OptionalbadgeSemantic badge color for UI rendering: 'green' | 'amber' | 'red' | 'blue' | 'gray'.
OptionalbandNormalized status tier key (e.g. "high", "medium", "low").
OptionalclassPredicted class label, present for classification problems.
OptionaldriversTop signed per-record drivers behind this prediction (P1-5), present only for models with exact
per-row attribution (linear). Feature names are post-preprocessing output columns; UIs collapse/humanize
them. value > 0 pushed the score up, < 0 down. Absent for tree/ensemble/multiclass models.
OptionaliconFontAwesome icon name (e.g. 'fa-circle-check', 'fa-triangle-exclamation').
True when this record contributed a development row to the model's Training Snapshot (its id is a development row id of the snapshot's manifest): per row, so a record held out in the locked holdout, or never in the snapshot, is false. Always false for a model trained without a snapshot.
The model that produced the prediction (lineage).
Classification or regression.
Numeric model output: probability (classification) or value (regression).
ISO-8601 UTC timestamp of when this prediction was produced. Lets write-back persist a
dedicated "last scored at" column on the target entity via OutputMapping
({ "LastScoredAt": "$.scoredAt" }) — distinct from the row's whole-record __mj_UpdatedAt,
which moves on any edit, not just scoring.
OptionalscoreDisplay label for the score column (e.g. "Renewal Probability", "Default Risk").
OptionalstatusQualitative status label evaluated against model OutcomeConfig (e.g. "High", "Low Risk", "Severe").
OptionalstatusDisplay label for the status column (e.g. "Renewal Status", "Risk Level").
The target/label the model predicts.
The structured payload a successful scoring run carries on its
RecordResult.