Model-Agnostic Explainers

Explainers that only need a model's input/output behavior (perturb-and-observe), with no access to gradients or internal activations. More...

Collaboration diagram for Model-Agnostic Explainers:

Files
file	kernel_shap.hpp
	KernelSHAP – model-agnostic Shapley value approximation via weighted linear regression (charter Part 1, Phase 3; theory: xai_context.aDNA's technique_shap.md).
file	lime.hpp
	LIME – local interpretable model-agnostic explanations (charter Part 1, Phase 3; theory: xai_context.aDNA's technique_lime.md).
file	linear_algebra.hpp
	Small, dense linear-system solve – shared by weighted_linear_regression.hpp (Phase 3's LIME/KernelSHAP) and gaussian_process.hpp (this campaign's GP-BO surrogate).
file	matrix_decompositions.hpp
	Small dense decompositions on the host: symmetric eigensolver, power iteration, QR and SVD (roadmap FND-4).
file	pdp.hpp
	Partial Dependence Plot – a global marginal-effect technique, sweeping one feature's value while averaging the model's response over a background set (charter addition 2026-09-19, see charter Decisions Log).
file	weighted_linear_regression.hpp
	Weighted least squares via normal equations – the shared fitting primitive Phase 3's LIME and KernelSHAP explainers both reduce to.

Detailed Description

Explainers that only need a model's input/output behavior (perturb-and-observe), with no access to gradients or internal activations.