claim
active
claim:threshold-like-performance-flips-occur-when-anchoring-strength-s-crosses-a-task-dependent-critical-value-scThreshold-like performance flips occur when anchoring strength S crosses a task-dependent critical value Sc.
Interpretation of abrupt behavior changes.
Source paper
extracted_from(2025) · Edward Yi Chang · Kaya, Zeyneb N. · Ethan Chang
Neighborhood — ranked by edge-count
Hypotheses (1)
hypothesis
- Core testable hypothesis of UCCT about the nature of performance transitions under anchoring
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.
- How minimal, task-specific prompt examples rebind model priors across threshold boundaries without weight updates, studied through arithmetic reasoning tasks.
Artifacts (1)
artifact
- Main paper presenting UCCT and semantic anchoring framework.
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.
- Small prompt changes can yield threshold-like shifts because S crosses the critical value Scclaim0.820Authors' explanation for abrupt behavioral changes
- A central claim about the operational value of S.
- The threshold value of S above which performance shifts abruptly; model- and layer-specific
- Strong priors require higher-cohesion anchors to overcome, manifesting as delayed thresholds or reduced transferhypothesis0.769Prediction for Experiment 1 cross-domain anchoring
- The specific gap UCCT addresses that prior phase/representation work left open
- Authors contrast their work with prior phase/representation studies
- Conclusion from E1 and central UCCT claim.
- Critical anchoring strength above which performance flips sharply.