pith. sign in

arxiv: 2606.26927 · v1 · pith:OBUR5VM5new · submitted 2026-06-25 · 💻 cs.SE

Are LLMs Ready for Anti-Pattern Detection in Microservice Architectures?

Marco De Luca , Domenico Amalfitano , Porfirio Tramontana , Anna Rita Fasolino This is my paper

Pith reviewed 2026-06-26 03:49 UTC · model grok-4.3

classification 💻 cs.SE
keywords microservice architecturesanti-pattern detectionlarge language modelsprompt-based analysisstatic analysisarchitectural assessmentsoftware maintainabilityprecision and recall
0
0 comments X

The pith

LLMs provide competitive support for detecting several microservice anti-patterns but fall short where explicit structural or cross-service evidence is needed.

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

The paper tests whether large language models can detect architectural anti-patterns in microservice systems through prompt-based analysis of static repository files. It runs three general-purpose models on a benchmark of repositories labeled with 16 anti-patterns and compares results to a static-analysis baseline using the same precision and recall measures. LLMs match or approach the baseline on patterns whose evidence is local, mixed, or semantic, yet they miss patterns that hinge on explicit structure or dependencies across services. If correct, this means prompt-based LLM checks could serve as a flexible supplement that adapts to varied code without new hand-written rules, while static methods stay necessary for dependency-heavy cases.

Core claim

The paper establishes that LLMs deliver useful support for anti-pattern detection in microservice architectures via prompt-based analysis of static artifacts, reaching competitive precision and recall on several of the 16 patterns when evidence is local, heterogeneous, or semantically rich, while showing clear shortfalls on patterns that demand explicit structural or cross-service dependency information where static analysis stays more reliable.

What carries the argument

Prompt-based analysis pipeline that feeds static repository artifacts to LLMs and measures output against a static-analysis baseline using uniform precision and recall on the 16 annotated anti-patterns.

If this is right

  • Hybrid detection that routes semantic-heavy patterns to LLMs and structural patterns to static tools would cover more cases than either alone.
  • Prompt-based LLM checks can be applied to new or heterogeneous repositories without writing additional detection rules.
  • Performance gaps on cross-service patterns indicate that LLM outputs would benefit from explicit structural context supplied in the prompt.
  • Maintainability assessments for microservices could incorporate LLM scans as a first-pass filter before targeted static verification.

Where Pith is reading between the lines

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

  • A combined system might first let an LLM flag candidate anti-patterns and then run static analysis only on the flagged services to reduce overall computation.
  • The same prompt pipeline could be tested on other kinds of architectural smells that mix code-level and configuration-level signals.
  • If prompts were expanded with dependency graphs extracted by lightweight parsers, the LLM gap on structural patterns might narrow without changing the model.
  • Repository-scale evaluation could reveal whether LLMs generalize across different microservice frameworks or primarily succeed on the styles present in the current benchmark.

Load-bearing premise

The chosen set of annotated microservice repositories and the single uniform precision-recall protocol give a representative and fair comparison between the LLM approach and static analysis.

What would settle it

Running the same LLMs on a fresh collection of microservice repositories where the anti-patterns with structural dependencies appear more often and the LLMs still score higher than the static baseline on those patterns.

Figures

Figures reproduced from arXiv: 2606.26927 by Anna Rita Fasolino, Domenico Amalfitano, Marco De Luca, Porfirio Tramontana.

