GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917462946086912 |
|---|---|
| author | Zewde, Kidus Ren, Simiao Shen, Xingyu Wu, Jiaqi Zhou, Yuchen Duong, Tommy Zhang, Zikang Traister, Ethan Xie, Kewen |
| author_facet | Zewde, Kidus Ren, Simiao Shen, Xingyu Wu, Jiaqi Zhou, Yuchen Duong, Tommy Zhang, Zikang Traister, Ethan Xie, Kewen |
| contents | The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the immediate aftermath of the model's April 21, 2026 release. Leveraging the Twitter API v2 and a multi-stage curation pipeline spanning multilingual text heuristics (English, Japanese, and Chinese), browser-automated Twitter "Made with AI" badge verification, and model name variant matching, we curate 10,217 confirmed GPT-image-2 images from 27,662 collected records over a six-day window.
We characterize the dataset across four analyses: CLIP-based zero-shot subject taxonomy, OCR text legibility (82.0% of images contain detectable text), face detection (59.2% of images, 22,583 total faces), and semantic clustering (137 CLIP ViT-L/14 clusters).
A key negative result is that C2PA content credentials are systematically stripped by Twitter's CDN on upload, rendering cryptographic provenance verification infeasible for social-media-sourced AI images. The dataset and all curation code are released publicly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25370 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment Zewde, Kidus Ren, Simiao Shen, Xingyu Wu, Jiaqi Zhou, Yuchen Duong, Tommy Zhang, Zikang Traister, Ethan Xie, Kewen Computer Vision and Pattern Recognition Artificial Intelligence The release of GPT-image-2 by OpenAI marks a watershed moment in AI-generated imagery: the boundary between photographic reality and synthetic content has never been more difficult to discern. We introduce the GPT-Image-2 Twitter Dataset, the first published dataset of GPT-image-2 generated images, sourced from publicly available Twitter/X posts in the immediate aftermath of the model's April 21, 2026 release. Leveraging the Twitter API v2 and a multi-stage curation pipeline spanning multilingual text heuristics (English, Japanese, and Chinese), browser-automated Twitter "Made with AI" badge verification, and model name variant matching, we curate 10,217 confirmed GPT-image-2 images from 27,662 collected records over a six-day window. We characterize the dataset across four analyses: CLIP-based zero-shot subject taxonomy, OCR text legibility (82.0% of images contain detectable text), face detection (59.2% of images, 22,583 total faces), and semantic clustering (137 CLIP ViT-L/14 clusters). A key negative result is that C2PA content credentials are systematically stripped by Twitter's CDN on upload, rendering cryptographic provenance verification infeasible for social-media-sourced AI images. The dataset and all curation code are released publicly. |
| title | GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2604.25370 |