| cff-version: 1.2.0 | |
| message: "If you cite DotCheck engines or measured holdout gates, use the citation below." | |
| title: "DotCheck AI-likeness engines (inhouse@12, inhouse-text@11, inhouse-video@2)" | |
| authors: | |
| - name: "DotCheck" | |
| url: "https://dotcheck.ai" | |
| repository-code: "https://huggingface.co/DotCheck" | |
| license: "Apache-2.0" | |
| date-released: "2026-07-28" | |
| abstract: >- | |
| DotCheck serves binary AI-likeness scores for images (wire inhouse@12 / | |
| Vermeer@12, adapted SigLIP2 + linear head), text (inhouse-text@11 / Valla@11, | |
| seven languages), and video frame bags (inhouse-video@2 / Muybridge) using | |
| linear/logistic heads on commercial-clean backbones. Live heads are | |
| published under Apache-2.0 on Hugging Face; everyday product scoring runs | |
| through DotCheck. | |
| keywords: | |
| - ai-detection | |
| - image-classification | |
| - text-classification | |
| - video | |
| - siglip2 | |
| preferred-citation: | |
| type: soft | |
| authors: | |
| - name: "DotCheck" | |
| title: "DotCheck engines (inhouse@12, inhouse-text@11, inhouse-video@2)" | |
| url: "https://dotcheck.ai/docs" | |
| year: 2026 | |