Metraipolis › archive › dc_afa03a93c614
Counterfactual Predictions in Scientific Emulators Without Controlled Experiments — arXiv:2610.02252
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02252
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T22:49:52.041Z
- SHA-256 of the archived text
6c0efb28675cf58592b8d7d628cbd545e503300ee8f2455e1baa603744a63e2e- Stable URL of this page
https://metraipolis.com/documento/dc_afa03a93c614
How to cite
Counterfactual Predictions in Scientific Emulators Without Controlled Experiments — arXiv:2610.02252 — arXiv, https://arxiv.org/abs/2610.02252 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_afa03a93c614 (Metraipolis archive dc_afa03a93c614, sha256 6c0efb28675cf58592b8d7d628cbd545e503300ee8f2455e1baa603744a63e2e)
BibTeX
@misc{dcafa03a93c614,
title = {Counterfactual Predictions in Scientific Emulators Without Controlled Experiments — arXiv:2610.02252},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02252},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_afa03a93c614; sha256 6c0efb28675cf58592b8d7d628cbd545e503300ee8f2455e1baa603744a63e2e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02252. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many scientific questions require reasoning about what was never observed: What if the conditions, interventions, or history had been different? Models can predict accurately on observed data yet fail on such what-if queries when correlated inputs are varied independently. A common remedy is to add controlled simulation data in which these factors are explicitly disentangled, but this requires access to a simulator, can be computationally expensive, and inherits the simulator's modeling assumptions. We introduce ReRoute, a framework for targeted scientific what-if prediction that combines factual data with partial mechanistic knowledge, without requiring controlled intervention data for adaptation. ReRoute fixes the queried input of a pretrained backbone to a reference value, reintroduces its variation through a known mechanistic pathway, and fine-tunes on the original factual data, while leaving downstream effects to the learned dynamics. We provide a causal identification result for this construction under explicit structural assumptions, with the core argument machine-checked in Lean. After showing that ReRoute achieves highly accurate counterfactual predictions in a controlled advection-diffusion system where exact responses are available, we turn to state-of-the-art climate emulation. On held-out coupled-climate interventions, ReRoute reduces aggregate climate error by 18.2-31.8% under severe CO$_2$ distribution shifts while preserving skill under standard conditions, at a small fraction of the cost of retraining on additional controlled simulations, without even accounting for the substantial expense of generating such data. Finally, on an emulator trained from historical ERA5 reanalysis, where no counterfactual reference exists, ReRoute preserves substantially more of the surface warming implied by the observed boundary conditions under a fixed-CO$_2$ counterfactual. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Machine Learning (stat.ML). Pagina del lavoro: https://arxiv.org/abs/2610.02252 — 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 2026-10-05T22:45:55.732Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).