Figure 1
Figure 1. Figure 1: provides an overview of the experimental procedure pipeline. Repository Flattening MARS Execution LLM -Based AP Detection LLM Detected APs Data Analysis Data Analysis Repository Results for RQ2 Results for RQ1 Ground Truth Flattened Repository MARS detected APs AP-specific detection prompt [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Instance of the parametric AP-detection prompt for [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
read the original abstract

Microservice systems are prone to recurrent architectural anti-patterns (APs) that hinder maintainability, evolvability, and operational quality. Most existing AP detection approaches rely on static analysis and handcrafted rules, which can be effective but are often tool-dependent, limited to explicitly encoded detection logic, and difficult to adapt to heterogeneous repositories. In this paper, we investigate whether large language models (LLMs) are ready to support architectural anti-pattern detection in microservice architectures through a prompt-based analysis pipeline over static repository artifacts. We evaluate three general-purpose LLMs on a curated benchmark of microservice repositories annotated with 16 architectural anti-patterns, and compare their performance against the state-of-the-art static-analysis tool MARS using a uniform evaluation protocol based on precision and recall. Our results show that LLMs can provide useful support for anti-pattern detection, achieving competitive performance on several anti-patterns, especially when the relevant evidence is local, heterogeneous, or semantically rich. At the same time, they exhibit clear limitations on anti-patterns that require explicit structural or cross-service dependency evidence, where static analysis remains more reliable. These findings suggest that LLMs are not yet a replacement for traditional analyzers, but already represent a promising complementary aid for architectural assessment in microservice systems.

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

1 major / 0 minor

Summary. The paper investigates whether LLMs can support architectural anti-pattern detection in microservice systems via a prompt-based analysis pipeline on static repository artifacts. It evaluates three general-purpose LLMs against the static-analysis tool MARS on a curated benchmark annotated with 16 anti-patterns, using a uniform precision/recall protocol, and concludes that LLMs achieve competitive performance on anti-patterns with local, heterogeneous, or semantically rich evidence but show clear limitations on those requiring explicit structural or cross-service dependency evidence, positioning LLMs as a promising complementary aid rather than a replacement.

Significance. If the empirical results hold under a validated protocol, the work provides concrete evidence on the strengths and limitations of prompt-based LLMs for software architecture analysis tasks. It identifies specific conditions (local vs. structural evidence) where LLMs add value over rule-based tools and vice versa, which can inform the design of hybrid detection systems and guide practitioners in microservice maintenance. The comparison on a multi-AP benchmark contributes empirical data to the AI-for-SE literature.

major comments (1)
  1. [Evaluation protocol (as described in the abstract and results sections)] The central claim of 'competitive performance on several anti-patterns' under a 'uniform evaluation protocol based on precision and recall' is load-bearing for the paper's conclusions, yet the protocol requires mapping LLM free-form responses to binary detections. This introduces an interpretation step absent from MARS's deterministic rule-based outputs, making direct comparability sensitive to unstated choices in annotation or tie-breaking. Details on this mapping (e.g., manual vs. automated, prompt-dependent rules) must be provided to substantiate the head-to-head results.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive comment on the evaluation protocol. We address the concern directly below.

read point-by-point responses

  1. Referee: [Evaluation protocol (as described in the abstract and results sections)] The central claim of 'competitive performance on several anti-patterns' under a 'uniform evaluation protocol based on precision and recall' is load-bearing for the paper's conclusions, yet the protocol requires mapping LLM free-form responses to binary detections. This introduces an interpretation step absent from MARS's deterministic rule-based outputs, making direct comparability sensitive to unstated choices in annotation or tie-breaking. Details on this mapping (e.g., manual vs. automated, prompt-dependent rules) must be provided to substantiate the head-to-head results.

    Authors: We agree that the manuscript would benefit from greater transparency on the mapping from LLM free-form responses to binary detections. While the protocol is uniform in applying identical precision and recall metrics to both LLM and MARS outputs against the same ground-truth annotations, the interpretation step for LLMs is an additional element that requires explicit description. In the revised manuscript we will expand the Evaluation Protocol section to document the mapping procedure, including whether it was manual or automated, the guidelines or rubric applied, and how ambiguities were resolved. revision: yes

