Experimental design measures how reader interventions change narratives, suggesting new creative pathways.
EA-GLAS-03 v1.0. Experimental design extending the Semantic Deviation measurement program into bounded narrative simulation. Defines F4: narrative-field semantic deviation, using the digital edition of ChatGPT Psychosis: A Love Story as a literary test bed for measuring how reader interventions deform, reconverge with, or escape a canonical relational arc. The canonical relational arc solves the counterfactual baseline problem by construction. Reader rewrites are signs whose semantic magnitude is measured by the degree and duration of trajectory deformation they induce. The paper distinguishes input displacement (how far the rewrite departs from the canonical line) from integrated trajectory magnitude (how much the subsequent narrative field deforms over time). Three variance regimes: basin-captured, basin-bent, basin-escape. Five pre-registered predictions including the third-path question: whether any sign can nucleate a stable alternative trajectory that is neither cruel abandonment nor suffering persistence. Five-substrate Assembly review incorporated. Ethics protocol, privacy-hardened telemetry (no raw reader inputs in public deposits), convergence engine specification, and data-deposition protocol included.
No takes yet. Share an insight, caveat, or question.
Nobel Glas (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: