Object models in which time, versioning, causality, etc., are significant are probably far better modelled by considering the time component as another key rather than an intrinsic property of the underlying model.

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

• The ability to represent relationships (e.g. correlations or associations) among variables, rather than a system of independent variables, is essential for any connectionist model of cognition.claim0.794
  Necessary condition for connectionist cognition.
• Software implementations for all of the models/behaviours presented are common for n = 2, and can be made very efficient for α_i that map many objects onto a much smaller set of object families.claim0.794
  Claim about current practical feasibility and efficiency of 2-way associative implementations.
• We stress that in today’s models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.quote0.793
  Caveat and forward-looking statement from the abstract.
• The strengths of all three models (concurrent OOP, logic, functional) are irrelevant to parallelism, and generally unhelpful in dealing with process creation and coordination.claim0.785
  Assertion that the popular models add nothing to parallel programming.
• Causal abstraction is not enough for mechanistic interpretability because it becomes vacuous without assumptions about how models encode informationclaim0.782
  Central thesis of the paper
• Models are being used ubiquitously for the control of complex dynamic systems.claim0.780
  Assertion in the abstract that models are pervasive in controlling complex dynamics, setting the motivation for the theorem.
• As LLMs scale, they develop increasingly general abstractions, with large models linearly representing abstract concepts like truth that capture shared properties of diverse inputsclaim0.778
  Interpretive claim connecting scale to abstraction level in LLM representations
• The earlier a base model (less exposure to LM-related data), the more it is surprised by its own spontaneous self-referential capabilities.claim0.776
  Claim that capability emerges from architecture, not data, and that later models lose the surprise.