Circularity Check

0 steps flagged

Empirical evaluation with no derivations, fitted predictions, or load-bearing self-citations

full rationale

The paper conducts a direct empirical comparison of three LLMs against the external static-analysis tool MARS on a curated benchmark of 16 anti-patterns, reporting precision and recall under a uniform protocol. No equations, parameter fitting, predictions derived from inputs, or self-citation chains appear in the abstract or described methodology. The central claims rest on measured performance numbers against an independent tool and benchmark, not on any reduction to the paper's own definitions or prior author work. This matches the default expectation for non-circular empirical studies.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is an empirical benchmarking study; no free parameters are fitted, no new axioms are introduced, and no new entities are postulated.

pith-pipeline@v0.9.1-grok · 5766 in / 1099 out tokens · 42306 ms · 2026-06-26T03:49:03.002992+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

56 extracted references · 7 canonical work pages

  1. [1]

    On the maintenance support for microservice-based systems through the specification and the detection of microservice antipatterns,

    R. Tighilt, M. Abdellatif, I. Trabelsi, L. Madern, N. Moha, and Y .-G. Gu´eh´eneuc, “On the maintenance support for microservice-based systems through the specification and the detection of microservice antipatterns,” J. Syst. Softw., vol. 204, no. C, Oct. 2023. [Online]. Available: https://doi.org/10.1016/j.jss.2023.111755

    work page doi:10.1016/j.jss.2023.111755 2023

  2. [2]

    Automated code-smell detection in microservices through static analysis: A case study,

    A. Walker, D. Das, and T. Cerny, “Automated code-smell detection in microservices through static analysis: A case study,” Applied Sciences, vol. 10, no. 21, p. 7800, 2020

    2020

  3. [3]

    Fowler, K

    M. Fowler, K. Beck, J. Brant, W. Opdyke, and E. Roberts, Refactoring: Improving the design of existing code. Addison-Wesley, 1999

    1999

  4. [4]

    W. J. Brown, R. C. Malveau, H. W. McCormick III, and T. J. Mowbray, AntiPatterns: Refactoring Software, Architectures, and Projects in Crisis. Wiley, 1998

    1998

  5. [5]

    Microservices anti-patterns: A taxonomy,

    D. Taibi, V . Lenarduzzi, and C. Pahl, “Microservices anti-patterns: A taxonomy,” in Microservices: Science and Engineering. Springer International Publishing, 2020, pp. 111–128

    2020

  6. [6]

    On the study of microservices antipatterns: a catalog proposal,

    R. Tighilt, M. Abdellatif, N. Moha, H. Mili, G. E. Boussaidi, J. Privat, and Y .-G. Gu´eh´eneuc, “On the study of microservices antipatterns: a catalog proposal,” in Proceedings of the European Conference on Pattern Languages of Programs 2020, ser. EuroPLoP ’20. Association for Computing Machinery, 2020

    2020

  7. [7]

    Flexible educational software architecture: at the example of eas.lit 2,

    R. Meissner and A. Thor, “Flexible educational software architecture: at the example of eas.lit 2,” in International Workshop on Intelligent Mentoring in Higher Education (IMHE), 2020. [Online]. Available: https://ceur-ws.org/V ol-3046/imhe 2020 paper 2.pdf

    2020

  8. [8]

    On the definition of microservice bad smells,

    D. Taibi and V . Lenarduzzi, “On the definition of microservice bad smells,” IEEE Software, vol. 35, no. 3, pp. 56–62, 2018

    2018

  9. [9]

    Catalog and detection techniques of microservice anti-patterns and bad smells: A tertiary study,

    T. Cerny, A. S. Abdelfattah, A. A. Maruf, A. Janes, and D. Taibi, “Catalog and detection techniques of microservice anti-patterns and bad smells: A tertiary study,” Journal of Systems and Software, vol. 206, p. 111829, 2023

    2023

  10. [10]

