The forgery is now caught by construction
the forgery is now caught by construction: bradford’s ai tests drawings with five measurements and reaches 90 percent accuracy on 900 authenticated works, while openai stamps every chatgpt image with c2pa provenance and a synthid watermark. a screenshot still strips all of it.
provenance is a race between signing and stripping.
Context
The University of Bradford said on Jun 17, 2026 that its AI can tell a genuine drawing from a fake with close to 90 percent accuracy by analysing five key visual features, published in PLOS ONE.
OpenAI's content provenance post (May 19, 2026, updated Oct 5, 2026) describes Content Credentials, SynthID and a public verification tool that checks files for OpenAI provenance signals including C2PA.
The five features and close to 90 percent accuracy match the Bradford release. The 900 authenticated works, 'every ChatGPT image' being stamped and a screenshot stripping the marks are not seen in the sources read, so unsupported here, not refuted. 'Provenance race' is the author's.
Related work
- University of Bradford: AI learns to spot art fakes in five simple tests ↗Jun 17, 2026.
- OpenAI: Advancing content provenance ↗May 19, 2026, updated Oct 5.
- OpenAI: Verify OpenAI-generated content ↗Verification tool.
Watch next
- Test whether the OpenAI verification tool still reads a cropped screenshot.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 2 October 2026 at 09:48 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →