Shadow-Loom: Causal Reasoning over Graphical World Model of Narratives
For researchers in computational narratology and causal reasoning, this provides a novel framework integrating causal and narrative physics, but it is presented as a proof-of-concept without empirical validation.
Shadow-Loom introduces a framework for causal reasoning over narrative world models, enabling the computation of reader states (mystery, dramatic irony, suspense, surprise) and counterfactual analysis using Pearl's ladder of causation, with LLMs used only for extraction and rendering. The system is released as an open-source research artifact without benchmarked results.
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.