Categorical Sensor

stochastic-process · 37 views
stochastic-processstochastic

What It Is

Random draws from 6 to 12 non-uniform categories. Peaked, unpredictable, low entropy.

Interpretation

Standard analysis sees: left-skewed; few distinct values; aperiodic / broadband. The atlas finds no named structure, but the source is distinctively extreme on Zipf–Mandelbrot (16-bit):zipf_alpha (+3.1z) — beyond what the standard bank predicts for it. It sits beside Markov Chain (10-state) in the atlas (standard-bank rank 40) — a neighbor conventional features miss.

What standard analysis sees
tail heaviness0.78
asymmetry0.01
occupancy0.13
short-range corr0.34
long-range memory0.43
spectral colour0.66
periodicity0.09
complexity0.51
time-irreversibility0.29
volatility clustering0.27
multifractality0.43
dimensionality0.51
nonstationarity0.44
What the atlas adds
Atlas-extreme metrics the standard bank can’t predict for this source
Zipf–Mandelbrot (16-bit):zipf_alpha+3.1zbank-miss 2.2σ
Zipf–Mandelbrot (8-bit):zipf_alpha+2.6zbank-miss 2.2σ

Composition

dtypeuint8
range[20, 235]
unique values8 / 16384
mean ± std100 ± 44.7

Fixed alphabet — only 8 distinct symbols across 16384 samples.

Render Gallery

Atlas Position

Nearest neighborDistance
Poker Hands3.45
Markov Chain (10-state)3.51
Sandpile3.70cross-origin

Open in Atlas →

Which Geometries Light Up

Zipf–Mandelbrot (16-bit) › Zipf–Mandelbrot (16-bit):zipf_alpharank 5/3062.3562
Zipf–Mandelbrot (8-bit) › Zipf–Mandelbrot (8-bit):zipf_alpharank 5/3063.1660
in number-theory
alphabetical
← / → within domain · ⇧← / ⇧→ alphabetical · ⇧← / ⇧→ inside an open render = same view across sources