Metraipolis › archive › dc_22d2e25fb397
Unit-level aggregation breaks coverage in causal foundation models — arXiv:2610.22770
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22770
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:21:20.974Z
- SHA-256 of the archived text
fd31b36dabeb69bc3bfee39598221a96c64d55dd7de7c70cad33c3301f248493- Stable URL of this page
https://metraipolis.com/documento/dc_22d2e25fb397
How to cite
Unit-level aggregation breaks coverage in causal foundation models — arXiv:2610.22770 — arXiv (en), https://arxiv.org/abs/2610.22770 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_22d2e25fb397 (Metraipolis archive dc_22d2e25fb397, sha256 fd31b36dabeb69bc3bfee39598221a96c64d55dd7de7c70cad33c3301f248493)
BibTeX
@misc{dc22d2e25fb397,
title = {Unit-level aggregation breaks coverage in causal foundation models — arXiv:2610.22770},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22770},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_22d2e25fb397; sha256 fd31b36dabeb69bc3bfee39598221a96c64d55dd7de7c70cad33c3301f248493},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22770. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Causal foundation models (CFMs) show promising results for treatment-effect estimation, with unit-level estimates that are competitive on standard benchmarks. Many causal analyses, however, inform decisions through effects averaged over groups of units, such as the full sample, the treated units, or a subgroup, and for such decisions a CFM is useful only if its credible intervals are calibrated. We examine these intervals and find that their coverage degrades, both in simple synthetic settings and on standard benchmarks. On ACIC 2016, for example, temperature-calibrated 95% intervals from CausalPFN fall below nominal coverage beyond groups of 30 out of 4802 units, and intervals for the full-sample average contain the true value in only 20% of datasets. We trace this problem to how these models are trained and how their intervals are formed. They output a predictive distribution for one unit at a time and, at inference time, combine the unit-level variances as if the errors on different units were independent. We show formally that posterior uncertainty over the data-generating process makes these errors correlated. As a result, the combined variance is too small by a factor that grows with the size of the group. Empirically, this factor predicts where coverage fails and by how much. We then show that two neural process models, which make joint predictions for a group of units, account for this correlation and substantially improve coverage on synthetic tasks and, as heads on a frozen CausalPFN, on all six benchmarks. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.22770 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:17:41.700Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).