Latent State Modeling of Multichannel Autonomic Signals

This repository accompanies a preregistered secondary-data study on latent state modeling of multichannel autonomic signals. The project tests whether physiological time series are better described by switching state-space models with recurrent latent states than by a single non-switching baseline, and whether retained states can be described with physiological fingerprints, matched across datasets, and partly preserved under frozen-transfer testing. Three public datasets are analyzed: WESAD, CASE, and VitaStress. All datasets are processed using a common preregistered analysis logic based on protocol-grounded baseline–task–recovery segmentation, fixed one-second windows, within-dataset standardization, and candidate state solutions from K = 2 to K = 10 compared with a K = 1 baseline. The repository contains analysis scripts, derived one-second window files, model-fit summaries, inferred state sequences, state-level fingerprint tables, cross-dataset matching outputs, frozen-transfer outputs, supplementary figures, and implementation notes documenting dataset selection and deviations from the original preregistered dataset plan. Version 1.3: This version updates the manuscript title, framing, supplementary material title, and repository description to match the revised manuscript prepared for a biomedical signal processing journal. The updated version frames the study as a reproducible physiological signal-modeling framework rather than as a general psychophysiological theory paper. It retains the preregistered H1–H4 analysis sequence, the final WESAD, CASE, and VitaStress implementation, the K = 1 versus K = 2–10 model comparison, the state-level fingerprint framework, cross-dataset correspondence testing, and frozen-transfer reporting. It also adds clearer reporting on the limits of public secondary datasets, including constraints on raw signal-quality assessment, artifact annotations, and representative raw physiological traces. Preregistration and full project materials are also available on OSF: Full project: https://osf.io/7ahx5 Preregistration: https://osf.io/4jrbg/overview