Metraipolis › archive › dc_01a56a2c4e80
Causal Foundation Models — arXiv:2609.03003
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.03003
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T02:07:43.615Z
- SHA-256 of the archived text
2a28b403fa4ec125e4d4a57ea3b10a8234710c6a1f30174f835209e296995269- Stable URL of this page
https://metraipolis.com/documento/dc_01a56a2c4e80
How to cite
Causal Foundation Models — arXiv:2609.03003 — arXiv (en), https://arxiv.org/abs/2609.03003 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01a56a2c4e80 (Metraipolis archive dc_01a56a2c4e80, sha256 2a28b403fa4ec125e4d4a57ea3b10a8234710c6a1f30174f835209e296995269)
BibTeX
@misc{dc01a56a2c4e80,
title = {Causal Foundation Models — arXiv:2609.03003},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.03003},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01a56a2c4e80; sha256 2a28b403fa4ec125e4d4a57ea3b10a8234710c6a1f30174f835209e296995269},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03003. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Causal inference is the practice of estimating the effect of a treatment or intervention from data. It traditionally requires a bespoke pipeline for every new problem: first proposing a causal mechanism, selecting a compatible estimator, and finally training it. Meanwhile, across diverse settings and modalities, much of machine learning has shifted to the paradigm of foundation models: networks pretrained once at scale and applied to new tasks without fine-tuning. Causal foundation models (CFMs) bring this paradigm to causal inference. CFMs are pretrained neural networks that estimate causal quantities, such as the average treatment effect, on entirely new datasets using in-context learning without requiring model updates. This work provides a practical introduction to this emerging area. We summarize the necessary background in causal inference and machine learning before discussing CFMs. Throughout, we include example code and Jupyter notebooks. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2609.03003 — 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 2026-10-17T01:47:25.517Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).