OptionalacademiClawChecks
academiClawChecks?: MetricValidationAcademiClawCheck[]
OptionalagenticGraphRagChecks
agenticGraphRagChecks?: MetricValidationAgenticGraphRagCheck[]
OptionalagentScenarioTestChecks
agentScenarioTestChecks?: MetricValidationAgentScenarioTestCheck[]
OptionalarchitectureRealityChecks
architectureRealityChecks?: MetricValidationArchitectureRealityCheck[]
bioinformaticsAgentChecks?: MetricValidationBioinformaticsAgentCheck[]
OptionalbusinessWorkflowChecks
businessWorkflowChecks?: MetricValidationBusinessWorkflowCheck[]
OptionalccPluginEvalChecks
ccPluginEvalChecks?: MetricValidationCcPluginEvalCheck[]
OptionalchipBenchmarkChecks
chipBenchmarkChecks?: MetricValidationChipBenchmarkCheck[]
OptionalcoderCupChecks
coderCupChecks?: MetricValidationCoderCupCheck[]
OptionalconfidenceSummary
confidenceSummary?: DiagnosticConfidenceSummary
OptionalconfounderControlChecks
confounderControlChecks?: MetricValidationConfounderControlCheck[]
OptionalcontinualLearningChecks
continualLearningChecks?: MetricValidationContinualLearningCheck[]
OptionalcooperBenchChecks
cooperBenchChecks?: MetricValidationCooperBenchCheck[]
correlationRatio
correlationRatio: number
OptionalcounterfactualChecks
counterfactualChecks?: MetricValidationCounterfactualCheck[]
OptionaldataAgentAnalyticalChecks
dataAgentAnalyticalChecks?: MetricValidationDataAgentAnalyticalCheck[]
OptionaldatasetHash
datasetHash?: string
OptionalembodiedAgentChecks
embodiedAgentChecks?: MetricValidationEmbodiedAgentCheck[]
OptionalevaluatorSuiteChecks
evaluatorSuiteChecks?: MetricValidationEvaluatorSuiteCheck[]
evidenceCoverage
evidenceCoverage: number
OptionalgateMode
gateMode?: "ci" | "lifecycle"
OptionalguardbenchChecks
guardbenchChecks?: MetricValidationGuardbenchCheck[]
OptionalhermesBenchChecks
hermesBenchChecks?: MetricValidationHermesBenchCheck[]
OptionalhumanStudyBenchChecks
humanStudyBenchChecks?: MetricValidationHumanStudyBenchCheck[]
OptionalinferenceOptimizationChecks
inferenceOptimizationChecks?: MetricValidationInferenceOptimizationCheck[]
integrityIndex
integrityIndex: number
OptionaljavaCodingAgentChecks
javaCodingAgentChecks?: MetricValidationJavaCodingAgentCheck[]
OptionalkubernetesOperationalAgentChecks
kubernetesOperationalAgentChecks?: MetricValidationKubernetesOperationalAgentCheck[]
layerScores
layerScores: LayerScore[]
OptionallegacyBenchChecks
legacyBenchChecks?: MetricValidationLegacyBenchCheck[]
OptionallifecycleObservabilityChecks
lifecycleObservabilityChecks?: MetricValidationLifecycleObservabilityCheck[]
OptionallivingEnvironmentChecks
livingEnvironmentChecks?: MetricValidationLivingEnvironmentCheck[]
OptionalmirageDrugRepositioningChecks
mirageDrugRepositioningChecks?: MetricValidationMirageDrugRepositioningCheck[]
OptionalmobileAgentChecks
mobileAgentChecks?: MetricValidationMobileAgentCheck[]
modalityTransformationChecks?: MetricValidationModalityTransformationCheck[]
OptionalnetworkTroubleshootingChecks
networkTroubleshootingChecks?: MetricValidationNetworkTroubleshootingCheck[]
OptionalopenCodeLabChecks
openCodeLabChecks?: MetricValidationOpenCodeLabCheck[]
OptionaloutcomeAlignmentChecks
outcomeAlignmentChecks?: MetricValidationOutcomeAlignmentCheck[]
OptionalparallelResearchSkillChecks
parallelResearchSkillChecks?: MetricValidationParallelResearchSkillCheck[]
OptionalpentestBenchmarkChecks
pentestBenchmarkChecks?: MetricValidationPentestBenchmarkCheck[]
OptionalpersonaAgentChecks
personaAgentChecks?: MetricValidationPersonaAgentCheck[]
OptionalprocessEvidenceChecks
processEvidenceChecks?: MetricValidationProcessEvidenceCheck[]
questionScores
questionScores: QuestionScore[]
OptionalragChunkingTechniqueChecks
ragChunkingTechniqueChecks?: MetricValidationRagChunkingTechniqueCheck[]
OptionalragPipelineChecks
ragPipelineChecks?: MetricValidationRagPipelineCheck[]
OptionalrankingStabilityChecks
OptionalravigBenchChecks
ravigBenchChecks?: MetricValidationRavigBenchCheck[]
OptionalrealignSimulationChecks
