To Use AI as Dice of Possibilities with Timing Computation

2026-05-01

AI Summary

Traditional noun-centric modeling paradigms struggle to capture dynamic processes along an open-ended temporal dimension. This work proposes a verb-centric modeling framework that, through verb primitives, temporal computation, and possibility modeling, achieves—for the first time—a purely data-driven, prior-knowledge-free approach to automatic discovery of clinical trajectories and counterfactual temporal inference. Applied to longitudinal electronic health records from 3,276 breast cancer patients, the method successfully identifies clinically meaningful patient trajectories and enables effective counterfactual reasoning. These results establish a novel paradigm for artificial intelligence as a tool embodying the grammar of thought, shifting the focus from static entities to dynamic actions and their temporal evolution.

Abstract

The dominant noun-based modeling paradigm has fundamentally constrained AI development, precluding any adequate representation of the future as an open temporal dimension. This paper introduces a verb-based paradigm, together with precise definitions of \emph{timing computation} and \emph{possibility}, that enables AI to function as an effective instrument for realizing the grammar of our thought. Applied to longitudinal EHR data from 3,276 breast cancer patients, the framework empirically demonstrates: (1) automatic discovery of clinically significant patient trajectories, and (2) counterfactual timing deduction. Both results are purely data-driven, require no prior domain knowledge, and, to our knowledge, represent the first such demonstrations in the machine learning literature.

Problem

• noun-based modeling
• temporal dimension
• AI paradigm
• future representation
• timing computation

Innovation

• verb-based paradigm
• timing computation
• possibility
• counterfactual timing deduction
• longitudinal EHR