claim
active
claim:the-additive-form-s-d-dr-log-k-is-parsimonious-and-aligns-with-log-odds-intuitionThe additive form S = ρd - dr - log k is parsimonious and aligns with log-odds intuition
Justification for the linear combination
Source paper
extracted_from(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang
Neighborhood — ranked by edge-count
Communities (3)
community
- Few-shot anchoring & latent structuremembers_ofHow minimal examples disambiguate and recruit latent arithmetic/reasoning interpretations in LLMs
- Anchoring score threshold theorymembers_ofPredictive framework using S = ρd − dr − log k to explain few-shot performance phase transitions.
- Predictive metric S = ρd - dr - log k quantifies when LLM behavior sharply transitions across few-shot, SFT, and CoT settings via layer-wise calibration.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Claim that S predicts threshold midpoints across different bases, tasks, and models
- S = ρd − dr − log k is a predictive correlate of anchoring success across few-shot, SFT, and CoT.claim0.800UCCT's practical utility claim.
- Implicit hypothesis behind S form.
- Predictive practical utility claim.
- Prediction 3: log posterior odds additive in context and steering, with crossover N* predictable from prior odds and magnitudehypothesis0.778Eq. 10.
- Core result.
- (ii) does the anchoring score S = ρd − dr − log k consistently correlate with performance across anchoring methods?question0.757Second research question in E2
- log P(M(α) complies) is approximately linear in α when probability is not close to 1 on Qwen 3 4B pathfinding0.753Empirical basis for the extrapolation.