{"ID":3083851,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T06:05:08.191440377Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05797","arxiv_id":"2606.05797","title":"Causal Longitudinal Prior-Fitted Networks for Counterfactual Outcome Prediction","abstract":"Longitudinal treatment decisions require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data. Existing longitudinal causal estimators typically train a new model for each cohort or simulator. We introduce Causal Longitudinal Prior-Fitted Networks (CausalLongPFN), a prior-fitted in-context predictor for longitudinal causal prediction. The model is pretrained entirely on synthetic episodes sampled from a broad prior over temporal structural causal models, exposing it to treatment-confounder feedback, latent heterogeneity, nonlinear state evolution, delayed effects, and cumulative treatment responses. At test time, CausalLongPFN is frozen: it conditions on support trajectories, a query history, and a proposed future treatment sequence, and returns a predictive distribution over future outcomes without gradient updates or propensity-model fitting. Multi-step predictions are obtained by recursively applying the one-step predictor under the specified treatment sequence. We evaluate on branchable cancer, HIV, and warfarin benchmarks with ground-truth counterfactual labels, and on factual-only rolling-origin prediction in MIMIC-III ICU trajectories. CausalLongPFN is competitive with domain-trained longitudinal baselines on counterfactual benchmarks and performs strongly on factual MIMIC-III prediction, suggesting that broad synthetic causal pretraining can provide a useful frozen alternative when repeated domain-specific training is costly or impractical.","short_abstract":"Longitudinal treatment decisions require predicting potential outcomes under future treatment sequences in the presence of time-varying confounding, heterogeneous patient dynamics, and limited domain-specific data. Existing longitudinal causal estimators typically train a new model for each cohort or simulator. We intr...","url_abs":"https://arxiv.org/abs/2606.05797","url_pdf":"https://arxiv.org/pdf/2606.05797v1","authors":"[\"Amirhossein Zare\",\"Amirhessam Zare\",\"Herlock Rahimi\",\"Reza Salarikia\",\"Mohammad Kashkooli\"]","published":"2026-06-04T07:26:40Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"stat.ML\"]","methods":"[]","has_code":false}