    On microservice analysis and architecture evolution: A systematic mapping study,

    V . Bushong, A. S. Abdelfattah, A. A. Maruf, D. Das, A. Lehman, E. Jaroszewski, M. Coffey, T. Cerny, K. Frajtak, P. Tisnovsky, and M. Bures, “On microservice analysis and architecture evolution: A systematic mapping study,” Applied Sciences, vol. 11, no. 17, 2021

    2021

  11. [11]

    How sonarqube-identified technical debt is prioritized: An exploratory case study,

    R. Alfayez, R. Winn, W. Alwehaibi, E. Venson, and B. Boehm, “How sonarqube-identified technical debt is prioritized: An exploratory case study,”Information and Software Technology, vol. 156, p. 107147, 2023

    2023

  12. [12]

    On the diffuseness of technical debt items and accuracy of remediation time when using sonarqube,

    M. T. Baldassarre, V . Lenarduzzi, S. Romano, and N. Saarim ¨aki, “On the diffuseness of technical debt items and accuracy of remediation time when using sonarqube,” Information and Software Technology, vol. 128, p. 106377, 2020

    2020

  13. [13]

    Comparison of static analysis architec- ture recovery tools for microservice applications,

    S. Schneider, A. Bakhtin, X. Li, J. Soldani, A. Brogi, T. Cerny, R. Scandariato, and D. Taibi, “Comparison of static analysis architec- ture recovery tools for microservice applications,” Empirical Software Engineering, vol. 30, no. 5, p. 128, jun 2025

    2025

  14. [14]

    Offline mining of microservice- based architectures (extended version),

    J. Soldani, J. Khalili, and A. Brogi, “Offline mining of microservice- based architectures (extended version),” SN Computer Science, vol. 4, 04 2023

    2023

  15. [15]

    Using microservice telemetry data for system dynamic analysis,

    A. Al Maruf, A. Bakhtin, T. Cerny, and D. Taibi, “Using microservice telemetry data for system dynamic analysis,” in 2022 IEEE International Conference on Service-Oriented System Engineering (SOSE), 2022, pp. 29–38

    2022

  16. [16]

    Model- based analysis of microservice resiliency patterns,

    N. C. Mendonca, C. M. Aderaldo, J. Camara, and D. Garlan, “Model- based analysis of microservice resiliency patterns,” in 2020 IEEE International Conference on Software Architecture (ICSA), 2020, pp. 114–124

    2020

  17. [17]

    Modeling and analysis of dependen- cies between microservices in devsecops,

    J. McZara, S. Kafle, and D. Shin, “Modeling and analysis of dependen- cies between microservices in devsecops,” in 2020 IEEE International Conference on Smart Cloud (SmartCloud), 2020, pp. 140–147

    2020

  18. [18]

    Graph-based root cause analysis for service-oriented and microservice architectures,

    A. Brand ´on, M. Sol ´e, A. Hu ´elamo, D. Solans, M. S. P ´erez, and V . Munt´es-Mulero, “Graph-based root cause analysis for service-oriented and microservice architectures,” Journal of Systems and Software, vol. 159, p. 110432, 2020

    2020

  19. [19]

    Jcallgraph: Tracing microservices in very large scale container cloud platforms,

    H. Liu, J. Zhang, H. Shan, M. Li, Y . Chen, X. He, and X. Li, “Jcallgraph: Tracing microservices in very large scale container cloud platforms,” in Cloud Computing – CLOUD 2019: 12th International Conference. Springer-Verlag, 2019, p. 287–302

    2019

  20. [20]

    Code ownership: The principles, differences, and their associations with software quality,

    P. Thongtanunam and C. Tantithamthavorn, “Code ownership: The principles, differences, and their associations with software quality,” in 2024 IEEE 35th International Symposium on Software Reliability Engineering (ISSRE), 2024, pp. 379–390

    2024

  21. [21]

