# CausalGuard: Conformal Inference under Graph Uncertainty

arXiv: https://arxiv.org/abs/2605.21928 · HTML: https://mlsanity.com/paper/2605.21928/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 21 May 2026.

## Builds on (most cited first, 21 of 21)

- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [Estimation and Inference of Heterogeneous Treatment Effects using Random Forests](https://mlsanity.com/paper/1510.04342/) (2015)
- [Conformal Prediction Under Covariate Shift](https://mlsanity.com/paper/1904.06019/) (2019)
- [Causal Effect Inference with Deep Latent-Variable Models](https://mlsanity.com/paper/1705.08821/) (2017)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Conformal Inference of Counterfactuals and Individual Treatment Effects](https://mlsanity.com/paper/2006.06138/) (2020)
- [Causal Discovery with Language Models as Imperfect Experts](https://mlsanity.com/paper/2307.02390/) (2023)
- [Sensitivity Analysis of Individual Treatment Effects: A Robust Conformal Inference Approach](https://mlsanity.com/paper/2111.12161/) (2021)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Conformal Meta-learners for Predictive Inference of Individual Treatment Effects](https://mlsanity.com/paper/2308.14895/) (2023)
- [VERGE: Formal Refinement and Guidance Engine for Verifiable LLM Reasoning](https://mlsanity.com/paper/2601.20055/) (2026)
- [Forte : Finding Outliers with Representation Typicality Estimation](https://mlsanity.com/paper/2410.01322/) (2024)
- [Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation](https://mlsanity.com/paper/2412.13952/) (2024)
- [K4: Online Log Anomaly Detection Via Unsupervised Typicality Learning](https://mlsanity.com/paper/2507.20051/) (2025)
- [LABELING COPILOT: A Deep Research Agent for Automated Data Curation in Computer Vision](https://mlsanity.com/paper/2509.22631/) (2025)
- [Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers](https://mlsanity.com/paper/2601.07036/) (2026)
- [Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM](https://mlsanity.com/paper/2509.22832/) (2025)
- [Toward Guarantees for Clinical Reasoning in Vision Language Models via Formal Verification](https://mlsanity.com/paper/2602.24111/) (2026)
- [CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG](https://mlsanity.com/paper/2602.05143/) (2026)

## Abstract (arXiv)

Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph misspecification can cause under-coverage, while graph-agnostic conformal wrappers may regain nominal coverage only through large padding. We introduce CausalGuard, a structure-weighted conformal framework that calibrates after aggregating graph-conditional doubly robust pseudo-outcomes. Candidate DAGs are proposed from an LLM-derived edge prior, pruned by conditional-independence tests, and reweighted by Bayesian Information Criterion. A composite nonconformity score then calibrates the posterior-weighted pseudo-outcome. CausalGuard provides distribution-free finite-sample marginal coverage for this aggregated pseudo-outcome; under causal identification, overlap, conditional-mean nuisance stability, and concentration on target-aligned valid adjustment strategies, its conditional mean converges to the true Conditional Average Treatment Effect. Across five benchmarks, CausalGuard attains mean coverage above the nominal 90% level for the directly evaluable target and reduces width when graph-agnostic conformal baselines require large padding. Stress tests show that CausalGuard suppresses invalid collider adjustment and remains stable under misspecified priors when the retained candidate set is data-supported.