Statistical Properties of the King Wen Sequence: An Anti-Habituation Structure That Does Not Improve Neural Network Training

TL;DR

This study analyzes the statistical properties of the ancient King Wen sequence and tests whether its unique structure benefits neural network training, finding it actually hampers performance due to high variance.

Contribution

It provides a rigorous statistical characterization of the King Wen sequence and empirically demonstrates its lack of benefit for neural network training.

Findings

King Wen sequence has statistically significant properties like higher transition distances and asymmetry.

Experiments show King Wen sequence degrades neural network training performance.

High variance in the sequence destabilizes gradient-based optimization.

Abstract

The King Wen sequence of the I-Ching (c. 1000 BC) orders 64 hexagrams -- states of a six-dimensional binary space -- in a pattern that has puzzled scholars for three millennia. We present a rigorous statistical characterization of this ordering using Monte Carlo permutation analysis against 100,000 random baselines. We find that the sequence has four statistically significant properties: higher-than-random transition distance (98.2nd percentile), negative lag-1 autocorrelation (p=0.037), yang-balanced groups of four (p=0.002), and asymmetric within-pair vs. between-pair distances (99.2nd percentile). These properties superficially resemble principles from curriculum learning and curiosity-driven exploration, motivating the hypothesis that they might benefit neural network training. We test this hypothesis through three experiments: learning rate schedule modulation, curriculum ordering, and seed sensitivity analysis, conducted across two hardware platforms (NVIDIA RTX 2060 with PyTorch and Apple Silicon with MLX). The results are uniformly negative. King Wen LR modulation degrades performance at all tested amplitudes. As curriculum ordering, King Wen is the worst non-sequential ordering on one platform and within noise on the other. A 30-seed sweep confirms that only King Wen's degradation exceeds natural seed variance. We explain why: the sequence's high variance -- the very property that makes it statistically distinctive -- destabilizes gradient-based optimization. Anti-habituation in a fixed combinatorial sequence is not the same as effective training dynamics.