Skip to main content
GET
JudgeCalibrationAPI mirrors erdo_judge_calibration.

Authorizations

Authorization
string
header
required

An Erdo API key (erdo_api_...) or scoped token (erdo_token_...).

Query Parameters

project_slug
string
limit
integer<int32>
Required range: -2147483648 <= x <= 2147483647

Response

Success response

defects
ExperimentDefect is one human "this variant is broken" verdict from the ledger · object[]

ledger — the seeded complement to each judge's misordered_examples. They are not attributed to any single judge (a defect scores no judge's ordering); it is a standalone failure signal judge generation reads to propose a lens that would have caught the broken page before it shipped. Bounded per read.

judged_bets
integer<int64>
judges
JudgeCalibrationStats is one judge's track record: how often its predictions · object[]
observations_scanned
integer<int64>

computation saw (after RBAC filtering) — a hint that the limit was hit.

random_arm_bets
integer<int64>

judge screening (a variant carrying random_arm=true) or was screened by at least one judge. The ratio is the permanent random arm's headline number: with too few random-arm bets the engine cannot know whether its judges beat random selection at all — the comparison needs exactly the labels the judges saved. Counted at the (experiment, variant) grain over measured variants.