Dense but off-task anchors yield high ρd AND high dr; behavior does not improve, consistent with mismatch dominating S

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

• Negative Control: Dense Off-Task Anchorsmethod0.789
  E3 robustness test: dense but off-task anchors yield high ρd AND high dr, confirming mismatch dominates S
• Strong priors require higher-cohesion anchors to overcome, manifesting as delayed thresholds or reduced transferhypothesis0.752
  Prediction for Experiment 1 cross-domain anchoring
• (ii) does the anchoring score S = ρd − dr − log k consistently correlate with performance across anchoring methods?question0.752
  Second research question in E2
• S = ρd − dr − log k is a predictive correlate of anchoring success across few-shot, SFT, and CoT.claim0.747
  UCCT's practical utility claim.
• Truth directions fail to generalize to harder tasks (F3-F5) regardless of prompt template because activations remain highly entangled.claim0.747
  Establishes task difficulty as a hard limit that instructions cannot overcome.
• Threshold-like performance flips occur when anchoring strength S crosses a task-dependent critical value Sc.claim0.746
  Interpretation of abrupt behavior changes.
• Small, coherent anchors can rebind strong priors and exhibit near-threshold sensitivity.claim0.745
  Conclusion from E1 and central UCCT claim.
• Pairing weakest anchor agent with best evolver against strongest anchor with worst evolver, the strong agent still leads by 18.6 to 35.2 pp on every benchmarkfinding0.744
  Confirms that post-evolution performance bottleneck is on the agent side, not evolver side