Expand description
wm-simulation — Monte Carlo simulation, counterfactual estimation, forecasting, and prediction calibration.
N21: Ports v2’s wm-evolution MC suite capabilities for v4:
- Monte Carlo simulation — Bayesian MC, Quasi-MC, sensitivity analysis
- Counterfactual estimation — synthetic control projection for causal impact
- Forecasting — time series forecasting with confidence intervals
- Prediction calibration — Brier scorecard with the Murphy decomposition
- Bayesian optimization — GP surrogates + Expected Improvement search
- Information-theoretic measures — entropy, mutual information
This enables the SelfModel to forecast outcomes, the Dream cycle to simulate counterfactuals, and the Homeostatic loop to simulate action consequences before executing them.
Re-exports§
pub use bayesian::BayesianOptimizer;pub use bayesian::Expr;pub use bayesian::GaussianProcess;pub use bayesian::OptimizationStep;pub use bayesian::expected_improvement;pub use bayesian::norm_cdf;pub use bayesian::norm_pdf;pub use calibration::BrierScorecard;pub use calibration::CalibrationBin;pub use calibration::CalibrationPrediction;pub use calibration::CalibrationStore;pub use claims::CALIBRATION_PRIOR_SAMPLES;pub use claims::Claim;pub use claims::ClaimStatus;pub use claims::ClaimsLedger;pub use claims::ValidationEvent;pub use counterfactual::CounterfactualEstimator;pub use counterfactual::CounterfactualResult;pub use forecasting::ForecastMethod;pub use forecasting::ForecastResult;pub use forecasting::Forecaster;pub use monte_carlo::Distribution;pub use monte_carlo::McConfig;pub use monte_carlo::McResult;pub use monte_carlo::MonteCarloSimulator;pub use pce::Pce;pub use pce::SuperforecasterResult;pub use pce::latin_hypercube;pub use pce::superforecaster;pub use rare_event::ImportanceResult;pub use rare_event::SubsetResult;pub use rare_event::importance_sampling;pub use rare_event::subset_simulation;pub use sde::DriftType;pub use sde::MlMcResult;pub use sde::SdeConfig;pub use sde::SdeResult;pub use sde::Solver;pub use sde::solve;pub use sde::solve_mlmc;pub use sensitivity::SensitivityAnalyzer;pub use sensitivity::SensitivityIndex;pub use sensitivity::SensitivityResult;
Modules§
- bayesian
- Gaussian Process surrogates and Bayesian optimization.
- calibration
- Prediction calibration — Brier scorecard with the Murphy decomposition.
- claims
- Claims ledger — the prescience track record as a first-class store.
- counterfactual
- Counterfactual estimation — synthetic control projection for causal impact measurement.
- forecasting
- Time series forecasting with confidence intervals.
- monte_
carlo - Monte Carlo simulation — sampling-based estimation.
- pce
- Superforecaster pipeline — LHS sampling → polynomial chaos expansion (PCE) → Sobol’ sensitivity indices → Bayesian optimization.
- rare_
event - Rare-event probability estimation.
- sde
- Stochastic differential equation solvers — Euler–Maruyama and Milstein.
- sensitivity
- Sensitivity analysis — measures how uncertainty in model inputs contributes to uncertainty in the output.