Impacto de la inteligencia artificial generativa en la calidad del código fuente: estudio cuasiexperimental
DOI:
https://doi.org/10.65415/xfce7x48Palabras clave:
inteligencia artificial generativa; calidad del software; código fuente; ingeniería de software; simulaciónResumen
La inteligencia artificial generativa se incorporó con rapidez a los entornos de programación, pero sus efectos sobre la calidad del código no son uniformes. Este estudio evalúa, mediante un diseño cuasiexperimental, el cambio asociado al uso de un asistente generativo en corrección funcional, mantenibilidad, complejidad, legibilidad, seguridad y productividad. Se construyeron 128 registros sintéticos —64 de control y 64 experimentales— con mediciones pretest y postest. El desenlace principal fue el porcentaje de pruebas unitarias superadas; los modelos ANCOVA emplearon errores robustos HC3, ajuste de Holm e intervalos bootstrap para la g de Hedges. En la simulación, la asistencia con IA produjo una diferencia ajustada de 5,11 puntos porcentuales en pruebas superadas (IC 95 %: 3,22–7,01; p ajustada < 0,001; g = 0,94) y redujo el tiempo en 12,77 minutos (IC 95 %: −15,93 a −9,61). También mejoró complejidad, legibilidad, documentación y Pylint. No se observaron beneficios concluyentes en vulnerabilidades ni duplicación. Los resultados delimitan un escenario reproducible y no constituyen evidencia obtenida de participantes reales; sirven para formular y someter a prueba un protocolo empírico posterior.
Descargas
Referencias
Al Madi, N. (2022). How readable is model-generated code? Examining readability and visual inspection of GitHub Copilot. Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering, 1–5. https://doi.org/10.1145/3551349.3560438
Asare, O., Nagappan, M., & Asokan, N. (2023). Is GitHub’s Copilot as bad as humans at introducing vulnerabilities in code? Empirical Software Engineering, 28(6), Article 129. https://doi.org/10.1007/s10664-023-10380-1
Banh, L., Holldack, F., & Strobel, G. (2025). Copiloting the future: How generative AI transforms software engineering. Information and Software Technology, 183, 107751. https://doi.org/10.1016/j.infsof.2025.107751
Barke, S., James, M. B., & Polikarpova, N. (2023). Grounded Copilot: How programmers interact with code-generating models. Proceedings of the ACM on Programming Languages, 7(OOPSLA1), 85–111. https://doi.org/10.1145/3586030
Bird, C., Ford, D., Zimmermann, T., Forsgren, N., Kalliamvakou, E., Lowdermilk, T., & Gazit, I. (2022). Taking flight with Copilot. Queue, 20(6), 35–57. https://doi.org/10.1145/3582083
Coleman, D., Ash, D., Lowther, B., & Oman, P. (1994). Using metrics to evaluate software system maintainability. Computer, 27(8), 44–49. https://doi.org/10.1109/2.303623
Dantas, C., Rocha, A., & Maia, M. (2023). Assessing the readability of ChatGPT code snippet recommendations: A comparative study. Proceedings of the XXXVII Brazilian Symposium on Software Engineering, 283–292. https://doi.org/10.1145/3613372.3613413
Denny, P., Kumar, V., & Giacaman, N. (2023). Conversing with Copilot: Exploring prompt engineering for solving CS1 problems using natural language. Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1, 1136–1142. https://doi.org/10.1145/3545945.3569823
Ebert, C., & Louridas, P. (2023). Generative AI for software practitioners. IEEE Software, 40(4), 30–38. https://doi.org/10.1109/MS.2023.3265877
Fu, Y., Liang, P., Tahir, A., Li, Z., Shahin, M., Yu, J., & Chen, J. (2025). Security weaknesses of Copilot-generated code in GitHub projects: An empirical study. ACM Transactions on Software Engineering and Methodology, 34(8), 1–34. https://doi.org/10.1145/3716848
