Skip to content
Hayonix

API reference · Schema

EvaluationResults

Aggregate results so far (final once ended)

  • rowsobjectrequired

    Rows by status

    Show 5 fields of rows
    • totalintegerrequired

      Rows in the dataset

    • judgedintegerrequired

      Rows that received a verdict

    • erroredintegerrequired

      Rows that could not be judged (a failed call, a missing column, no usable judge answer)

    • skippedintegerrequired

      Never finished: the run ended early

    • openintegerrequired

      Rows still being worked on

  • passedinteger | nullrequired

    Judged rows that pass; null when the evaluation defines no passing labels or score, and in mode `pairwise`

  • pass_ratenumber | nullrequired

    Passed ÷ judged, 0–1

  • labelsarray of object | nullrequired

    Mode `label`: every choice with its count, zeros included; null in other modes

    Show 2 fields of labels
    • labelstringrequired

      One of `label.choices`

    • countintegerrequired

      Judged rows given this label

  • scoresobject | nullrequired

    Mode `grade`: statistics of the scores; null in other modes

    Show 5 fields of scores
    • meannumber | nullrequired

      Mean score; null before any row is judged

    • std_devnumber | nullrequired

      Population standard deviation of the scores; null before any row is judged

    • minnumber | nullrequired

      Lowest score given; null before any row is judged

    • maxnumber | nullrequired

      Highest score given; null before any row is judged

    • histogramarray of objectrequired

      Scores over `grade.min`–`grade.max`: one bucket per whole number when there are at most 20, else 20 equal-width buckets

      Show 3 fields of histogram
      • fromnumberrequired

        Lower bound of the bucket (inclusive)

      • tonumberrequired

        Upper bound of the bucket; equal to `from` when each bucket is one whole-number score

      • countintegerrequired

        Judged rows whose score falls in the bucket

  • pairwiseobject | nullrequired

    Mode `pairwise`: how the two candidates compared; null in other modes

    Show 5 fields of pairwise
    • a_winsintegerrequired

      Pairs where both passes chose A

    • b_winsintegerrequired

      Pairs where both passes chose B

    • tiesintegerrequired

      Pairs where both passes called a tie

    • inconsistentintegerrequired

      Pairs whose two judging passes (A first, B first) disagreed

    • a_win_ratenumber | nullrequired

      A wins ÷ (A wins + B wins + ties), 0–1, over consistent pairs only; null before any consistent pair

Example
{
  "rows": {
    "total": 1,
    "judged": 1,
    "errored": 1,
    "skipped": 1,
    "open": 1
  },
  "passed": 1,
  "pass_rate": 1.5,
  "labels": [
    {
      "label": "string",
      "count": 1
    }
  ],
  "scores": {
    "mean": 1.5,
    "std_dev": 1.5,
    "min": 1.5,
    "max": 1.5,
    "histogram": [
      {
        "from": 1.5,
        "to": 1.5,
        "count": 1
      }
    ]
  },
  "pairwise": {
    "a_wins": 1,
    "b_wins": 1,
    "ties": 1,
    "inconsistent": 1,
    "a_win_rate": 1.5
  }
}