    Code ownership in open- source ai software security,

    J. Wen, D. Yuan, L. Ma, and H. Chen, “Code ownership in open- source ai software security,” in Proceedings of the 2nd International Workshop on Responsible AI Engineering, ser. RAIE ’24. Association for Computing Machinery, 2024, p. 28–35. [Online]. Available: https://doi.org/10.1145/3643691.3648586

    work page doi:10.1145/3643691.3648586 2024

  22. [22]

    Ownership vs contribution: Investigating the alignment between ownership and con- tribution,

    E. Zabardast, J. Gonzalez-Huerta, and B. Tanveer, “Ownership vs contribution: Investigating the alignment between ownership and con- tribution,” in 2022 IEEE 19th International Conference on Software Architecture Companion (ICSA-C), 2022, pp. 30–34

    2022

  23. [23]

    Our vision for better code ownership,

    Q. Trotter, E. Kesty, and Q. Bays, “Our vision for better code ownership,” 2023, sourcegraph Blog. [Online]. Available: https://sourcegraph.com/blog/our-vision-for-code-ownership

    2023

  24. [24]

    An approach for evaluating the potential impact of anti-patterns on microservices performance,

    R. Matar and J. Jahi ´c, “An approach for evaluating the potential impact of anti-patterns on microservices performance,” in 2023 IEEE 20th International Conference on Software Architecture Companion (ICSA-C), 2023, pp. 167–170

    2023

  25. [25]

    Towards microservice smells detection,

    I. Pigazzini, F. A. Fontana, V . Lenarduzzi, and D. Taibi, “Towards microservice smells detection,” in Proceedings of the 3rd International Conference on Technical Debt, ser. TechDebt ’20. Association for Computing Machinery, 2020, p. 92–97

    2020

  26. [26]

    Identifying availability tactics to sup- port security architectural design of microservice-based systems,

    G. Marquez and H. Astudillo, “Identifying availability tactics to sup- port security architectural design of microservice-based systems,” in Proceedings of the 13th European Conference on Software Architecture - V olume2, ser. ECSA ’19. Association for Computing Machinery, 2019, p. 123–129

    2019

  27. [27]

    Automated code-smell detection in microservices through static analysis: A case study,

    A. Walker, D. Das, and T. Cerny, “Automated code-smell detection in microservices through static analysis: A case study,” Applied Sciences, vol. 10, no. 21, 2020

    2020

  28. [28]

    Automatic anti-pattern detection in microservice architectures based on distributed tracing,

    T. H ¨ubener, M. R. V . Chaudron, Y . Luo, P. Vallen, J. van der Kogel, and T. Liefheid, “Automatic anti-pattern detection in microservice architectures based on distributed tracing,” in Proceedings of the 44th International Conference on Software Engineering: Software Engineering in Practice, ser. ICSE-SEIP ’22. New York, NY , USA: Association for Comput...

    work page doi:10.1145/3510457.3513066 2022

  29. [29]

    Visualizing anti-patterns in microservices at runtime: A systematic mapping study,

    G. Parker, S. Kim, A. A. Maruf, T. Cerny, K. Frajtak, P. Tisnovsky, and D. Taibi, “Visualizing anti-patterns in microservices at runtime: A systematic mapping study,” IEEE Access, vol. 11, pp. 4434–4442, 2023

    2023

  30. [30]

    Unsupervised detection of microservice trace anomalies through service-level deep bayesian networks,

    P. Liu, H. Xu, Q. Ouyang, R. Jiao, Z. Chen, S. Zhang, J. Yang, L. Mo, J. Zeng, W. Xue, and D. Pei, “Unsupervised detection of microservice trace anomalies through service-level deep bayesian networks,” in 2020 IEEE 31st International Symposium on Software Reliability Engineering (ISSRE), 2020, pp. 48–58

    2020

  31. [31]

    Real-time anomaly detection using distributed tracing in microservice cloud applications,

