arXiv Machine Learning June 4, 2026 By Dario Rancati, Max Welling, Francesco Locatello

Reconciling Causality and Non-Equilibrium Thermodynamics with Hamiltonian Causal Models

Read the original on arXiv Machine Learning →

arXiv:2606. 04822v1 Announce Type: new Abstract: Causal modeling of physical temporal phenomena must handle interventions that act along trajectories, nonstationary induced laws, path-dependent effects, and feedback mediated by dynamics, all challenging in standard causal models.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 28

Beyond Directed Acyclic Graphs: Causal Zeros and Causal Differential Equations

arXiv:2607. 22910v1 Announce Type: new Abstract: Pearl's structural causal model (SCM) framework, built on directed acyclic graphs (DAGs) and the do-calculus, is the dominant formal language for causal reasoning.

By Sergei V. Kalinin

arXiv Machine Learning

Jul 23

Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States

arXiv:2607. 19531v1 Announce Type: cross Abstract: Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors.

By Faraz Dadgostari, Neda Nazemi

Hugging Face Trending Papers

Jul 21

Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States

Power grids, markets, and interacting populations, settle into feedback driven equilibria observed through unknown sensors. Our Equilibrium Causal Game (ECG) joins a game to its cyclic causal model, hidden inputs, sensor map, and rules for interventions and equilibrium selection; interventions edit declared objects and recompute equilibrium.

arXiv Machine Learning

1d ago

Generalised Transportability via Causal Abstractions

arXiv:2608. 15645v1 Announce Type: new Abstract: Transporting a causal conclusion from a source study population to a target one is a fundamental problem in causal inference.

By Yorgos Felekis, Paris Giampouras, Fabio Massimo Zennaro, Theodoros Damoulas

benchmarks

arXiv Machine Learning

Jun 2

Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families

arXiv:2606. 02231v1 Announce Type: cross Abstract: Temporal systems often exhibit non-stationary behaviour, such as seasonal climate variation or glucose fluctuations in patients with type-1 diabetes.

By Roel Hulsman, Carles Balsells-Rodas, Sara Magliacane

benchmarks

arXiv Machine Learning

Aug 10

Adversarial Causal Intervention Falsification

arXiv:2608. 06427v1 Announce Type: new Abstract: Generative models can reproduce an observational distribution while encoding an incorrect causal structure.

By Mojtaba Eslami

safety

Related stories

Beyond Directed Acyclic Graphs: Causal Zeros and Causal Differential Equations

Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States

Equilibrium Causal Games: Separation, Identification, and the Identifiability of Cyclic Latent States

Generalised Transportability via Causal Abstractions

Identifiable Markov Switching Models with Instantaneous Effects and Exponential Families

Adversarial Causal Intervention Falsification