{"ID":2837110,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20601","arxiv_id":"2511.20601","title":"The Driver-Blindness Phenomenon: Why Deep Sequence Models Default to Autocorrelation in Blood Glucose Forecasting","abstract":"Deep sequence models for blood glucose forecasting consistently fail to leverage clinically informative drivers--insulin, meals, and activity--despite well-understood physiological mechanisms. We term this Driver-Blindness and formalize it via $Δ_{\\text{drivers}}$, the performance gain of multivariate models over matched univariate baselines. Across the literature, $Δ_{\\text{drivers}}$ is typically near zero. We attribute this to three interacting factors: architectural biases favoring autocorrelation (C1), data fidelity gaps that render drivers noisy and confounded (C2), and physiological heterogeneity that undermines population-level models (C3). We synthesize strategies that partially mitigate Driver-Blindness--including physiological feature encoders, causal regularization, and personalization--and recommend that future work routinely report $Δ_{\\text{drivers}}$ to prevent driver-blind models from being considered state-of-the-art.","short_abstract":"Deep sequence models for blood glucose forecasting consistently fail to leverage clinically informative drivers--insulin, meals, and activity--despite well-understood physiological mechanisms. We term this Driver-Blindness and formalize it via $Δ_{\\text{drivers}}$, the performance gain of multivariate models over match...","url_abs":"https://arxiv.org/abs/2511.20601","url_pdf":"https://arxiv.org/pdf/2511.20601v1","authors":"[\"Heman Shakeri\"]","published":"2025-11-25T18:30:55Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}