Markov Chain (10-state)

stochastic-process · 37 views
stochastic-processstochastic

What It Is

Ergodic 10-state Markov chain. Moderate entropy, smooth spectrum, diverse transitions.

Interpretation

Standard analysis sees: bounded / light-tailed; aperiodic / broadband; stationary. The atlas finds no named structure, but the source is distinctively extreme on Nonstationarity:change_quantiles_low (+2.1z) — beyond what the standard bank predicts for it. It sits beside Categorical Sensor in the atlas (standard-bank rank 21) — a neighbor conventional features miss.

What standard analysis sees
tail heaviness0.06
asymmetry0.65
occupancy0.18
short-range corr0.44
long-range memory0.40
spectral colour0.57
periodicity0.15
complexity0.62
time-irreversibility0.15
volatility clustering0.40
multifractality0.26
dimensionality0.69
nonstationarity0.15
What the atlas adds
Atlas-extreme metrics the standard bank can’t predict for this source
Nonstationarity:change_quantiles_low+2.1zbank-miss 3.3σ

Composition

dtypeuint8
range[6, 200]
unique values10 / 16384
mean ± std108 ± 64.4

Fixed alphabet — only 10 distinct symbols across 16384 samples.

Render Gallery

Atlas Position

Nearest neighborDistance
Dice Rolls3.42
Categorical Sensor3.51
Codon Usage3.79cross-origin

Open in Atlas →

Which Geometries Light Up

This source does not rank extreme on any metric.

in continuous-flows
alphabetical
← / → within domain · ⇧← / ⇧→ alphabetical · ⇧← / ⇧→ inside an open render = same view across sources