finding
active
finding:fast-lyapunov-indicator-f-strongly-correlates-with-the-number-of-distinct-solutions-a-reasoning-trajectory-passes-through-before-convergingFast Lyapunov indicator λF strongly correlates with the number of distinct solutions a reasoning trajectory passes through before converging
Links saddle-crossing intensity to the number of candidate-answer switches during reasoning.
Source paper
extracted_from(2026) · Jeffrey Lai · Anthony Bao · J. Quinn · William Gilpin
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Interprets the λF–solution-switch-frequency correlation as evidence that saddles are algorithmically meaningful.
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.
- Metric directly localizing saddle-like boundaries between solution routes by measuring maximal local trajectory separation.
- Evidence of a bottleneck between richer internal variation and final report distribution in impulsivity→interest condition
- Pre-bifurcation, all finite-time Lyapunov exponents are negative, so no transient chaos occursfinding0.734Establishes the baseline (non-chaotic) regime before the bifurcation.
- Establishes the mechanistic link between lower VFE and critical dynamics, supporting the paper's criticality prediction
- Prediction 2: if LRH holds, steering raises belief at a sigmoidal rate with magnitude mhypothesis0.729From Eq. 8.
- Claim that S predicts threshold midpoints across different bases, tasks, and models
- Beliefs linearly decodable.
- App. E.