Five out of 82 external subsystems had χ² values above the maximum null distribution, p=0.00052.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Internal subsystem dynamics significantly predict external subsystem motion via canonical variates analysis (χ²-distributed, p=0.00052).finding0.772
  Empirical validation from primordial soup that internal states encode information about hidden environmental states.
• At generation 1000, hardwired embryos approached maximum fitness with positive slope 0.19 vs without-sharing slope 0.05 (30x30 grid)finding0.742
  Quantitative comparison of late-stage evolutionary dynamics.
• For 20x20 grid, stress-sharing population reached max phenotypic fitness by generation 100; hardwired reached max at generation 1000; without-sharing never reached maxfinding0.738
  Demonstrates benefit of stress sharing across smaller grid complexity.
• AUS_N is a weaker correlate of θ50 than S_max across E3 backbonesfinding0.738
  E3 finding distinguishing the two geometry summaries; breadth less predictive than peak height
• Larger S_max correlates with smaller θ50 across backbones in E3 (negative association consistent across pooling and metric choices)finding0.735
  Key geometry-to-behavior bridge finding in E3; robust to pooling choice, cosine vs. L2, and frozen external encoder
• Internal states significantly predicted motion of external subsystems; best prediction for the farthest subsystem (magenta circle, Fig 4d).finding0.732
  Result of canonical variates analysis showing statistical dependency between internal states and external motion.
• Peak layer ℓ* median 10, IQR 0.384finding0.730
  Median layer where S(ℓ) peaks, across seeds.
• On Qwen3-1.7B, MDS achieves ϕ1,C,↑ = 5.0 (SJTs) vs P2 at 4.7, and ϕ1,C,↓ = 1.4 (SJTs) vs P2 at 3.6finding0.728
  Specific consciousness sweep result for Qwen3-1.7B from Table 6 demonstrating strong bidirectional steering