# Predictive gains, causal losses: why interventional competence cannot be learned from data alone

**Published:** November 4, 2026
**Author:** Marcus Thomas
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/predictive-gains-causal-losses-why-interventional-competence-cannot-be-l

arXiv:2611.03861v1 Announce Type: new Abstract: Retaining predictive gains can require persistent errors in a model's response to interventions. For deterministic predictors with finite second moments under squared-error loss, any observational advantage over the best predictor…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2611.03861)

**Tags:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*