Evaluating Model Retraining under Drift: Paired Comparisons of Cumulative Subgroup Disparity

Clinical risk models routinely achieve strong aggregate performance while producing materially different error rates across patient subgroups. Audit pipelines have been proposed to catch this, but their components are rarely stress-tested, so it is unclear which parts of an audit can be trusted and under what conditions. We present KAISEN, a five-phase audit pipeline covering subgroup stratification, disparity measurement, mechanism diagnostics, post-hoc mitigation, and drift monitoring, evaluated to the point of failure on a synthetic benchmark of 16 disease tasks, 15 social-determinant axes from Healthy People 2030, and three prespecified intersections. Four findings follow. (i) Significance tracks each axis's gap against its own minimum detectable effect: rank correlation between significance count and raw equalized-odds difference (EOD) across the 15 axes is rho = 0.56, rising to rho = 0.78 once EOD is standardized by that floor. (ii) Per-group threshold optimization reduces EOD in 48 of 48 held-out runs (paired delta = -0.285, 95% CI [-0.313, -0.252]), while group-wise Platt scaling -- the better calibrator -- behaves as a coin flip on EOD (19 of 48 runs improved, 95% CI [0.26, 0.55]) with mean effect near zero, so what an audit should report is the variance, not the average. (iii) The mechanism diagnostic classifies 144 of 144 controlled cases correctly but recovers none of 48 model-driven cases under proxy misspecification, with no signal that it failed. (iv) CUSUM failures and false alarms track cohort realization far more than disease: at the reference threshold, all 27 false alarms and 7 of 8 missed shifts come from different seeds (chi-squared p = 0.002), so a threshold tuned on one cohort fails to transfer. All results are synthetic with known ground truth and do not establish clinical validity. Code, artifacts, and scripts reproducing every number are released.

We study the problem of understanding where two populations differ within a feature space, which we formalize in the concept of a differential subgroup: a subset of individuals from both populations who, despite sharing similar characteristics, exhibit exceptional differences in a target outcome. Differential subgroups reveal the regions of the feature space where population-level gaps are most pronounced and can help practitioners identify the covariate combinations that are structurally responsible for these differences, e.g.~in clinical analysis, model diagnostics, or treatment-effect studies. We introduce a general optimization objective for discovering differential subgroups and establish conditions under which the resulting subgroups admit a causal interpretation of population differences. We propose DiffSub, a gradient-based approach that discovers interpretable differential subgroups in tabular data. Across synthetic benchmarks, medical case studies, model-error analyses, and treatment-effect settings, DiffSub identifies informative subgroups that reveal where population differences arise and why.

Drifting models are capable one-step generative models trained to follow a drifting field. The field combines attractive and repulsive softmax-weighted centroids over the data and current-generator distributions. In practice, only a minibatch of $n$ samples from each distribution is available, and each centroid is approximated by an empirical estimate. In this paper, we begin by showing that the minibatch centroid is in general a biased estimator of the target centroid, with a pointwise $O(1/n)$ bias arising from softmax self-normalization. Correcting this bias requires the expectation over the full distribution, which is intractable. We instead approximate the leading bias term from in-batch statistics and propose Analytical Bias Correction (ABC), a closed-form plug-in adjustment. We prove that ABC reduces the bias from $O(1/n)$ to $O(1/n^2)$, introduces no first-order increase in total variance, and preserves convex-hull containment of the corrected centroid. In practice, ABC requires only two additional lines of code and has negligible wall-time overhead under compiled execution. Toy experiments confirm the theoretical $O(1/n)$ and $O(1/n^2)$ scaling. On CIFAR-10, ABC reduces FID and trains faster, with the largest gains at small $n$, where the bias is most significant.