com.eignex.kumulant/stat/regression/glm/Link/Logit Logit @Serializable@SerialName(value = "Logit")data object Logit : Link(source)mu = sigmoid(eta). Bernoulli likelihood; expects y in {0, 1}. Functions curvature open override fun curvature(eta: Double): Double(source)Second derivative of the per-observation negative log-likelihood at eta. invMean open override fun invMean(eta: Double): Double(source)Inverse link: maps the linear predictor eta to the response mean. loss open override fun loss(eta: Double, y: Double): Double(source)softplus(eta) - y * eta = log(1 + exp(eta)) - y * eta, computed stably.