realignSimulationChecks?: MetricValidationRealignSimulationCheck[]
OptionalrequireAcademiClawProof
requireAcademiClawProof?: boolean
OptionalrequireAgenticGraphRagProof
requireAgenticGraphRagProof?: boolean
OptionalrequireAgentScenarioTestProof
requireAgentScenarioTestProof?: boolean
OptionalrequireArchitectureRealityProof
requireArchitectureRealityProof?: boolean
requireBioinformaticsAgentProof?: boolean
OptionalrequireCcPluginEvalProof
requireCcPluginEvalProof?: boolean
OptionalrequireChipBenchmarkProof
requireChipBenchmarkProof?: boolean
OptionalrequireCoderCupProof
requireCoderCupProof?: boolean
OptionalrequireCooperBenchProof
requireCooperBenchProof?: boolean
OptionalrequireEvaluatorSuiteProof
requireEvaluatorSuiteProof?: boolean
OptionalrequireGuardbenchMetricProof
requireGuardbenchMetricProof?: boolean
OptionalrequireHermesBenchProof
requireHermesBenchProof?: boolean
OptionalrequireHumanStudyBenchProof
requireHumanStudyBenchProof?: boolean
OptionalrequireInferenceOptimizationProof
requireInferenceOptimizationProof?: boolean
OptionalrequireJavaCodingAgentProof
requireJavaCodingAgentProof?: boolean
OptionalrequireKubernetesOperationalAgentProof
requireKubernetesOperationalAgentProof?: boolean
OptionalrequireLegacyBenchProof
requireLegacyBenchProof?: boolean
OptionalrequireLegalCodeRagProof
requireLegalCodeRagProof?: boolean
OptionalrequireLivingEnvironmentProof
requireLivingEnvironmentProof?: boolean
OptionalrequireMirageDrugRepositioningProof
requireMirageDrugRepositioningProof?: boolean
OptionalrequireMirageRagMetricProof
requireMirageRagMetricProof?: boolean
OptionalrequireMobileAgentProof
requireMobileAgentProof?: boolean
OptionalrequireNetworkTroubleshootingProof
requireNetworkTroubleshootingProof?: boolean
OptionalrequireOpenCodeLabProof
requireOpenCodeLabProof?: boolean
OptionalrequireParallelResearchSkillProof
requireParallelResearchSkillProof?: boolean
OptionalrequirePentestBenchmarkProof
requirePentestBenchmarkProof?: boolean
OptionalrequirePersonaAgentProof
requirePersonaAgentProof?: boolean
OptionalrequireRagasNotebookProof
requireRagasNotebookProof?: boolean
OptionalrequireRagChunkingTechniqueProof
requireRagChunkingTechniqueProof?: boolean
OptionalrequireRagEvaluationPipelineProof
requireRagEvaluationPipelineProof?: boolean
OptionalrequireRavigBenchProof
requireRavigBenchProof?: boolean
OptionalrequireRealignSimulationProof
requireRealignSimulationProof?: boolean
OptionalrequireResumeRagEvaluatorProof
requireResumeRagEvaluatorProof?: boolean
OptionalrequireScientificLiteratureProof
requireScientificLiteratureProof?: boolean
OptionalrequireSecureVibeBenchProof
requireSecureVibeBenchProof?: boolean
OptionalrequireSubtleMemoryProof
requireSubtleMemoryProof?: boolean
OptionalrequireTraceEvaluationProof
requireTraceEvaluationProof?: boolean
OptionalrequireWebEvalDatasetProof
requireWebEvalDatasetProof?: boolean
OptionalresumeRagEvaluatorChecks
resumeRagEvaluatorChecks?: MetricValidationResumeRagEvaluatorCheck[]
OptionalsafetyUtilityChecks
safetyUtilityChecks?: MetricValidationSafetyUtilityCheck[]
OptionalscientificLiteratureChecks
scientificLiteratureChecks?: MetricValidationScientificLiteratureCheck[]
OptionalsecureVibeBenchChecks
secureVibeBenchChecks?: MetricValidationSecureVibeBenchCheck[]
OptionalsignedEvidenceRefs
signedEvidenceRefs?: QuestionScoreSignedEvidenceRef[]
OptionalsourceRefs
sourceRefs?: string[]
OptionalstrategicInteractionChecks
strategicInteractionChecks?: MetricValidationStrategicInteractionCheck[]
OptionalsubtleMemoryChecks
subtleMemoryChecks?: MetricValidationSubtleMemoryCheck[]
toolSandboxChecks?: MetricValidationToolSandboxCheck[]
OptionaltraceEvaluationChecks
traceEvaluationChecks?: MetricValidationTraceEvaluationCheck[]
trustLabel
trustLabel: TrustLabel
unsupportedClaimCount
unsupportedClaimCount: number
OptionalvalidationFacetChecks
validationFacetChecks?: MetricValidationFacetCheck[]
OptionalwebEvalDatasetChecks
webEvalDatasetChecks?: MetricValidationWebEvalDatasetCheck[]