    M. Raeiszadeh, A. Ebrahimzadeh, A. Saleem, R. H. Glitho, J. Eker, and R. A. F. Mini, “Real-time anomaly detection using distributed tracing in microservice cloud applications,” in 2023 IEEE 12th International Conference on Cloud Networking (CloudNet), 2023, pp. 36–44

    2023

  32. [32]

    Tracegra: A trace-based anomaly detection for microservice using graph deep learning.Computer Communications, 204:109–117, 2023

    J. Chen, F. Liu, J. Jiang, G. Zhong, D. Xu, Z. Tan, and S. Shi, “Tracegra: A trace-based anomaly detection for microservice using graph deep learning,” Comput. Commun., vol. 204, no. C, p. 109–117, Apr. 2023. [Online]. Available: https://doi.org/10.1016/j.comcom.2023.03.028

    work page doi:10.1016/j.comcom.2023.03.028 2023

  33. [33]

    Autoencoder-based anomaly detection in microservices using distributed tracing,

    S. Shahini and H. Momeni, “Autoencoder-based anomaly detection in microservices using distributed tracing,” in 2024 20th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP), 2024, pp. 1–6

    2024

  34. [34]

    Multi-dimensional anomaly detection and fault localization in microservice architectures: A dual-channel deep learning approach with causal inference for intelligent sensing,

    S. Xing, Y . Wang, and W. Liu, “Multi-dimensional anomaly detection and fault localization in microservice architectures: A dual-channel deep learning approach with causal inference for intelligent sensing,” Sensors, vol. 25, no. 11, p. 3396, 2025. [Online]. Available: https://www.mdpi.com/1424-8220/25/11/3396

    2025

  35. [35]

    Detection of microservice-based software anomalies based on opentracing in cloud,

    M. Khanahmadi, A. Shameli-Sendi, M. Jabbarifar, Q. Fournier, and M. Dagenais, “Detection of microservice-based software anomalies based on opentracing in cloud,” Software: Practice and Experience, vol. 53, no. 8, pp. 1681–1699, 2023. [Online]. Available: https: //onlinelibrary.wiley.com/doi/abs/10.1002/spe.3208

    work page doi:10.1002/spe.3208 2023

  36. [36]

    Graph-based anti-pattern detec- tion in microservice applications,

    A. L. Røhne, B. Pronk, and B. Akesson, “Graph-based anti-pattern detec- tion in microservice applications,” in 2024 50th Euromicro Conference on Software Engineering and Advanced Applications (SEAA), 2024, pp. 341–349

    2024

  37. [37]

    Code smell dataset,

    A. Nizam, ¨Omer Kerem Adalı, and E. ˙Islamo˘glu, “Code smell dataset,”

  38. [38]

    Available: https://dx.doi.org/10.21227/j0rn-ht76

    [Online]. Available: https://dx.doi.org/10.21227/j0rn-ht76

    work page doi:10.21227/j0rn-ht76

  39. [39]

    Mlcq: Industry-relevant code smell data set,

    L. Madeyski and T. Lewowski, “Mlcq: Industry-relevant code smell data set,” in Proceedings of the 24th International Conference on Evaluation and Assessment in Software Engineering, ser. EASE ’20. New York, NY , USA: Association for Computing Machinery, 2020, p. 342–347. [Online]. Available: https://doi.org/10.1145/3383219.3383264

    work page doi:10.1145/3383219.3383264 2020

  40. [40]

    Smellycode++: Multi-label dataset for code smell detection,

    N. Alomari, A. Alazba, H. Aljamaan, and M. Alshayeb, “Smellycode++: Multi-label dataset for code smell detection,” Scientific Data, vol. 12, no. 1, p. 1207, 2025. [Online]. Available: https://doi.org/10.1038/ s41597-025-05465-z

    2025

  41. [41]

    apolloconfig/apollo,

    “apolloconfig/apollo,” https://github.com/apolloconfig/apollo/tree/ de05540e6c9a18cdf370ae95ca5e544d7b8d04bf, accessed: 2026-02-24

