claim
active
claim:the-ordering-of-few-shot-thresholds-k50-and-transition-widths-aligns-with-k50-dr-dThe ordering of few-shot thresholds k50 and transition widths aligns with k50 ∝ dr/ρd.
Interpretation of E2 results.
Source paper
extracted_from(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang
Neighborhood — ranked by edge-count
Findings (3)
finding
- Lowest threshold condition in E2; near-zero/one-shot threshold consistent with high pretraining density
- In-base gains accompanied by uneven OOD drops; higher-density priors more robust.
- Widest transition in E2; consistent with lower prior density requiring more shots for reliable threshold crossing
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.
- Empirical characterization of k50 midpoints and transition widths across transformer models, tracking how pretraining density ρd/dr predicts in-context learning thresholds.
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.
- E2 main interpretive claim.
- Shot midpoint ordering k50(B10) < k50(B8) ≈ k50(B9) and transition widths correlate with mismatch D(P0∥PT)hypothesis0.868Testable prediction for Experiment 2
- Shot count needed to reach 50% accuracy; reflects when anchoring strength crosses critical value.
- Do pattern density ρd and prior-target distance dr serve as predictive correlates of few-shot thresholds?question0.833First E2 research question directly testing UCCT's core predictive claims
- (i) do pattern density (ρd) and prior–target distance (dr) serve as predictive correlates of few-shot thresholds?question0.829First research question in Experiment 2
- Shot midpoints follow k50 ∝ dr/ρd; higher cohesion and lower mismatch yield fewer required examplesclaim0.823Core quantitative prediction of UCCT validated by E2 threshold ordering
- Interpretation that pattern density from pretraining determines few-shot requirements
- Hypothesis: Shot midpoint ordering k50(B10) < k50(B8) ≈ k50(B9) follows pretraining exposure densityhypothesis0.810E2 prediction that bases with higher pretraining exposure require fewer shots to cross threshold