Haindl, P., & Weinberger, G. (2024). Does ChatGPT help novice programmers write better code? Results from static code analysis. IEEE Access, 12, 114146–114156. https://doi.org/10.1109/ACCESS.2024.3445432
Hou, X., Zhao, Y., Liu, Y., Yang, Z., Wang, K., Li, L., Luo, X., Lo, D., Grundy, J., & Wang, H. (2024). Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(8), 1–79. https://doi.org/10.1145/3695988
Husein, R. A., Aburajouh, H., & Catal, C. (2025). Large language models for code completion: A systematic literature review. Computer Standards & Interfaces, 92, 103917. https://doi.org/10.1016/j.csi.2024.103917
International Organization for Standardization. (2023). ISO/IEC 25010:2023 systems and software engineering—Systems and software Quality Requirements and Evaluation (SQuaRE)—Product quality model. https://www.iso.org/standard/78176.html
Lakens, D. (2013). Calculating and reporting effect sizes to facilitate cumulative science: A practical primer for t-tests and ANOVAs. Frontiers in Psychology, 4, Article 863. https://doi.org/10.3389/fpsyg.2013.00863
Liang, J. T., Yang, C., & Myers, B. A. (2024). A large-scale survey on the usability of AI programming assistants: Successes and challenges. Proceedings of the IEEE/ACM 46th International Conference on Software Engineering, 1–13. https://doi.org/10.1145/3597503.3608128
McCabe, T. J. (1976). A complexity measure. IEEE Transactions on Software Engineering, SE-2(4), 308–320. https://doi.org/10.1109/TSE.1976.233837
Moradi Dakhel, A., Majdinasab, V., Nikanjam, A., Khomh, F., Desmarais, M. C., & Jiang, Z. M. (2023). GitHub Copilot AI pair programmer: Asset or liability? Journal of Systems and Software, 203, 111734. https://doi.org/10.1016/j.jss.2023.111734
Mozannar, H., Bansal, G., Fourney, A., & Horvitz, E. (2024). Reading between the lines: Modeling user behavior and costs in AI-assisted programming. Proceedings of the CHI Conference on Human Factors in Computing Systems, 1–16. https://doi.org/10.1145/3613904.3641936
Nguyen, N., & Nadi, S. (2022). An empirical evaluation of GitHub Copilot’s code suggestions. Proceedings of the 19th International Conference on Mining Software Repositories, 1–5. https://doi.org/10.1145/3524842.3528470
Oertel, J., Klünder, J., & Hebig, R. (2025). Don’t settle for the first! How many GitHub Copilot solutions should you check? Information and Software Technology, 183, 107737. https://doi.org/10.1016/j.infsof.2025.107737
Ouyang, S., Zhang, J. M., Harman, M., & Wang, M. (2025). An empirical study of the non-determinism of ChatGPT in code generation. ACM Transactions on Software Engineering and Methodology, 34(2), 1–28. https://doi.org/10.1145/3697010
Pearce, H., Ahmad, B., Tan, B., Dolan-Gavitt, B., & Karri, R. (2022). Asleep at the keyboard? Assessing the security of GitHub Copilot’s code contributions. 2022 IEEE Symposium on Security and Privacy, 754–768. https://doi.org/10.1109/SP46214.2022.9833571
Perry, N., Srivastava, M., Kumar, D., & Boneh, D. (2023). Do users write more insecure code with AI assistants? Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2785–2799. https://doi.org/10.1145/3576915.3623157
Prather, J., Reeves, B. N., Denny, P., Becker, B. A., Leinonen, J., Luxton-Reilly, A., Powell, G., Finnie-Ansley, J., & Santos, E. A. (2024). “It’s weird that it knows what I want”: Usability and interactions with Copilot for novice programmers. ACM Transactions on Computer-Human Interaction, 31(1), 1–31. https://doi.org/10.1145/3617367
Descargas
Publicado
Número
Sección
Licencia
Derechos de autor 2026 MSc. Rodrigo Pazmiño Perez, Norma Alexandra Valencia Castillo , Romulo Steev Vélez Martínez
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
