Situation: A plant-recognition system handles photos in two stages. First, a region finder isolates the main leaf from the image. Next, a species classifier decides whether the leaf is a maple leaf. For one photo that truly shows a maple leaf, the system outputs "not maple." When the engineers review the intermediate result, the isolated leaf looks centered, complete, and correctly captured.

Prompt: If the isolated leaf is correct, which stage is most likely causing the mistake, and what should the engineers inspect next?

Model response: The region finder is probably not the source of this error because it extracted the leaf properly. The most likely failure is in the species classifier, since it received the correct leaf cutout but still assigned the wrong label. The next step is to test the classifier on that exact cutout and compare it with other leaves it mislabels, looking for shared patterns such as blur, viewing angle, or similarity to other species. That will show where to focus improvements.

What matters:

• A correct intermediate cutout points away from the region finder
• The species classifier is the likely source of the wrong final decision
• Stage-by-stage error analysis attributes the failure using each component's output
• The next investigation should target the classifier's behavior on this example and similar ones
• Improvement effort should go to the component that actually made the mistake

Rubric: Full credit correctly identifies the species classifier as the likely fault because the extracted leaf was accurate, and says the team should examine the classifier's output on that cutout and search for recurring failure patterns to guide improvement.