Linear combination ρd – dr – log k yields a predictive correlate of success.

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

• S = ρd − dr − log k is a predictive correlate of anchoring success across few-shot, SFT, and CoT.claim0.860
  UCCT's practical utility claim.
• S = ρd - dr - log k is a predictive correlate of when few-shot behavior flipsclaim0.828
  Claim that S predicts threshold midpoints across different bases, tasks, and models
• S = ρd - dr - log k predicts shot midpoints across different bases, tasks, and modelsclaim0.813
  Predictive practical utility claim.
• The additive form S = ρd - dr - log k is parsimonious and aligns with log-odds intuitionclaim0.793
  Justification for the linear combination
• (ii) does the anchoring score S = ρd − dr − log k consistently correlate with performance across anchoring methods?question0.775
  Second research question in E2
• Linear truth directions in LLMs are reliable primarily in factual recall cases and break down when truth assessment depends on computing and storing intermediate results.claim0.759
  Central empirical conclusion of the paper about the fundamental limits of truth directions.
• Do pattern density ρd and prior-target distance dr serve as predictive correlates of few-shot thresholds?question0.736
  First E2 research question directly testing UCCT's core predictive claims
• Under reward shaping (G=100, H=-100, F=0), Active Inference scored 99.52, Bayesian RL 99.77, Q-learning 95.56, with nearly identical behavior between belief-based agents.finding0.735
  Table 2, row 3, showing equivalence when prior preferences match rewards.