# Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions

Source: [Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions](<https://www.sota2.com/research/paper/69c36bfc0636e5bf4afc6421>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-08T05:00:04.658Z

Authors: Panayiotis Panayiotou, \\"Ozg\\"ur \\c{S}im\\c{s}ek

Published: 2026-03-23T22:45:15.000Z

## Abstract

Causal discovery is challenging in general dynamical systems because, without strong structural assumptions, the underlying causal graph may not be identifiable even from interventional data. However, many real-world systems exhibit directional, cascade-like structure, in which components activate sequentially and upstream failures suppress downstream effects. We study causal discovery in such chain-reaction systems and show that the causal structure is uniquely identifiable from blocking interventions that prevent individual components from activating. We propose a minimal estimator with finite-sample guarantees, achieving exponential error decay and logarithmic sample complexity. Experiments on synthetic models and diverse chain-reaction environments demonstrate reliable recovery from a few interventions, while observational heuristics fail in regimes with delayed or overlapping causal effects.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Causal Discovery on Minimal Chain environment](<https://www.sota2.com/research/sota/causal-discovery-on-minimal-chain-environment.md>): Causal Discovery; Minimal Chain environment; F1 Score: 96.3.

- [Causal Discovery on Sequential Chain environment](<https://www.sota2.com/research/sota/causal-discovery-on-sequential-chain-environment.md>): Causal Discovery; Sequential Chain environment; F1 Score: 99.5.

- [Causal Discovery on Parallel Triggers environment](<https://www.sota2.com/research/sota/causal-discovery-on-parallel-triggers-environment.md>): Causal Discovery; Parallel Triggers environment; F1 Score: 99.9.

- [Causal Discovery on Intertwined Mechanisms environment](<https://www.sota2.com/research/sota/causal-discovery-on-intertwined-mechanisms-environment.md>): Causal Discovery; Intertwined Mechanisms environment; F1 Score: 99.9.

- [Causal Discovery on Linear Slot-Machine environment](<https://www.sota2.com/research/sota/causal-discovery-on-linear-slot-machine-environment.md>): Causal Discovery; Linear Slot-Machine environment; F1 Score: 99.9.

- [Causal Discovery on Slot-Machine environment Large](<https://www.sota2.com/research/sota/causal-discovery-on-slot-machine-environment-large.md>): Causal Discovery; Slot-Machine environment Large; F1 Score: 99.8.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.22620>)

[PDF](<https://arxiv.org/pdf/2603.22620.pdf>)
