eval_toolkit.claims#
|
Machine-readable result of evaluating claim specs. |
|
A claim plus the gates required before it can be treated as supported. |
|
Named callable gate used inside a |
|
Result of one evidence gate. |
|
Evaluate claim specs against a result payload and optional manifest. |
|
Require an external diagnostic payload, optionally thresholded. |
|
Require a non-null headline/comparison block at an arbitrary path. |
|
Require enough negatives for a low-FPR claim to be statistically feasible. |
|
Require a numeric metric to satisfy a threshold comparison. |
|
Require minimum total/positive/negative counts for a slice. |
|
Fail if result config or manifest leakage report has error-severity findings. |
|
Fail if any scorer block contains an |
|
Require a paired-difference comparison under a slice. |
|
Require a metric path under one scorer result. |
|
Require a scorer result under a slice. |
|
Require |
|
Require source-role metadata with the requested roles in the manifest. |
|
Fail if result or manifest contains non-finite numeric values. |