mlsanityData to 14 Oct 2026

Orca: Neural Operators for Causal Reasoning in Continuous Time

arXiv 2607.27867 ↗First posted 30 Jul 2026cs.AIcited by 0

On the map: LLM reasoning → Causal reasoning in LLMs

Abstract (arXiv)

Structural causal models are the standard language for reasoning about interventions and counterfactuals, but they describe static variables, typically measured once, and usually forbid cyclic dependencies. Many systems we care about, such as patients, climates, and economies, instead evolve continuously in time, are observed at irregular time points, and contain feedback loops. We argue that neural operator learning provides a natural foundation for causal reasoning in this setting, and propose Orca, a framework in which each node of the causal graph is a function of time and each mechanism is a learned map between function spaces. We extend existing neural operator architectures to express causal mechanisms: a mechanism computes the function value of a node from its parent nodes by taking several parent functions as input, respects the arrow of time, and treats latent exogenous noise as a function that can be inferred and reused for counterfactuals. We formalize the model class and demonstrate counterfactual reasoning on synthetic continuous-time examples. Code is available at https://github.com/gerritgr/orca

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning. Builds on 13 of its 22 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

13 of 22 references.

References · 13

  1. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
  2. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
  3. 2017Deep Setscited by 1,421
  4. 2020Neural Operator: Graph Kernel Network for Partial Differential Equationscited by 734
  5. 2022MIONet: Learning multiple-input operators via tensor productcited by 181
  6. 2019Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changescited by 166
  7. 2019Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Modelscited by 117
  8. 2018Causal Modeling of Dynamical Systemscited by 24
  9. 2025Stochastic Process Learning via Operator Flow Matchingcited by 14
  10. 2025Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learningcited by 12
  11. 2024Universal Functional Regression with Neural Operator Flowscited by 9
  12. 2023A Measure-Theoretic Axiomatisation of Causalitycited by 8
1 more
  1. 2025The Case for Time in Causal DAGscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025TempoBench: Reasoning Execution Without Causal Attribution Is Just Simulation
  2. 2025CausalARC: Abstract Reasoning with Causal World Models
  3. 2025Temporal Causal Reasoning with (Non-Recursive) Structural Equation Models
  4. 2025The Causal Round Trip: Generating Authentic Counterfactuals by Eliminating Information Loss
  5. 2025Towards Error-Centric Intelligence II: Energy-Structured Causal Models
  6. 2026Continual learning and refinement of causal models through dynamic predicate invention
  7. 2026CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators
  8. 2023Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning