DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.

Causing: CAUsal INterpretation using Graphs

Machine learning research code for causal perception: comparing competing structural causal models (SCMs) via interventional and counterfactual distributions, applied to fair credit decisions. Open source by Santander AI Lab.

A Python implementation of the do-calculus of Judea Pearl et al.

Summary of useful results in Causal Inference

"Causality: Models, Reasoning, and Inference-Judea Pearl(2009)"中文翻译及学习笔记

Use regression, inverse probability weighting, and matching to close confounding backdoors and find causation in observational data

A Powerful Python Library for Causal Inference

A minimal causal world model — learn causal graphs, intervene, plan.

Generate fictional-but-coherent causal operations worlds (executable sim + time-series + ground-truth causal answer-key) from a natural-language description — for benchmarking causal-discovery and control agents.

Memo's research works.

A five-layer causal-neuro-symbolic framework for machine fault diagnosis. Independently verifies neural predictions against machine physics; domain-agnostic via pluggable providers.

This repository contains an implementation of BP-CDM introduced in "Data-Driven Decision Support for Business Processes: Causal Reasoning on Interventions".

Automatically determine whether a causal effect is identifiable

An open-source framework for measuring true marketing channel contributions using causal inference without user-level tracking.

CausalLab — Interactive Causal Inference & Discovery Laboratory. 6 modules: SCM Builder, do-Calculus, PC Algorithm, Simpson's Paradox, IV Lab, Counterfactuals. Zero dependencies.

Bayesian Causal Inference in Doubly Gaussian DAG-probit Models

Demystifying Judea Pearl's do-calculus and the Backdoor Criterion by hand. Resolving a curated Simpson's Paradox using structural causal modeling on superhero battle mechanics.

Judea Pearl’s Causal Ladder, featuring Association, Intervention, and Counterfactual models.

Deterministic selective-labels harness: measures PD models on the declined population real data never sees, and prices it in profit. Plants ground truth; the operating frontier is a 25-seed distribution, not a point. sklearn-only, byte-reproducible.