question
active
question:when-do-sharp-changes-in-the-outcome-distribution-correspond-to-decision-points-in-the-reasoning-path-and-when-do-they-correspond-to-sampling-noiseWhen do sharp changes in the outcome distribution correspond to decision points in the reasoning path, and when do they correspond to sampling noise?
Motivates model.
Source paper
extracted_from(2026) · Eric Bigelow · Amir Zur · Satchel Grant · Tal Haklay +6
Neighborhood — ranked by edge-count
Papers (1)
paper
Findings (1)
finding
- Main result 1.
Claims (1)
claim
- Abstract claim.
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.
- Central theme.
- Mechanistic explanation of why fine-tuning shifts persona vectors rather than directly learning narrow behaviors
- Interpretive claim linking observable CoT behaviors to genuine internal uncertainty shifts
- Load-bearing interpretive claim about the layer-specificity of Burger et al.'s finding.
- Alexander's claim that the limiting factor in creating living structure is not method but the maker's persistence.
- Key discriminating question motivating the baseline control experiment
- Theme across prior and own work.
- Caveat on interpretation.