38 capabilities
26 of 38 have a bound kernel or engine. States are shown as the registry records them; a request fails closed wherever an adapter, specialist model or governed data is still missing.
| 方法 | Capability ID | 状态 | 运行于 |
|---|---|---|---|
| Robust Distribution | risk.capability.universal-mathematics-statistics.robust.distribution.v1 |
Reference implementation | Julia · frontier_risk_math.robust_distribution |
| Empirical Distribution | risk.capability.universal-mathematics-statistics.empirical.distribution.v1 |
Reference implementation | Python · stats.empirical_distribution |
| Bayesian Updating | risk.capability.universal-mathematics-statistics.bayesian.updating.v1 |
Reference implementation | Julia · frontier_risk_math.beta_binomial |
| Hierarchical Bayesian | risk.capability.universal-mathematics-statistics.hierarchical.bayesian.v1 |
Adapter required | – |
| Extreme Value | risk.capability.universal-mathematics-statistics.extreme.value.v1 |
Reference implementation | – |
| Tail Risk | risk.capability.universal-mathematics-statistics.tail.risk.v1 |
Reference implementation | Python · tail.pot_gpd |
| Copula Dependency | risk.capability.universal-mathematics-statistics.copula.dependency.v1 |
Adapter required | – |
| Tail Dependence | risk.capability.universal-mathematics-statistics.tail.dependence.v1 |
Adapter required | Python · dependence.tail_empirical |
| Monte Carlo | risk.capability.universal-mathematics-statistics.monte.carlo.v1 |
Reference implementation | Python · simulation.monte_carlo |
| Latin Hypercube | risk.capability.universal-mathematics-statistics.latin.hypercube.v1 |
Reference implementation | Python · sampling.latin_hypercube |
| Importance Sampling | risk.capability.universal-mathematics-statistics.importance.sampling.v1 |
Reference implementation | Python · sampling.importance |
| Sequential Monte Carlo | risk.capability.universal-mathematics-statistics.sequential.monte.carlo.v1 |
Adapter required | – |
| Kalman Filter | risk.capability.universal-mathematics-statistics.kalman.filter.v1 |
Adapter required | – |
| Extended Kalman | risk.capability.universal-mathematics-statistics.extended.kalman.v1 |
Adapter required | – |
| Unscented Kalman | risk.capability.universal-mathematics-statistics.unscented.kalman.v1 |
Adapter required | – |
| Particle Filter | risk.capability.universal-mathematics-statistics.particle.filter.v1 |
Adapter required | – |
| Markov Chain | risk.capability.universal-mathematics-statistics.markov.chain.v1 |
Adapter required | Python · markov.transition |
| Hidden Markov | risk.capability.universal-mathematics-statistics.hidden.markov.v1 |
Adapter required | – |
| Change Point | risk.capability.universal-mathematics-statistics.change.point.v1 |
Reference implementation | Python · change.cusum |
| Anomaly Detection | risk.capability.universal-mathematics-statistics.anomaly.detection.v1 |
Reference implementation | Python · anomaly.robust_mad |
| Survival Analysis | risk.capability.universal-mathematics-statistics.survival.analysis.v1 |
Adapter required | Python · survival.kaplan_meier |
| Reliability | risk.capability.universal-mathematics-statistics.reliability.v1 |
Adapter required | Python · reliability.weibull |
| Fault Tree | risk.capability.universal-mathematics-statistics.fault.tree.v1 |
Adapter required | – |
| Event Tree | risk.capability.universal-mathematics-statistics.event.tree.v1 |
Adapter required | – |
| Bayesian Network | risk.capability.universal-mathematics-statistics.bayesian.network.v1 |
Adapter required | – |
| Information Theory | risk.capability.universal-mathematics-statistics.information.theory.v1 |
