Metraipolis › archive › dc_b74d596e10fb

CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes — arXiv:2609.39523

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39523
License (as archived)
CC0-1.0
Archived
2026-10-07T13:46:18.265Z
SHA-256 of the archived text
228f52c4346b6cb015262db9366c1ace96224655e710b535770a2e6348dd5427
Stable URL of this page
https://metraipolis.com/documento/dc_b74d596e10fb

How to cite

CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes — arXiv:2609.39523 — arXiv (en), https://arxiv.org/abs/2609.39523 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b74d596e10fb (Metraipolis archive dc_b74d596e10fb, sha256 228f52c4346b6cb015262db9366c1ace96224655e710b535770a2e6348dd5427)
BibTeX
@misc{dcb74d596e10fb,
  title = {CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental Regimes — arXiv:2609.39523},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39523},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b74d596e10fb; sha256 228f52c4346b6cb015262db9366c1ace96224655e710b535770a2e6348dd5427},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39523. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Causal foundation models (CFMs) amortise causal inference over priors of synthetic structural causal models (SCMs), predicting the effect of an experiment on a specific variable. However, observational data alone may leave multiple causal models compatible with available evidence, while experimental data with interventions on exactly the variable of interest might be unavailable. This work studies CFMs as a method to combine finite observational and surrogate-interventional datasets in order to predict a target conditional interventional distribution (CID) more accurately than with observational data alone. We first formalise the conceptual benefits of surrogate experiments. Building on this analysis, we introduce \textsc{Foundation Models for Causal Inference from Diverse Experimental Regimes} (\emph{CIDER-FM}), a causal foundation model that uses an intervention-aware representation and hierarchical three-axis attention to exchange information across variables, samples, and experimental regimes. We evaluate CIDER-FM against a wide range of baselines across diverse synthetic graph and mechanism families, as well as on both simulated and real-world data from Causal Chambers. Our results demonstrate strong CID prediction performance and show that incorporating experimental context can improve predictions over observational data alone.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.39523 — 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 2026-10-07T13:18:10.404Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).