A probabilistic method to rigor based text scoring

This paper introduces a novel method for evaluating the rigor of written text using Markov chain Monte Calro simulations. Traditional approaches to text analysis, such as readability metrics or grammatical checks, often fall short in assessing the logical consistency, structural complexity, and overall coherence that characterize rigorous writing[SWSK24]. I propose a probabilistic model that leverages Markov chains to quantify text rigor by analyzing word and phrase transitions within the text. Specifically, we model each word or n-gram as a state within a Markov chain and compute transition probabilities that capture patterns of consistency and complexity[Scind].