Cross-dialect syntactic variation tests the limits of comparative analysis, owing to the entanglement of inheritance and contact in dialect systems. Addressing this challenge requires analytical tools combining the theoretical depth of formal models of grammatical competence with quantitative taxonomic techniques. The Parametric Comparison Method (PCM) embodies this integration by quantifying structural similarity across grammars through the comparison of abstract syntactic rules. The method has been shown to achieve a good degree of resolution in dialectal domains, capturing subtle contrasts and yielding configurations aligning with phylogenetic expectations while remaining sensitive to contact-induced convergence. Fully assessing its effectiveness as a resource for the quantitative study of syntactic dialectology, however, requires an infrastructure that ensures systematic data collection, consistent parameter setting, and robust statistical evaluation across diverse datasets. The PCM Hub is a web-based resource designed for this purpose. It integrates guided elicitation, automated parameter-setting procedures, data management, and the computation of distances and automatic classifications within a unified environment. By standardizing the transition from raw linguistic observations to a structured, replicable empirical apparatus, the PCM Hub provides the practical and quantitative support necessary to test the power of the PCM across expanded comparative domains.

The use of parameters in the description of natural language syntax has to balance between the need to discriminate among (sometimes subtly different) languages, which can be seen as a cross-linguistic version of Chomsky’s (1964) descriptive adequacy, and the complexity of the acquisition task that a large number of parameters would imply, which is a problem for explanatory adequacy. Here we present a novel approach in which a machine learning algorithm is used to find dependencies in a table of parameters. The result is a dependency graph in which some of the parameters can be fully predicted from others. These empirical findings can be then subjected to linguistic analysis, which may either refute them by providing typological counter-examples of languages not included in the original dataset, dismiss them on theoretical grounds, or uphold them as tentative empirical laws worth of further study.