Skip to content
KortexyaKortexyaReasoning Layer SDK

Interface: BayesianPredictRequest

@kortexya/reasoninglayer

@kortexya/reasoninglayer / BayesianPredictRequest

Interface: BayesianPredictRequest

Section titled “Interface: BayesianPredictRequest”

Defined in: src/types/inference.ts:1026

Request for Bayesian prediction.

Remarks

Section titled “Remarks”

Dual input mode: Provide EITHER goal OR goal_id.

Unlike other inference requests, Bayesian prediction requires an effect_var naming the variable that holds the FuzzyNumber effect.

Properties

Section titled “Properties”

conformal?

Section titled “conformal?”

optional conformal?: number | null

Defined in: src/types/inference.ts:1038

Optional conformal coverage (e.g., 0.9 for 90% coverage).

effectVar

Section titled “effectVar”

effectVar: string

Defined in: src/types/inference.ts:1028

Name of the variable that holds the FuzzyNumber effect.

goal?

Section titled “goal?”

optional goal?: TermInputDto | null

Defined in: src/types/inference.ts:1030

Inline goal (should bind a FuzzyNumber variable). Mutually exclusive with goal_id.

goalId?

Section titled “goalId?”

optional goalId?: string | null

Defined in: src/types/inference.ts:1032

Saved goal reference. Mutually exclusive with goal.

maxDepth?

Section titled “maxDepth?”

optional maxDepth?: number

Defined in: src/types/inference.ts:1034

Maximum proof depth (default: 100).

minDegree?

Section titled “minDegree?”

optional minDegree?: number

Defined in: src/types/inference.ts:1036

Minimum degree threshold.

robust?

Section titled “robust?”

optional robust?: boolean

Defined in: src/types/inference.ts:1040

Use robust aggregation (Student-t/Huber) to downweight outliers.

saveGoal?

Section titled “saveGoal?”

optional saveGoal?: boolean

Defined in: src/types/inference.ts:1042

If true, save the goal for later reuse (returns goal_id in response).