All 40 destructive pairwise interactions occur exclusively among steerable-steerable pairs; no N/N or N/S pair is destructive

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

• Natural-steerable pairs split 26 constructive / 22 dominant but produce zero destructive outcomes; natural trait acts as anchorfinding0.840
  Natural trait acts as anchor in mixed pairs, suppressing steerable partner at worst but never collapsing both
• Destructive pairwise interactionconcept0.815
  Pairwise outcome where both traits fall significantly relative to their single-trait strengths
• 171 generic-trait pairs in Q8B split into 64 constructive, 67 dominant, and 40 destructive interactionsfinding0.787
  First systematic pairwise composition study across all pairs of 19 generic traits
• Steering vector constructed from all 16 contrastive pairs outperforms most single-pair vectors; best 4-pair vector outperforms full 16-pair vectorfinding0.764
  Demonstrates averaging multiple prompt pairs reduces noise; optimal subset selection further improves performance.
• Selves can be nested and overlapping, cooperating and competing both laterally and across levels.claim0.761
  Key TAME claim that biological systems are patchworks of agents, with higher Selves deforming option spaces for lower ones.
• When interactions constitute non-linearly separable functions, it creates a ‘we’; what we are doing becomes a relevant variable.claim0.750
  Explains how non-separability shifts identity from parts to collective.
• Which trait pairs combine cleanly, which produce a single dominant trait, and which collapse both?question0.742
  The open question motivating the pairwise composition study
• Pairwise steering needs empirical maps rather than assuming vector addition will behave like ordinary semantic blendingclaim0.740
  Cosine similarity is useful but insufficient; highly similar traits can still destructively interact