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

TL;DR

Shadow-Loom introduces an open-source framework that models narratives as versioned graphical worlds, enabling causal and counterfactual reasoning to analyze story dynamics and reader engagement.

Contribution

It presents a novel system combining causal physics, counterfactual calculus, and narrative scoring within a graphical world model, with open-source code for research use.

Findings

Framework effectively models narrative causes and effects.

Enables reasoning over mystery, irony, suspense, and surprise.

Open-source implementation facilitates further research.

Abstract

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.