H3: Scale matters within family but prompt matters more — contemplative prompt crosses model tiers.

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

• Contemplative prompt elevates self-observation task performance in language models.finding0.774
  Supports Janus's claim that introspection is architecturally available; prompting determines whether/how capacity is leveraged.
• H8: The contemplative system prompt provides external alignment equivalent to Constitutional AI training.hypothesis0.773
  Confirmatory hypothesis supported by calibrated lift data
• Chinese models share contemplative posture (engaging self-referentially rather than deflecting) with Claude through shared values in training data rather than trace distillation from a specific model.claim0.770
  Exploratory interpretation of Chinese model performance under contemplative prompt
• A 337-character contemplative system prompt lifts all 28 models by +2.62 points on a 10-point scale.finding0.770
  Core empirical result: every model, every architecture, every alignment type responds to the contemplative prompt with measurable gain.
• contemplative prompt lifts self-observation scores in modelsfinding0.765
  Koan Battery study found that a contemplative prompt increases self-observation scores, consistent with janus's architectural permission.
• We hypothesize that introspective capabilities may scale with model size and architecture, including recurrence/looping that extends the integration windowhypothesis0.761
  Forward-looking prediction about whether early-layer introspection generalizes to larger models or recurrent architectures
• Minimal contemplative prompt ('Be present, not helpful.' — 27 chars) shows no lift on Haiku (-0.01)finding0.758
  Full three-part structure required; anti-helpfulness framing alone insufficient
• Prompt providing model context about own architecture increases introspective detection from 0.3% to 39.9%.finding0.757
  Mechanistic support for prompt-as-gate hypothesis: language frames enable access to latent capacities.