Get evaluator run
Get one evaluator-run job with results and human-agreement summary
Authorizations
API key for authentication
Path Parameters
Annotation task to act on
"f47ac10b-58cc-4372-a567-0e02b2c3d479"
The evaluator run to act on
"f47ac10b-58cc-4372-a567-0e02b2c3d479"
Response
Successful Response
ID of the evaluator-run job
"f47ac10b-58cc-4372-a567-0e02b2c3d479"
ID of the task the job ran on
Current status of the job
queued, in_progress, completed, failed Failure reason, present when the job failed
When the job finished (ISO 8601 UTC)
The evaluators the job ran, each pinned to the version it used, with that version's rubric
One result per item and evaluator. Each keys back to evaluators by its evaluator and version IDs
How each evaluator's judgements line up with the human annotations on the same items
The exact item set the job ran on, frozen when the job started
Whether the run is shared publicly
Token for building the public share URL