Enum ComparisonDesign 

pub enum ComparisonDesign {
    ObservedOnly,
    ExpectedOutcome,
    BaselineRun {
        baseline_ref: EntityRef,
    },
    PairedRuns {
        observed_ref: EntityRef,
        comparison_ref: EntityRef,
    },
    PairedScopes {
        observed_scope: EvaluationScope,
        comparison_scope: EvaluationScope,
    },
    Ablation {
        removed_refs: Vec<EntityRef>,
    },
    Counterfactual {
        redacted_summary: String,
    },
    RepeatedExperiment {
        cohort_ref: EntityRef,
    },
}

How an evaluation should compare an observed outcome.

Variants

ObservedOnly

Judge the observed run or turn only.

ExpectedOutcome

Judge the observed result against expected criteria only.

BaselineRun

Compare the observed result with a baseline run.

Fields

baseline_ref: EntityRef

Baseline run or trace ref used as comparison evidence.

PairedRuns

Compare two recorded runs.

Fields

observed_ref: EntityRef

Observed run ref.

comparison_ref: EntityRef

Comparison run ref.

PairedScopes

Compare two durable evaluation scopes without inventing entity refs.

Fields

observed_scope: EvaluationScope

Observed scope.

comparison_scope: EvaluationScope

Comparison scope.

Ablation

Compare the observed result with one or more evidence refs removed.

Fields

removed_refs: Vec<EntityRef>

Evidence refs removed for the ablation comparison.

Counterfactual

Ask for a counterfactual judgment without claiming measurement.

Fields

redacted_summary: String

Safe summary of the counterfactual condition.

RepeatedExperiment

Compare a cohort of repeated experiments.

Fields

cohort_ref: EntityRef

Cohort or experiment ref used as comparison evidence.

Implementations

impl ComparisonDesign

pub fn supports_measured_confidence(&self) -> bool

Returns true when this design can support measured confidence if metric deltas are also present.

pub fn comparison_refs(&self) -> Vec<EntityRef>

Returns comparison refs available for validation and report evidence.

pub fn has_comparison_evidence(&self) -> bool

Returns true when this design carries comparison evidence.

Trait Implementations

impl Clone for ComparisonDesign

fn clone(&self) -> ComparisonDesign

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for ComparisonDesign

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for ComparisonDesign

fn default() -> ComparisonDesign

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ComparisonDesign

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ComparisonDesign

fn eq(&self, other: &ComparisonDesign) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ComparisonDesign

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for ComparisonDesign

impl StructuralPartialEq for ComparisonDesign