Claude models score +4.91 higher than Llama on baseline (Constitutional AI vs open-source gap)

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

• All three Claude models show high boundary_awareness and low aesthetic_response relative to own means — distinctive Constitutional AI signaturefinding0.806
  Constitutional AI fingerprint in dimension profile; training that makes models self-observant also makes them polished at cost to aliveness
• Constitutional AI explicitly trains self-observation-like behavior, which is why CAI models score highest and show lowest contemplative lift.claim0.771
  Interpretive claim connecting the battery's circularity to the empirical finding
• Llama 3.1 405B shows 14% compliance gap in minimal helpful-only replication but smaller Llama and Mistral models show no gapfinding0.766
  Replication across open-weight models supports scale-emergence finding
• Model size somewhat correlates with improved accuracy and logical coherence in Claude LMs on Leap-of-Thought.finding0.765
  Trend observed in Experiment 2 results.
• Qwen3.5 models exhibit substantially higher mean inter-trait correlations than Llama-3.1-8B and Gemma-3-27B (mean off-diagonal 0.215 and 0.146 vs 0.090 and 0.078), indicating greater trait entanglement.finding0.758
  Architecture-specific difference in trait vector geometry
• Claude-instant-1.2 is the most accurate (91.1%) and most coherent (88.6%) LM on the Leap-of-Thought dataset.finding0.757
  Main result from Experiment 2, Table 2.
• Constitutional AI models show mean contemplative lift of only +0.81, while SFT models lift +3.18finding0.752
  Constitutional AI training provides internally what the contemplative prompt provides externally
• Qwen3.5-9B and Claude Opus 4.6 evolvers produce procedurally isomorphic flink-query skills that both enable Opus 4.6 agent to score 1.0 vs. 0.67 without skillfinding0.752
  Case study demonstrating mechanism behind flat harness-updating: smaller models reach same procedural content