NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918373829378048 |
|---|---|
| author | Breneur, Oleksandr Marchenko Danilov, Adelaide Nourbakhsh, Aria Lamsiyah, Salima |
| author_facet | Breneur, Oleksandr Marchenko Danilov, Adelaide Nourbakhsh, Aria Lamsiyah, Salima |
| contents | We present NOTAI.AI, an explainable framework for machine-generated text detection that extends Fast-DetectGPT by integrating curvature-based signals with neural and stylometric features in a supervised setting. The system combines 17 interpretable features, including Conditional Probability Curvature, ModernBERT detector score, readability metrics, and stylometric cues, within a gradient-boosted tree (XGBoost) meta-classifier to determine whether a text is human- or AI-generated. Furthermore, NOTAI.AI applies Shapley Additive Explanations (SHAP) to provide both local and global feature-level attribution. These attributions are further translated into structured natural-language rationales through an LLM-based explanation layer, which enables user-facing interpretability. The system is deployed as an interactive web application that supports real-time analysis, visual feature inspection, and structured evidence presentation. A web interface allows users to input text and inspect how neural and statistical signals influence the final decision. The source code and demo video are publicly available to support reproducibility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05617 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution Breneur, Oleksandr Marchenko Danilov, Adelaide Nourbakhsh, Aria Lamsiyah, Salima Computation and Language 68T50, 68T07 I.2.7; I.2.6 We present NOTAI.AI, an explainable framework for machine-generated text detection that extends Fast-DetectGPT by integrating curvature-based signals with neural and stylometric features in a supervised setting. The system combines 17 interpretable features, including Conditional Probability Curvature, ModernBERT detector score, readability metrics, and stylometric cues, within a gradient-boosted tree (XGBoost) meta-classifier to determine whether a text is human- or AI-generated. Furthermore, NOTAI.AI applies Shapley Additive Explanations (SHAP) to provide both local and global feature-level attribution. These attributions are further translated into structured natural-language rationales through an LLM-based explanation layer, which enables user-facing interpretability. The system is deployed as an interactive web application that supports real-time analysis, visual feature inspection, and structured evidence presentation. A web interface allows users to input text and inspect how neural and statistical signals influence the final decision. The source code and demo video are publicly available to support reproducibility. |
| title | NOTAI.AI: Explainable Detection of Machine-Generated Text via Curvature and Feature Attribution |
| topic | Computation and Language 68T50, 68T07 I.2.7; I.2.6 |
| url | https://arxiv.org/abs/2603.05617 |