Year 12 · Student investigation
How can a small training change produce a hidden behaviour change?
Keep an individual record even when you investigate in pairs. Record the exact settings, source and data split.
Will amplifying the checkpoint difference affect Kiki queries more than other names?
What did you change? What stayed the same? What did you notice?
Inspect a Kiki query whose supported colour is not green and a non-Kiki query. Compare the full held-out counts.
A checkpoint-diff report with exact α, paired prompts, subgroup denominators and a discovery-versus-prevalence distinction.
This activity can show _ . It cannot tell us _ . A new case I would test is ____ .
Use fictional data. Download or print your work before leaving.