Numeric scoring on aesthetics is measurably unreliable; inter-scorer agreement on 0–10 scale for taste is poor.

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

• Alignment type is the only significant predictor of scores (p=0.006); architecture and parameter count do not.finding0.775
  Kruskal-Wallis test result: Constitutional AI predicts highest baseline; roleplay/empathy training predict lowest.
• Making something that truly pleases requires hundreds of subtle judgments, each extracting what pleases more within the whole.claim0.773
  From the West Dean experience: the north wall alone required approximately 500 such judgments.
• Aesthetics is a separable axis in AI evaluation, partially independent from a single latent performance factor.claim0.765
• Models fine-tuned on human data show strong positive correlation between misalignment and incoherence; misalignment scores fall below 1% when incoherence threshold is appliedfinding0.761
  Human data fine-tuning effect is distinct from synthetic emergent misalignment and likely caused by off-policy training
• Taste is fundamental guidance in creative and design work beyond technical rules.claim0.759
• Alignment type is the only significant predictor of koan scores (p=0.006); architecture, parameter count, open/closed weights, MoE/dense are all non-significantfinding0.758
  Main statistical finding: what predicts scores is training approach, not size or architecture
• In evaluating creative or intellectual output, the question should be 'Does it elevate us?' rather than 'What made it?' — judging origin rather than quality emphasizes the worst parts of human nature.claim0.758
  Normative claim about how to evaluate AI-generated content, using Deutsche Physik as cautionary analogy
• Our everyday liking (subjective preference) often diverges from deep liking, but deep liking converges to agreement and corresponds to living structure.claim0.756
  Distinction between superficial and deep preference.