIs, enabler abilities, maturity, and dependencies into a single queryable model.
    New modeling artifact introduced by the paper; no independent falsifiable evidence provided beyond the single use-case demonstration.

pith-pipeline@v0.9.0 · 5988 in / 1619 out tokens · 18263 ms · 2026-05-19T05:15:38.506297+00:00 · methodology

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

19 extracted references · 19 canonical work pages

  1. [1]

    Hoffmann et al

    M. Hoffmann et al. Hexa-X deliverable: D1.1 6G Vision, use cases and key societal values

    work page

  2. [2]

    Kerboeuf et al

    S. Kerboeuf et al. Design methodology for 6g end-to-end system: Hexa-x-ii perspective. IEEE Open Journal of the Communications Society, 5:3368–3394, 2024

    work page 2024

  3. [3]

    Barmpounakis et al

    S. Barmpounakis et al. Hexa-X-II deliverable: D2.6 Final end-to-end system evaluation results of the overall 6G system design

    work page

  4. [4]

    Recommendation ITU-R M.2160-0: Framework and overall objectives of the future development of IMT for 2030 and beyond

    ITU-R. Recommendation ITU-R M.2160-0: Framework and overall objectives of the future development of IMT for 2030 and beyond

    work page 2030

  5. [5]

    Wendt et al

    S. Wendt et al. Hexa-X-II deliverable: D1.1 Environmental, social, and economic drivers and goals for 6G

    work page

  6. [6]

    Almodovar et al

    J. Almodovar et al. Hexa-X-II deliverable: D1.2 6G Use Cases and Requirements

    work page

  7. [7]

    Porambage et al

    P. Porambage et al. Hexa-X-II deliverable: D2.2 Foundation of overall 6G system design and preliminary evaluation results

    work page

  8. [8]

    Zou et al

    Z. Zou et al. Hexa-X-II deliverable: D2.3 Interim overall 6G system design

    work page

  9. [9]

    Ramos et al

    E. Ramos et al. Hexa-X-II deliverable: D1.4 6G Value, Requirements and Ecosystem

    work page

  10. [10]

    Alemany et al

    P. Alemany et al. Hexa-X-II deliverable: D2.4 End-to-end system evaluation results from the interim overall 6G system

    work page

  11. [11]

    Jain et al

    A. Jain et al. Integrated hexa-x-ii enablers metadata for hexa-x-ii d2.5. Zenodo, 2025

    work page 2025

  12. [12]

    Guiding notes to use the trl self- assessment tool

    APRE and CDTI. Guiding notes to use the trl self- assessment tool

    work page

  13. [13]

    Le Sauze et al

    N. Le Sauze et al. Hexa-X-II deliverable: D2.5 Final overall 6G system design

    work page

  14. [14]

    Korpi, M

    D. Korpi, M. Honkala, and J. M. J. Huttunen. Deep learning-based pilotless spatial multiplexing. In Proc. 57th Asilomar Conference on Signals, Systems, and Computers , pages 1025–1029, October 2023

    work page 2023

  15. [15]

    Nimr et al

    A. Nimr et al. Hexa-X-II deliverable: D4.5 Final Results of 6G Radio Key Enablers

    work page

  16. [16]

    Porambage et al

    P. Porambage et al. Hexa-X-II deliverable: D2.1 Draft foundation for 6G system design

    work page

  17. [17]

    Alemany et al

    P. Alemany et al. Grouping intent-based packet-optical connectivity services. In 49th European Conference on Optical Communications (ECOC 2023), volume 2023, pages 744–747, 2023

    work page 2023

  18. [18]

    Adanza et al

    D. Adanza et al. Intentllm: An ai chatbot to create, find, and explain slice intents in teraflowsdn. In 2024 IEEE 10th International Confer- ence on Network Softwarization (NetSoft) , pages 307–309, 2024

    work page 2024

  19. [19]

    Abadal et al

    S. Abadal et al. Computing graph neural networks: A survey from algorithms to accelerators. ACM Comput. Surv., 54(9), October 2021. 18 VOLUME ,

    work page 2021