---
title: "Trait-Conditioned Latent Response-Process States"
output: rmarkdown::html_vignette
vignette: >
  %\VignetteIndexEntry{Trait-Conditioned Latent Response-Process States}
  %\VignetteEngine{knitr::rmarkdown}
  %\VignetteEncoding{UTF-8}
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(collapse = TRUE, comment = "#>")
library(eyeprocess)
```

M4 extends the M3 response + response-time + gaze + pupil measurement backbone with a sequential latent response-process state. The state is a statistical configuration of process measurements, not a psychological construct.

```{r}
sim <- simulate_multimodal_m4(n_person = 30, n_item = 8, seed = 20260820)
spec <- multimodal_m4_spec(n_states = 2, trait_conditioning = c("theta", "tau"))
print(spec)
```

The reference scored-response model remains state-independent. States shift RT, gaze, and pupil process channels only, and posterior state probabilities are the primary inferential object.