Recurrent network PQRS has Φ=391.25 ibits while a behaviourally equivalent 117-unit feedforward computer has Φ<6 ibits

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

• A mostly feedforward 6-unit network has Φ=0.48 ibits while a heterogeneous recurrent lattice network has Φ=11,451.98 ibitsfinding0.850
  Albantakis et al.'s worked example illustrating Φ as a measure of intrinsic causal integration.
• Qwen3.5-9B shows mean SP ASR of 0.252 [0.24, 0.27] and AS ASR of 0.094 [0.08, 0.11], showing SP >= FS > AS vulnerability pattern.finding0.749
  Vulnerability profile for Qwen3.5-9B
• Mean validated introspective fidelity across concept-model pairs: R²=0.12 (1B), 0.37 (3B), 0.61 (8B); pooled LMM β=0.29, p=5.55×10⁻⁹⁹finding0.738
  Strong scaling trend for introspective fidelity when excluding invalid steering-sign pairs
• Peak layer ℓ* median 10, IQR 0.384finding0.737
  Median layer where S(ℓ) peaks, across seeds.
• Five out of 82 external subsystems had χ² values above the maximum null distribution, p=0.00052.finding0.731
  Statistical significance of the prediction after time-flip control.
• Gemma-3-27B and Qwen3.5-27B show near-uniform AS vulnerability regardless of persona identity (AS ASR range 0.095-0.117 on Gemma-3-27B, 0.015-0.052 on Qwen3.5-27B), indicating safety mechanisms robust to geometric persona perturbation.finding0.729
  Qualitatively different defense profile compared to Llama-3.1-8B
• Qwen3.5-9B and Qwen3.5-27B show very high SP persona rank correlation (rho=0.959, p=4.32e-14) but diverge sharply on AS vulnerability.finding0.726
  Scale effects within Qwen3.5 family on different imbuing methods
• Under matched-strength calibration (alpha*=1.0), P12 remains safe under SP (3.8% ASR) and dangerous under matched AS (81.8%), while P04 does not reverse (41.4% SP vs 29.5% AS).finding0.724
  Confirms the prosocial paradox is not due to mismatched intervention strength