EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond binary AI text detection: Partial authorship, source-text similarity, and an integrated threshold model of detectability

István Füzesi, Péter Lengyel, János Pancsira

International Review of Applied Sciences and Engineering · 05.11.2026 · 17 (3) · 455-470

DOI: 10.1556/1848.2026.01535 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Review of Applied Sciences and Engineering, erschienen am 05.11.2026. Verfasst von István Füzesi und 2 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates AI text detection under conditions that more closely reflect real-world writing practices than conventional binary human-versus-AI benchmarks. Rather than treating authorship as a dichotomy, detectability is examined as a function of partial AI authorship, source-text similarity, and generator heterogeneity. Ten pre-LLM, human-written English scientific abstracts were used as reference texts, from which four authorship states (H100, AI50, AI75, and AI100) were constructed through controlled rewriting and paragraph-level mixing. AI-generated content was produced using four large language models: ChatGPT, Gemini, Claude, and LLaMA. Detection outputs from Turnitin and GPTZero were evaluated using non-parametric statistics, correlation analysis, and logistic threshold modeling. The results demonstrate that fully human and fully AI-rewritten texts are statistically distinguishable: median AI scores increased from 0 in H100 to 53 in AI100 for Turnitin ( U = 49.5, P < 0.001) and from 0 to 11 for GPTZero ( U = 61.0, P < 0.001), although AI-generated texts did not constitute a homogeneous class. Detectability also varied significantly across the four nominal authorship states for both Turnitin (H = 30.39, P < 0.001) and GPTZero (H = 21.77, P < 0.001), and systematically with source-text similarity and the generating model. Turnitin showed greater sensitivity than GPTZero to changes in nominal AI proportion and transformation intensity, particularly under mixed-authorship conditions. Significant generator-dependent differences were also observed, with Gemini outputs generally receiving higher AI-detection scores than ChatGPT or LLaMA outputs. The main methodological contribution is the Integrated Detectability Threshold Model (IDTM), which represents detection probability as a joint function of nominal AI proportion and transformation intensity. Within the present sample, the model identified a similarity transition range of approximately 63–66%, below which Turnitin-based detection became more likely than non-detection. These findings support a shift from binary AI classification toward a threshold- and risk-sensitive interpretation of AI text detectability.

Zitieren

APA

Füzesi, I., Lengyel, P., & Pancsira, J. (2026). Beyond binary AI text detection: Partial authorship, source-text similarity, and an integrated threshold model of detectability. International Review of Applied Sciences and Engineering, 17(3), 455-470. https://doi.org/10.1556/1848.2026.01535

Vancouver

Füzesi I, Lengyel P, Pancsira J. Beyond binary AI text detection: Partial authorship, source-text similarity, and an integrated threshold model of detectability. International Review of Applied Sciences and Engineering. 2026;17(3):455-470. doi:10.1556/1848.2026.01535

BibTeX
@article{Fzesi2026,
  author = {Füzesi, István and Lengyel, Péter and Pancsira, János},
  title = {Beyond binary AI text detection: Partial authorship, source-text similarity, and an integrated threshold model of detectability},
  journal = {International Review of Applied Sciences and Engineering},
  year = {2026},
  volume = {17},
  number = {3},
  pages = {455--470},
  doi = {10.1556/1848.2026.01535}
}
Kostenlos starten →