1 coral_monotonicity_violation_rate

rri_metrics.coral.coral_monotonicity_violation_rate(logits)

Compute the fraction of monotonicity violations in CORAL probabilities.

CORAL expects P(y > k) to be non-increasing with k. This returns the per-sample fraction of threshold pairs that violate this ordering.

1.1 Parameters

Name	Type	Description	Default
logits	Tensor	`Tensor["... K-1"]` threshold logits.	required

1.2 Returns

Name	Type	Description
	Tensor	`Tensor["..."]` fraction of violations in `[0, 1]`.

# coral_monotonicity_violation_rate { #aria_nbv.rri_metrics.coral.coral_monotonicity_violation_rate }

```python
rri_metrics.coral.coral_monotonicity_violation_rate(logits)
```

Compute the fraction of monotonicity violations in CORAL probabilities.

CORAL expects ``P(y > k)`` to be non-increasing with ``k``. This returns
the per-sample fraction of threshold pairs that violate this ordering.

## Parameters {.doc-section .doc-section-parameters}

| Name   | Type   | Description                             | Default    |
|--------|--------|-----------------------------------------|------------|
| logits | Tensor | ``Tensor["... K-1"]`` threshold logits. | _required_ |

## Returns {.doc-section .doc-section-returns}

| Name   | Type   | Description                                             |
|--------|--------|---------------------------------------------------------|
|        | Tensor | ``Tensor["..."]`` fraction of violations in ``[0, 1]``. |