|
pulsatrix 1.1.0
|
Tools that don't depend on a particular explainer: perturbation explainers that only need a model's input/output behavior, explanation-quality metrics (faithfulness, randomization, complexity), the null-model baseline, and dense matrix decompositions for analysing activations and weights. More...

Files | |
| file | anchors.hpp |
| Anchors (Ribeiro, Singh and Guestrin, "Anchors: High-Precision Model-Agnostic
Explanations", AAAI 2018): an if-then rule around one input that keeps the model's prediction with high probability, whatever the other features do (XAI-4). | |
| file | explanation_agreement.hpp |
| Whether two models explain the same inputs with the same evidence (roadmap KD-2): a distilled student against its teacher, a fine-tuned model against its base, or any two models that take the same input. | |
| file | explanation_metrics.hpp |
| Explanation-quality metrics in the Quantus families (roadmap XAI-5): faithfulness (deletion and insertion curves, with ROAD's imputation), randomization (the model-parameter randomization test) and complexity (sparseness and complexity). | |
| file | global_sensitivity.hpp |
| Global sensitivity analysis: Morris elementary effects and Sobol indices (CFS-4). | |
| file | ice.hpp |
| Individual conditional expectation (ICE), its centered and derivative forms, two-feature partial dependence (CFS-1) and accumulated local effects (CFS-2). | |
| 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 | null_model_baseline.hpp |
| The baseline rule as one call (roadmap XAI-6): run any explainer, probe or featurizer on the trained model and on a re-initialized ("null") model, and compare. | |
| 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 | prototypes.hpp |
| Explaining by example (XAI-4): the background inputs nearest one input that the model treats the same way and differently, and ProtoDash's weighted prototypes that summarize a dataset (Gurumoorthy, Dhurandhar, Cecchi and Aggarwal, ICDM 2019). | |
| file | rule_extraction.hpp |
| Rules from trees, run by the Datalog engine (roadmap KD-3): a surrogate or distilled tree becomes a Datalog program that classifies the same way. | |
| file | sensitivity.hpp |
| Local sensitivity: one-at-a-time input changes and occlusion (CFS-3). | |
| file | surrogate_tree.hpp |
| A global surrogate: a shallow decision tree fitted to a model's predictions, with its fidelity to the model on held-out inputs (XAI-4; TREPAN, Craven and Shavlik 1996). | |
| 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. | |
Tools that don't depend on a particular explainer: perturbation explainers that only need a model's input/output behavior, explanation-quality metrics (faithfulness, randomization, complexity), the null-model baseline, and dense matrix decompositions for analysing activations and weights.