{
  "id": 4862,
  "url": "https://arxiv.org/abs/2605.05706v1",
  "title": "Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine",
  "summary": "Estimating individualized treatment effects from longitudinal observational data is central to data-driven medicine, yet existing methods face a fundamental limitation: reducing confounding bias often suppresses clinically informative heterogeneity, degrading patient-specific predictions. Here, we identify this tension as a bias-precision paradox in causal representation learning and introduce sampling-based maximum mean discrepancy (sMMD), a stochastic alignment strategy that replaces global ad",
  "authors": "Peisong Zhang, Manqiang Peng, Yuxuan Wu, Pawit Phadungsaksawasdi, Wesley Yeung, Ye Zhang et al.",
  "category": "research",
  "topics": "bias-fairness,safety-alignment,healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-07T05:51:21.000Z",
  "fetched_at": "2026-07-14T16:31:17.584Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4862",
  "original_url": "https://arxiv.org/abs/2605.05706v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}