A Novel Naive Bayes Classifier for Detecting AI-Generated Text in Digital Twin Systems Using Word Pair Probabilities
Bibliographic record
Abstract
Digital twin systems, which create virtual replicas of physical entities, are pivotal in industries such as manufacturing, healthcare, and urban planning, enabling real-time monitoring, predictive maintenance, and data-driven decision-making. These systems depend on trustworthy textual data—maintenance logs, operational reports, and technical documentation—to ensure accurate simulations. However, the rise of sophisticated AI language models like ChatGPT and Gemini introduces a significant challenge: AI-generated text can infiltrate these systems, undermining data integrity and potentially leading to flawed simulations with serious real-world implications. This paper presents a novel Multinomial Naive Bayes classifier that utilizes word pair probabilities to detect and classify AI-generated text with exceptional precision. Unlike existing detection tools, this approach not only identifies AI-generated content but also differentiates between specific AI models, achieving accuracies of 94% in binary classification (ChatGPT vs. Gemini), 95% in ternary classification (Human vs. ChatGPT vs. Gemini), and 93% in quaternary classification (Human vs. ChatGPT vs. Gemini vs. OtherAI). By enhancing the reliability of textual inputs, this classifier bolsters data provenance in digital twin applications, ensuring robust and dependable virtual models. Rooted in extensive research, this scalable method addresses a pressing issue in the era of AI-driven text generation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".