Reference implementation | Python · information.mutual_information |
| Entropy and Concentration | risk.capability.universal-mathematics-statistics.entropy.and.concentration.v1 |
Reference implementation | Julia · frontier_risk_math.concentration |
| Correlation | risk.capability.universal-mathematics-statistics.correlation.v1 |
Reference implementation | Python · stats.correlation |
| Regression | risk.capability.universal-mathematics-statistics.regression.v1 |
Adapter required | Python · regression.ols |
| Gaussian Process | risk.capability.universal-mathematics-statistics.gaussian.process.v1 |
Adapter required | Python · gaussian_process.rbf |
| Spatial Statistics | risk.capability.universal-mathematics-statistics.spatial.statistics.v1 |
Adapter required | Python · spatial.morans_i |
| Geostatistics | risk.capability.universal-mathematics-statistics.geostatistics.v1 |
Adapter required | Python · geostatistics.ordinary_kriging |
| Bootstrap | risk.capability.universal-mathematics-statistics.bootstrap.v1 |
Reference implementation | Python · stats.bootstrap_mean_ci |
| Global Sensitivity | risk.capability.universal-mathematics-statistics.global.sensitivity.v1 |
Connected | Python · sensitivity.sobol_outputs |
| Shapley Sensitivity | risk.capability.universal-mathematics-statistics.shapley.sensitivity.v1 |
Adapter required | Python · sensitivity.shapley_coalitions |
| Optimisation under Uncertainty | risk.capability.universal-mathematics-statistics.optimization.under.uncertainty.v1 |
Adapter required | Python · optimization.robust_minimax |
| Multi-Criteria Decision | risk.capability.universal-mathematics-statistics.multi.criteria.decision.v1 |
Adapter required | Python · decision.weighted_mcda |
| Real Options | risk.capability.universal-mathematics-statistics.real.options.v1 |
Adapter required | Python · decision.real_option_binomial |
Methods, data and supports
- Method families
- robust statistics, Bayesian inference, extreme value, Monte Carlo, copula dependence, stochastic process, time series, change detection, survival reliability, spatial statistics, geostatistics, optimisation, decision analysis, information theory
- 领域
- cross-domain
- Compute planes
- Julia, TypeScript
- Source classes
- governed-observations, sealed-risk-data-cut
- Spatial supports
- point, object, grid, region, network
- Temporal supports
- instant, series, window, scenario
状态
The Global Risks Index 的方法、结构和定义为预备性工作草案（2026），供审阅和评论，不供实施。在从受治理的证据截取中发布版本之前，不会出现任何数值；届时数值将附有区间、类别、来源及其更正途径。模拟器以您选择的数字运行已发布的方法，绝不显示 NXS-GRX 数值。
NXS-GRX 不是什么
NXS-GRX 是研究和风险分析信息。它不是信用评级或 ESG 评级，不使用任何评级尺度；它不是金融工具的基准，不是官方统计，不是紧急警报或官方分类，也不是建议。不得用于评估自然人。风险等级是已发布尺度上的区间，绝不是对国家或个人的排名。
机构与来源
The Nexus Consortium is stewarded by three independent not-for-profit institutions: The Global Centre for Risk and Innovation (GCRI), through GCRI US in Washington, DC and GCRI Canada in Ontario, with GCRI Canada as Lead Institution, Consortium Secretariat and lead contracting organisation; The Global Risks Forum (GRF); and The Global Risks Alliance (GRA). Technology, infrastructure and service providers work with the Consortium at arm’s length under written agreements, like every other external party in the public-private-planet model, and hold no role in its stewardship.
每个数值均附有其来源的署名，这些来源保留各自的许可。外部名称仅为互操作性而引用。Nexus 撰写的文本拟在发布时采用 CC BY 4.0。
Avis en français
La méthodologie et les définitions du NXS-GRX sont un projet de travail préparatoire (2026). Le NXS-GRX est une information de recherche et d’analyse des risques : ni notation, ni indice de référence financier, ni statistique officielle, ni alerte, ni conseil. Les classes de risque sont des bandes sur une échelle publiée, non des classements.