Causal World Models

Follow this topic Ask about this topic

Momentum

7 papers in the last four weeks, up 40% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 32

All topics

Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives
May 4, 2026David WilmotCausal World Models Interactive Storytelling
To Use AI as Dice of Possibilities with Timing Computation
May 1, 2026Jia Li, Vipin Kumar, Rui ZhangCausal World Models Time-Series Causal Discovery
Department of Surgery, University of Minnesota, Minneapolis, United States · Department of Computer Science & Engineering, University of Minnesota, Minneapolis, United States

May 4, 2026, cs.AIJ/K move · Enter open · S save

Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives

David Wilmot

Causal World Models Interactive Storytelling World Models Causal Reasoning Counterfactual Reasoning

Open paper AskPDF arXiv

Stories hold a reader's attention because they have causes, secrets, and consequences. Shadow-Loom is an experimental open-source framework that turns a narrative into a versioned graphical world model and lets two engines act on it: a causal physics grounded in Pearl's ladder of causation and a recently proposed counterfactual calculus over Ancestral Multi-World Networks; and a narrative physics that scores the same graph against four structural reader-states -- mystery, dramatic irony, suspense, and surprise -- in the tradition of Sternberg's curiosity/suspense/surprise triad, with suspense formalised in the structural-affect line of work on story comprehension and computational suspense. Large language models are used only at the boundary: extraction, rendering, and audit; identification, intervention, and counterfactual reasoning are carried out in typed code over the graph. The system is offered as a research artefact rather than as a benchmarked NLP model; code, fixtures, and pipeline are released open source.

Momentum

Related topics

Latest papers 32

Shadow-Loom: Causal Reasoning over Graphical World Models of Narratives

To Use AI as Dice of Possibilities with Timing Computation