Tag
This paper develops the QQ equality from cognitive science into an audit criterion for LLMs, characterizes theoretical mechanism classes, and empirically tests on an open-weight instruction-tuned model, finding that saturation (near-deterministic responses) prevents distribution-level audits.
This paper develops a quantum-like extension of the Tug-of-War decision-making model, using a qutrit internal state to model context dependence and decision dynamics, and argues that contextual probability is a resource signature of minimal decision dynamics.
This paper proposes that quantum probability can be understood as a projection of contextual spacetime formation under finite-state requirements, reinterpreting interference and noncommutativity as mismatches from a fixed classical spacetime projection.