RAG-007RAG · Staying truthfullayaeval.StrictGroundedness

Strict Groundedness

A yes or no: is every claim proven? One gap fails it.

Simulation state:

When it passes

All claims proven.

Threshold satisfied: evaluation score >= 0.50.

When it fails

One claim unproven — fail.

Violation detected: execution flagged for human review or fallback routing.

SDK Specification

Parameter	Value	Description
Class	StrictGroundedness	Python evaluator class in layaeval
Required Fields	"retrieved_context", "response"	Arguments expected in the call signature
Default Threshold	>= 0.50	Passes when quality score is at or above this value
Category	RAG Evaluation	Staying truthful (Does every line come from the pages, with nothing made up?)

Python Example

pip install layaeval

strict-groundedness.py

1from layaeval import StrictGroundedness
2
3metric = StrictGroundedness(threshold=0.50)  # passes at or above 0.50
4
5res = metric(
6    retrieved_context="Paris is the capital of France, with 2.1M residents.",
7    response="Paris is the capital of France.",
8)
9
10print(res.passed, res.value, res.confidence)