    2026

  42. [42]

    Descartesresearch/teastore,

    “Descartesresearch/teastore,” https://github.com/DescartesResearch/ TeaStore/tree/e93bca736abe5bf92267d0bc61e95fc9198e6014, accessed: 2026-02-24

    2026

  43. [43]

    zpng/spring-cloud-microservice-examples,

    “zpng/spring-cloud-microservice-examples,” https://github.com/zpng/ spring-cloud-microservice-examples, accessed: 2026-02-24

    2026

  44. [44]

    william-tran/freddys-bbq,

    “william-tran/freddys-bbq,” https://github.com/william-tran/ freddys-bbq, accessed: 2026-02-24

    2026

  45. [45]

    sqshq/piggymetrics,

    “sqshq/piggymetrics,” https://github.com/sqshq/piggymetrics/tree/ fd5ee3c555ea9cd6067eacf3f2a3e8b85fe4fe77, accessed: 2026-02-24

    2026

  46. [46]

    microservices-patterns/ftgo-application,

    “microservices-patterns/ftgo-application,” https:// github.com/microservices-patterns/ftgo-application/tree/ c028190295d64b5fad8993e2f3a6dd88270e9bf2, accessed: 2026-02-24

    2026

  47. [47]

    oktadev/spring-boot-microservices-example,

    “oktadev/spring-boot-microservices-example,” https://github.com/ oktadev/spring-boot-microservices-example.git, accessed: 2026-02-24

    2026

  48. [48]

    Microservice-api-patterns/lakesidemutual,

    “Microservice-api-patterns/lakesidemutual,” https://github. com/Microservice-API-Patterns/LakesideMutual/tree/ bdc6d30135149563c057dd30f21b7df68608c500, accessed: 2026-02-24

    2026

  49. [49]

    Hiejulia/warehouse-microservice,

    “Hiejulia/warehouse-microservice,” https://github.com/HieJulia/ warehouse-microservice, accessed: 2026-02-24

    2026

  50. [50]

    Joecao/qbike,

    “Joecao/qbike,” https://github.com/JoeCao/qbike, accessed: 2026-02-24

    2026

  51. [51]

    ewolff/microservice (microservice-demo subdirectory),

    “ewolff/microservice (microservice-demo subdirectory),” https://github.com/ewolff/microservice/tree/master/microservice-demo, accessed: 2026-02-24

    2026

  52. [52]

    benwilcock/cqrs-microservice-sampler,

    “benwilcock/cqrs-microservice-sampler,” https://github.com/ benwilcock/cqrs-microservice-sampler, accessed: 2026-02-24

    2026

  53. [53]

    idugalic/micro-company,

    “idugalic/micro-company,” https://github.com/idugalic/micro-company/ tree/8f4a2189403c13af66a964d31d7dc5228e489a0b, accessed: 2026-02- 24

    2026

  54. [54]

    A probabilistic interpretation of precision, recall and f-score, with implication for evaluation,

    C. Goutte and E. Gaussier, “A probabilistic interpretation of precision, recall and f-score, with implication for evaluation,” in Advances in Information Retrieval, D. E. Losada and J. M. Fern ´andez-Luna, Eds. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, pp. 345–359

    2005

  55. [55]

    Landscape and taxonomy of prompt engineering patterns in software engineering,

    Y . Sasaki, H. Washizaki, J. Li, N. Yoshioka, N. Ubayashi, and Y . Fukazawa, “Landscape and taxonomy of prompt engineering patterns in software engineering,” IT Professional, vol. 27, no. 1, pp. 41–49, 2025

    2025

  56. [56]

    Better zero-shot reasoning with role-play prompting,

    A. Kong, S. Zhao, H. Chen, Q. Li, Y . Qin, R. Sun, X. Zhou, E. Wang, and X. Dong, “Better zero-shot reasoning with role-play prompting,” 2024

    2024