Computational Detection of Constitutional Drift: Network Analysis and Semantic Measurement of Argentine Supreme Court Jurisprudence (1922–2025)

Abstract

This study introduces a computational framework for quantifying constitutional degradation through judicial citation network analysis and semantic text mining. Traditional legal scholarship relies on qualitative interpretation, which limits systematic cross-jurisdictional comparison and predictive modeling of constitutional evolution. This paper addresses that gap by developing three open-source algorithms applied to 72 Argentine Supreme Court decisions (1989–2025). Three algorithms were developed: JurisRank (a PageRank adaptation measuring doctrinal fitness through citation networks), RootFinder (Ancestral Borrowing Analysis Network for genealogical concept tracing), and Legal-Memespace (principal component analysis for multidimensional doctrine mapping). Cases were selected through stratified sampling covering emergency decrees, economic regulations, and control domains, with inter-coder reliability of 𝜅 = 0.83 (95% CI: 0.76–0.89). Formalist constitutional interpretations declined in network fitness from 0.89 (1922 baseline) to 0.03 (2025), a reduction of 97%, while emergency doctrines rose from 0.11 to 0.97 (Kendall’s 𝜏 = −0.89, p < 0.001). K-fold cross-validation (k = 5) yields a mean accuracy of 73.2%. In the 2024–2025 period, institutional resistance to executive decrees correlated 0.91 with fiscal impact across 28 analyzed measures, suggesting selective constitutional enforcement. Monte Carlo simulations (n = 1000) assign 82% probability to formalist doctrine reaching functional extinction (fitness < 0.05) by 2030. The framework enables automated constitutional monitoring, cross-jurisdictional comparison, and early crisis detection. All algorithms are released as open-source software (github.com/adrianlerer/peralta-metamorphosis) for independent validation and collaborative extension, demonstrating that evolutionary legal theory can transition from a speculative framework to an empirical research program.  

Received: 20 October 2025 | Revised: 11 March 2026 | Accepted: 18 March 2026

Conflicts of Interest

The author declares that he has no conflicts of interest to this work.

Data Availability Statement

The data and code that support the findings of this study are openly available in the GitHub repository “peralta-metamorphosis” at https://github.com/adrianlerer/peralta-metamorphosis.

Author Contribution Statement

Ignacio Adrián Lerer: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data curation, Writing – original draft, Writing – review & editing, Visualization, Project administration.