Member Junction
    Preparing search index...

    The outcome of building a prediction from a plan.

    interface BuildPredictionResult {
        errorMessage: string;
        Gate?: BuildGateDecision;
        heldReason: string;
        leaderboard?: MLLeaderboardEntryPayload[];
        leakageFlagged: boolean;
        model?: MJMLModelEntity;
        modelId?: string;
        pipeline?: MJMLTrainingPipelineEntity;
        pipelineId?: string;
        published: boolean;
        readyToPublish: boolean;
        success: boolean;
        trust?: TrustVerdict;
        warnings?: FeatureStepWarning[];
    }
    Index

    Properties

    errorMessage: string

    A clean error message when the build failed; else null.

    The training run's stored gate decision; absent when the build failed before a run stored one.

    heldReason: string

    When not published, the plain reason (leakage, a calibration hold, the trust verdict, auto-publish off, or the promotion gate's refusal); else null.

    The leaderboard of the build's one training run.

    leakageFlagged: boolean

    Whether training flagged a leakage warning (held for analyst review).

    The trained model entity (present on successful build).

    modelId?: string

    The trained MJ: ML Models id (present once training completes).

    The created pipeline entity (present once pipeline is created).

    pipelineId?: string

    The created MJ: ML Training Pipelines id (present once the pipeline is created).

    published: boolean

    Whether the model was published into the business catalog.

    readyToPublish: boolean

    True when the model was not published only because auto-publish was off: it shipped under its protocol, training flagged no leakage and it holds no calibration hold, so the promotion gate may be asked to publish it.

    success: boolean

    Whether the build (pipeline create + train) succeeded.

    trust?: TrustVerdict

    The plain-language trust verdict: the training run's stored gate decision rendered as copy.

    warnings?: FeatureStepWarning[]

    Structured warnings emitted during plan translation or training (e.g. dropped candidate features).