mlsanityData to 7 Oct 2026

To Use AI as Dice of Possibilities with Timing Computation

arXiv 2605.01134 ↗First posted 1 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The dominant noun-based modeling paradigm, grounded in probability theory and committed to pre-specified noun entities as primitive modeling units, is insufficient as a grammar of thought: It leaves timing outside the computational scope, precluding any adequate representation of the future as an open space of possibilities. This paper addresses three conceptual gaps absent from the existing literature: (1) possibility space -- a framework admitting multiple possible timelines for the same event; (2) timing computation -- the treatment of timing as a computable rather than observed dimension; and (3) causal factum -- the maximal causal efficacy recovered by reasoning backward from possible futures, rather than assumed in advance. Together, these definitions dissolve the confounding problem inherent to noun-based causal inference and provide the foundation for a spontaneously growing causal-reasoning world model. As proof of concept, we instantiate the framework and apply it to longitudinal EHR data from 3,276 breast cancer patients, demonstrating for the first time, to our knowledge, automatic trajectory discovery and counterfactual timing deduction (i.e., a What-If Machine) in a purely data-driven manner.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 19 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

12 of 19 references.

References · 12

  1. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  2. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  3. 2016DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Networkcited by 354
  4. 2021Multi-Time Attention Networks for Irregularly Sampled Time Seriescited by 234
  5. 2019Time2Vec: Learning a Vector Representation of Timecited by 208
  6. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  7. 2017Machine Learning for Survival Analysis: A Surveycited by 112
  8. 2018Can recurrent neural networks warp time?cited by 53
  9. 2024TA-RNN: an Attention-based Time-aware Recurrent Neural Network Architecture for Electronic Health Recordscited by 6
  10. 2023Emergence and Causality in Complex Systems: A Survey on Causal Emergence and Related Quantitative Studiescited by 3
  11. 2022Dynamic Survival Transformers for Causal Inference with Electronic Health Recordscited by 1
  12. 2026Capture Timing-Attention of Events in Clinical Time Seriescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ACCESS : A Benchmark for Abstract Causal Event Discovery and Reasoning
  2. 2025TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation
  3. 2024CELLO: Causal Evaluation of Large Vision-Language Models
  4. 2026Generated Context versus Governed State: Functional Conditions for Accountable Longitudinal Clinical Reasoning
  5. 2025Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
  6. 2026Learning Dynamic Belief Graphs for Theory-of-mind Reasoning
  7. 2025HCR-Reasoner: Synergizing Large Language Models and Theory for Human-like Causal Reasoning
  8. 2024Large Language Models for Constrained-Based Causal Discovery