S is a predictive correlate calibrated on dev sets, not an absolute measure

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

• The anchoring score S is a predictive correlate of when anchoring succeeds and why small prompt changes yield threshold-like shifts.claim0.776
  A central claim about the operational value of S.
• S = ρd − dr − log k is a predictive correlate of anchoring success across few-shot, SFT, and CoT.claim0.763
  UCCT's practical utility claim.
• dev set calibrationmethod0.760
  Fixed dev pool of 1000 prompts used for whitening and z-scoring parameters.
• S = ρd - dr - log k is a predictive correlate of when few-shot behavior flipsclaim0.756
  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 modelsclaim0.756
  Predictive practical utility claim.
• The results generalise readily to non-equilibrium systems where scaling relationships remain similar (e.g., dynamic or localised scaling).claim0.752
  Claim about broader applicability of the scaling argument
• Alignment type is the only significant predictor of scores (p=0.006); architecture and parameter count do not.finding0.746
  Kruskal-Wallis test result: Constitutional AI predicts highest baseline; roleplay/empathy training predict lowest.
• it creates a ‘we’; what we are doing, for example, whether our behaviours are coordinated or not, becomes a relevant variable.quote0.741
  Illustrates how non-separable functions shift identity to the collective level.