# Formalizing and falsifying causal pathways of rare events

arXiv: https://arxiv.org/abs/2605.31254 · HTML: https://mlsanity.com/paper/2605.31254/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 46 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 29 of 29)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Feature relevance quantification in explainable AI: A causal problem](https://mlsanity.com/paper/1910.13413/) (2019)
- [Causal Consistency of Structural Equation Models](https://mlsanity.com/paper/1707.00819/) (2017)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [Abstracting Causal Models](https://mlsanity.com/paper/1812.03789/) (2018)
- [Probabilities of Causation: Bounds and Identification](https://mlsanity.com/paper/1301.3898/) (2013)
- [Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?](https://mlsanity.com/paper/2502.15657/) (2025)
- [Causal structure based root cause analysis of outliers](https://mlsanity.com/paper/1912.02724/) (2019)
- [Causal Inference-Based Root Cause Analysis for Online Service Systems with Intervention Recognition](https://mlsanity.com/paper/2206.05871/) (2022)
- [Shapley Flow: A Graph-based Approach to Interpreting Model Predictions](https://mlsanity.com/paper/2010.14592/) (2020)
- [MicroHECL: High-Efficient Root Cause Localization in Large-Scale Microservice Systems](https://mlsanity.com/paper/2103.01782/) (2021)
- [Root Cause Analysis In Microservice Using Neural Granger Causal Discovery](https://mlsanity.com/paper/2402.01140/) (2024)
- [Causal Explanations and XAI](https://mlsanity.com/paper/2201.13169/) (2022)
- [Causal Sufficiency and Actual Causation](https://mlsanity.com/paper/2102.02311/) (2021)
- [Causal discovery in heavy-tailed models](https://mlsanity.com/paper/1908.05097/) (2019)
- [Root Cause Analysis of Outliers with Missing Structural Knowledge](https://mlsanity.com/paper/2406.05014/) (2024)
- [Root Cause Analysis for Microservice System based on Causal Inference: How Far Are We?](https://mlsanity.com/paper/2408.13729/) (2024)
- [Non-parametric causal effects based on longitudinal modified treatment policies](https://mlsanity.com/paper/2006.01366/) (2020)
- [Root cause discovery via permutations and Cholesky decomposition](https://mlsanity.com/paper/2410.12151/) (2024)
- [An Interventionist Approach to Mediation Analysis](https://mlsanity.com/paper/2008.06019/) (2020)
- [Meaningful Causal Aggregation and Paradoxical Confounding](https://mlsanity.com/paper/2304.11625/) (2023)
- [Extremes of structural causal models](https://mlsanity.com/paper/2503.06536/) (2025)
- [Robust Root Cause Diagnosis using In-Distribution Interventions](https://mlsanity.com/paper/2505.00930/) (2025)
- [time2time: Causal Intervention in Hidden States to Simulate Rare Events in Time Series Foundation Models](https://mlsanity.com/paper/2509.05801/) (2025)
- [Toward Universal Laws of Outlier Propagation](https://mlsanity.com/paper/2502.08593/) (2025)
- [Decomposition of Probabilities of Causation with Two Mediators](https://mlsanity.com/paper/2505.04983/) (2025)
- [Beyond Single-Feature Importance with ICECREAM](https://mlsanity.com/paper/2307.09779/) (2023)

## Abstract (arXiv)

Building on recent formalizations of root cause analysis for rare events (``outliers'') in structural equation models, we propose a formal definition of a causal pathway and discuss its testable implications. We identify conditions under which these implications depend only on a causal abstraction defined by the pathway of rare events, rather than on the full causal graph of the underlying system. Accordingly, we introduce an abstraction of causal structure to pathways of rare events that bridges simple verbal causal explanations and detailed causal modeling.