This is refering to 99% in the context of “amount of loss that you explain in a human interpretable way for some component in the model” (a notion of faithfulness). For downstream tasks, either much higher or much lower reliability could be the right target (depending on the exact task).
This is refering to 99% in the context of “amount of loss that you explain in a human interpretable way for some component in the model” (a notion of faithfulness). For downstream tasks, either much higher or much lower reliability could be the right target (depending on the exact task).