Shared models of relative scarcities

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

• shared model of relative scarcitiesconcept0.957
  The definitional essence of cognitive glues proposed by the paper.
• relative scarcitiesconcept0.836
  The underlying variables that cognitive glues model in a shared way.
• Cognitive glues are shared models of relative scarcitiesclaim0.820
  Core thesis of the paper stated in the title.
• unified models (direct image generation)concept0.709
  Models that directly generate images during reasoning, described as computationally expensive and architecturally non-trivial.
• Autoregressive modelsframework0.709
  Second model system studied; used to show why flat autoregressive LLMs struggle with long-range coherence.
• Analogous features and circuits form across models and tasks.claim0.706
  Third of three speculative claims asserting that learned features are not model-specific but represent universal solutions to learning problems
• Lack of rigorous cross-model comparison demonstrating that specific named features (not just correlated ones) form across architecturesquestion0.706
  Explicitly identified research gap: anecdotal evidence exists but rigorous characterization is absent
• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.705
  The central hypothesis of the paper; the platonic representation hypothesis itself