Paper: arXiv 2509.08183
Authors: Crystal Rust
Abstract
We introduce a new risk modeling framework where chaotic attractors shape the geometry of Bayesian inference. By combining heavy-tailed priors with Lorenz and Rossler dynamics, the models naturally generate volatility clustering, fat tails, and extreme events. We compare two complementary approaches: Model A, which emphasizes geometric stability, and Model B, which highlights rare bursts using Fibonacci diagnostics. Together, they provide a dual perspective for systemic risk analysis, linking Black Swan theory to practical tools for stress testing and volatility monitoring.
Complexity vs Empirical Score
- Math Complexity: 8.0/10
- Empirical Rigor: 3.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper is dense with advanced mathematics, including chaotic dynamics, Bayesian inference, and complex geometric diagnostics, while the empirical evidence is limited to simulated data without real-world backtests or implementation details.
Research Flowchart
flowchart TD
A["Research Goal: Model Black Swan Events"] --> B{"Data: Historical Volatility &<br>Extreme Event Distributions"}
B --> C["Methodology: Chaotic Bayesian Inference"]
C --> D["Model A: Lorenz Dynamics<br>Geometric Stability"]
C --> E["Model B: Rossler Dynamics<br>Fibonacci Rare Bursts"]
D --> F["Computational Process:<br>MCMC Sampling<br>Strange Attractors"]
E --> F
F --> G["Outcomes: Volatility Clustering<br>Heavy Tails & Stress Testing"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper introduces a dual‑model framework for chaotic Bayesian inference, comprising Model A (Poincaré–Mahalanobis) that anchors inference in geometric attractor structure and Model B (Correlation–Integral with Fibonacci diagnostics) that emphasizes recurrence statistics and volatility clustering
Source sentence
7 Conclusion We introduced a dual-model framework for chaotic inference and rare-event detection.
Assumes 2
- Posterior distributions are constrained to lie on Lorenz‑ or Rössler‑type chaotic attractors. model
Source sentence
By letting posterior distributions live on Lorenz- or R¨ossler-type attractors, and using 2 heavy-tailed priors, we obtain probability structures that exhibit endogenous volatility clustering, bursts, and fat tails.
- Heavy‑tailed (fat‑tailed) priors are used for parameters to generate endogenous volatility clustering and fat tails. statistical
Source sentence
By letting posterior distributions live on Lorenz- or R¨ossler-type attractors, and using 2 heavy-tailed priors, we obtain probability structures that exhibit endogenous volatility clustering, bursts, and fat tails.
Data
- Synthetic Lorenz and Rössler attractor trajectories synthetic unknown
Source sentence
Observed reference data were generated from canonical Lorenz (for the Lorenz–Lorenz pairing) or from both Lorenz and R¨ossler attractors (for the Lorenz–R¨ossler pairing).
Costs
Not applicable
Finds 5
- Model A reproduces the butterfly geometry of the Lorenz attractor in the Poincaré section cloud and concentrates the posterior around the canonical parameter values (σ=10, ρ=28, β=8/3). theoretical
Source sentence
Model A (Poincar´e–Mahalanobis) reproduced the butterfly geometry in the section cloud (Fig. 1a), concentrated the posterior around the canonical values (σ = 10, ρ = 28, β = 8/3; Fig. 1b), and produced 6 (a) Section cloud (x vs z) (b) Posterior cloud (σ–ρ) (c) MH traces Figure 1: Figure 1.
- Model B, using correlation‑integral and Fibonacci diagnostics, highlights volatility bursts and short‑orbit sequences where the trajectory exceeds multi‑scale diagnostic thresholds. theoretical
Source sentence
Model B (Correlation–Integral with Fibonacci diagnostics) emphasized volatility bursts. Short orbit highlights identified subsequences where the trajectory exceeded multi-scale diagnostic thresholds (21/34/55/89; Fig. 2a).
- Across both Lorenz–Lorenz and Lorenz–Rössler experiments, diagnostic weighting shifts posterior emphasis from baseline geometric stability (Model A) to rare‑event clustering (Model B). theoretical
Source sentence
Together, the Lorenz–Lorenz comparison shows how diagnostic weighting shifts pos-terior emphasis from geometric stability (Model A) to rare-event clustering (Model B). This makes Model A a natural reference for baseline system stability.
- The correlation‑integral framework with Fibonacci diagnostics transfers across distinct chaotic systems, retaining sensitivity to volatility clustering despite different dynamical profiles. theoretical
Source sentence
This confirmed that Fibonacci-based diagnostics transfer across attractors with distinct dynamics. Model B (Correlation–Integral), R¨ossler attractor with Fibonacci diagnostics.
- The dual perspective provides complementary methodological insights and practical tools for systemic risk analysis, with Model A offering a stable geometric anchor and Model B delivering a novel pathway for rare‑event detection. theoretical
Source sentence
This dual perspective advances both methodological understanding and practical tools for systemic risk analysis.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 18 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.