Provenance Indicator
Also known as: Source Attribution
Information that identifies which AI model, trial, or prompt produced a particular piece of content in a multi-model comparison. Provenance indicators help users understand which models generate which claims, enabling them to build mental models of individual model strengths and weaknesses over time. For example, knowing that "GPT-4o says the chair is red while Gemini says it is pink" is more informative than simply knowing there is a disagreement. Provenance information also supports users in identifying model-specific patterns, such as learning that a particular model struggles with numbers or spatial relationships.
Category: artificial intelligence · interaction design
Related: Support Indicator · Multi-Model Comparison · Variation Surfacing · Model Reliability