evaluations

The server-computed report (?by=&allow_mixed=)

The evaluation's report, computed server-side over the verdicts the ledger holds: counts, void rate, per-environment tables (optionally by a label key), integrity (single judge, judge bound to code, memo hits, environment-graded verdicts), and Spearman rho against real outcomes when supplied. Refuses to average rows graded under different judges (allow_mixed names the mix) and to compare label values that share an identity.

get/preview/evaluations/{name}/report

Request

  • Base URL: https://autoresearch.sfcompute.com
  • URL: https://autoresearch.sfcompute.com/preview/evaluations/{name}/report
  • Auth: HTTP bearer

Path parameters

namestring required

The evaluation this call acts on.

Query parameters

bystring nullable

Group the table by this label key ("policy").

allow_mixedboolean nullable

Allow rows graded under different judges (the report names the mix).

allow_memo_across_labelsboolean nullable

Allow a by key whose values share an identity.

workspacestring

Act in this workspace (its slug). Omitted: the token's bound workspace, then the organization's default. Never ambient - there is no switch-workspace mutation on this door.

Response

The capability's JSON result.

objectstring

The resource type, when the result is one resource.

Changes

No recorded changes to this operation across all 1 revision of this API.