Metraipolis › archive › dc_6e04ecdecd41

Symmetries and Causality: Causal Effect Identification Beyond IID Data — arXiv:2609.03697

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.03697
License (as archived): CC0-1.0
Archived: 2026-10-17T01:12:03.666Z
SHA-256 of the archived text: e23e7587b18d179dc538a7ba765df24d7151e18c18f0e7d331414bc1c472b375
Stable URL of this page: https://metraipolis.com/documento/dc_6e04ecdecd41

How to cite

Symmetries and Causality: Causal Effect Identification Beyond IID Data — arXiv:2609.03697 — arXiv (en), https://arxiv.org/abs/2609.03697 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6e04ecdecd41 (Metraipolis archive dc_6e04ecdecd41, sha256 e23e7587b18d179dc538a7ba765df24d7151e18c18f0e7d331414bc1c472b375)

BibTeX

@misc{dc6e04ecdecd41,
  title = {Symmetries and Causality: Causal Effect Identification Beyond IID Data — arXiv:2609.03697},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03697},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6e04ecdecd41; sha256 e23e7587b18d179dc538a7ba765df24d7151e18c18f0e7d331414bc1c472b375},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03697. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In the natural sciences, symmetries and cause-effect relationships are ubiquitous. Yet for complex machine-learning tasks, like world-modeling in reinforcement learning, they appear difficult to harness. We propose a formal description of statistical systems based on symmetries in data leaving causal mechanisms invariant. The result is an abstract, simple and general mathematical language for causal reasoning. This paper provides formal descriptions of models and queries, setting up this language, and the formal infrastructure and strategies for their mathematically rigorous identification from data within this formalism. This approach reproduces and matches standard theoretical results on IID data and transport of experimental and non-experimental data. But its main purpose is to unify and substantially extend the scope of causal reasoning, in going beyond IID data and in approaching complex causal queries not captured by do- or soft-interventions. This new perspective on causally relevant aspects of data-modeling additionally sheds new light on well-known structures like c-components or hedges but also includes aspects of missing data and is inherently well-suited for the description of transfer and robustness properties.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI).
Categorie arXiv: Statistics Theory (math.ST) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.03697 — 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 2026-10-17T00:28:02.996Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).