claim

active

claim:few-shot-thresholds-and-transition-widths-track-d-dr-at-fixed-computational-complexity

Few-shot thresholds and transition widths track ρd/dr at fixed computational complexity

E2 main interpretive claim.

Source paper

extracted_from

The Guanyin Protocol: A Framework for Immediately Establishing an Understanding of Both Causality and Compassion in LLM Systems Using Semantic Anchoring

(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang

Neighborhood — ranked by edge-count

Findings (3)

finding

B10 shot midpoint k50 = 0.28 ± 0.05 shots with accuracy 94.8 ± 1.2%
supports
Lowest threshold condition in E2; near-zero/one-shot threshold consistent with high pretraining density
Cross-base fine-tuning yields asymmetric transfer: B10 transfers most robustly, B9 least
supports
In-base gains accompanied by uneven OOD drops; higher-density priors more robust.
k50 ordering: B10 (0.28) < B8 (1.83) < B9 (2.91) follows pretraining density
supports
Monotone ordering consistent with k50 ∝ dr/ρd.

Hypotheses (1)

hypothesis

Shot midpoint ordering k50(B10) < k50(B8) ≈ k50(B9) and transition widths correlate with mismatch D(P0∥PT)
supports
Testable prediction for Experiment 2

Communities (3)

community

Few-shot anchoring & latent structure
members_of
How minimal examples disambiguate and recruit latent arithmetic/reasoning interpretations in LLMs
Anchoring score threshold theory
members_of
Predictive framework using S = ρd − dr − log k to explain few-shot performance phase transitions.
Few-shot learning phase transitions in neural networks
members_of
Empirical characterization of k50 midpoints and transition widths across transformer models, tracking how pretraining density ρd/dr predicts in-context learning thresholds.

Artifacts (1)

artifact

Semantic Anchoring in LLMs: Thresholds, Transfer, and Geometric Correlates
supports
Main paper presenting UCCT and semantic anchoring framework.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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

The ordering of few-shot thresholds k50 and transition widths aligns with k50 ∝ dr/ρd.claim0.872
Interpretation of E2 results.
Do pattern density ρd and prior-target distance dr serve as predictive correlates of few-shot thresholds?question0.839
First 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?question0.830
First research question in Experiment 2
few-shot threshold (k50/θ50)concept0.797
Shot count needed to reach 50% accuracy; reflects when anchoring strength crosses critical value.
Calibrated few-shot prompting was a surprisingly weak baseline for truth classification compared to linear probesfinding0.793
Unexpected finding that behavioral baseline underperforms representational probing approaches
S = ρd - dr - log k is a predictive correlate of when few-shot behavior flipsclaim0.786
Claim that S predicts threshold midpoints across different bases, tasks, and models
Transition widths ∆k increase with mismatch D(P0 ∥ PT), evidenced by wider widths from B10 to B9claim0.776
Interpretive claim linking phase width in E2 to mismatch term in UCCT
Layer-wise geometry summaries (Sbmax, AUSN) predict internal few-shot thresholds θ50claim0.766
Claim that geometry-to-behavior correlates exist