The first public dataset of 10,217 GPT-Image-2 generated images sourced from Twitter in the week after release, with CLIP taxonomy, OCR, face detection, clustering analyses, and a finding that C2PA provenance data is stripped on upload.
Ammeba: A large-scale survey and dataset of media-based misinformation in-the-wild
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
QuAD aggregates quality-weighted detection scores from near-duplicates of an image to raise balanced accuracy by about 8% over simple averaging on state-of-the-art detectors.
AI-generated content in a new 150K-post dataset spreads virally via passive engagement, reaches consensus faster once flagged, and evades detectors more effectively as models improve.
The XNote dataset and LVLM benchmarks demonstrate that current models face significant challenges in generating accurate, grounded Community Notes for image-based contextual deception.
citing papers explorer
-
GPT-Image-2 in the Wild: A Twitter Dataset of Self-Reported AI-Generated Images from the First Week of Deployment
The first public dataset of 10,217 GPT-Image-2 generated images sourced from Twitter in the week after release, with CLIP taxonomy, OCR, face detection, clustering analyses, and a finding that C2PA provenance data is stripped on upload.
-
Quality-Aware Calibration for AI-Generated Image Detection in the Wild
QuAD aggregates quality-weighted detection scores from near-duplicates of an image to raise balanced accuracy by about 8% over simple averaging on state-of-the-art detectors.
-
The Synthetic Media Shift: Tracking the Rise, Virality, and Detectability of AI-Generated Multimodal Misinformation
AI-generated content in a new 150K-post dataset spreads virally via passive engagement, reaches consensus faster once flagged, and evades detectors more effectively as models improve.
-
XNote: Benchmarking Automated Community Notes Generation for Image-based Contextual Deception
The XNote dataset and LVLM benchmarks demonstrate that current models face significant challenges in generating accurate, grounded Community Notes for image-based contextual deception.