mlsanityData to 7 Oct 2026

Physical Simulators as Do-Operators: Causal Discovery under Latent Confounders for AI-for-Science

arXiv 2605.07467 ↗First posted 8 May 2026cs.LG cs.AI cs.ETcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing interventional causal discovery methods -- IGSP, DCDI, ENCO -- assume causal sufficiency (no latent confounders) and rely on virtual interventions in synthetic simulators. In AI-for-Science settings such as molecular design and materials science, latent confounders are ubiquitous and real interventions (e.g., physics-based simulations) require hours to days per data point. We propose CFM-SD (Causal Flow Matching with Simulation Data), which uses first-principles physical simulators as do-operators in Pearl's interventional calculus to simultaneously handle latent confounders and real interventional data. Theoretically, d-variable causal structure is identifiable with O(d) single-variable interventions -- the minimum under physical realizability constraints. In Intrinsic Evaluation on synthetic data (γ=0.2--0.8), CFM-SD achieves average F1=0.800 vs. F1=0.127--0.562 for all baselines. In Extrinsic Evaluation on real scientific data, CFM-SD achieves 57--58% bias reduction in molecular toxicity prediction and battery electrolyte optimization, demonstrating practical value beyond synthetic benchmarks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 33 references that are in the map. First posted on arXiv 8 May 2026.

Builds on

10 of 33 references.

References · 10

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  3. 2020Differentiable Causal Discovery from Interventional Datacited by 218
  4. 2021Efficient Neural Causal Discovery without Acyclicity Constraintscited by 82
  5. 2017Permutation-based Causal Inference Algorithms with Interventionscited by 78
  6. 2019Permutation-Based Causal Structure Learning with Unknown Intervention Targetscited by 69
  7. 2022Interventions, Where and How? Experimental Design for Causal Models at Scalecited by 49
  8. 2023Causal normalizing flows: from theory to practicecited by 49
  9. 2021Learning Neural Causal Models with Active Interventionscited by 40
  10. 2025DeCaFlow: A deconfounding causal generative modelcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Intervention-Based Time Series Causal Discovery via Simulator-Generated Interventional Distributions
  2. 2026CausalArena: Benchmarking Causal Discovery in the Foundation Model Era
  3. 2026Why LLMs Fail at Causal Discovery and How Interventional Agents Escape
  4. 2024LLM-initialized Differentiable Causal Discovery
  5. 2026Traceable Latent Variable Discovery Based on Multi-Agent Collaboration
  6. 2026Latent Confounded Causal Discovery via Lie Bracket Geometry
  7. 2025Causal-Copilot: An Autonomous Causal Analysis Agent
  8. 2026CausalGame: Benchmarking Causal Thinking of LLM Agents in Games