"Here, we show that reasoning models exhibit transient chaos, a physical consequence of the computational complexity of difficult tasks."

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

• Most reasoning models are expected to exhibit some form of doubly transient chaos, because properties like convergence-to-fixed-answers act as a dissipation-like mechanismhypothesis0.891
  Forward-looking predictive claim about reasoning models generally, based on the analogy to damped physical systems.
• Reasoning models' capability is tied to their ability to escape saddle points near incorrect solutionsclaim0.814
  Practical interpretive upshot connecting dynamics to model competence.
• Fractal basins and transient chaos are the generic manner in which computational complexity manifests in analogue systemsclaim0.805
  Generalizing interpretation connecting this paper's AI findings to physical analogue computation broadly.
• Reasoning slowdowns are an inevitable consequence of problem hardness in modern AI modelsclaim0.803
  The paper's central interpretive claim, closing statement of the abstract.
• Reasoning models' fractal basins are smooth and naturalistic, resembling optical caustics or turbulent transient lifetimes, despite the discrete puzzles being solvedclaim0.801
  Visual/qualitative characterization of the basin geometry linking it to classical physical fractal phenomena.
• "Our results show that reasoning slowdowns are an inevitable consequence of problem hardness in modern artificial intelligence models"quote0.799
  Closing sentence of the abstract stating the paper's headline conclusion.
• Complexity can be treated as a physical quantity with consequences for AI inferenceclaim0.786
  Closing philosophical claim situating the results within physical-computation theory.
• Modern reasoning models can be placed within the longstanding tradition framing computation as a physical processclaim0.778
  Closing claim connecting to Moore/Shaw/Crutchfield-style physical computation theory.