# When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments

arXiv: https://arxiv.org/abs/2609.17772 · HTML: https://mlsanity.com/paper/2609.17772/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 15 Sep 2026.

## Builds on (most cited first, 16 of 16)

- [Learning Representations for Counterfactual Inference](https://mlsanity.com/paper/1605.03661/) (2016)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder](https://mlsanity.com/paper/1609.08816/) (2016)
- [Exact post-selection inference, with application to the lasso](https://mlsanity.com/paper/1311.6238/) (2013)
- [Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates](https://mlsanity.com/paper/2005.00649/) (2020)
- [How to Make Causal Inferences Using Texts](https://mlsanity.com/paper/1802.02163/) (2018)
- [Using simulation studies to evaluate statistical methods](https://mlsanity.com/paper/1712.03198/) (2017)
- [Assessing Time-Varying Causal Effect Moderation in Mobile Health](https://mlsanity.com/paper/1601.00237/) (2016)
- [Structural Nested Models and G-estimation: The Partially Realized Promise](https://mlsanity.com/paper/1503.01589/) (2015)
- [Conceptualizing Treatment Leakage in Text-based Causal Inference](https://mlsanity.com/paper/2205.00465/) (2022)
- [Inference for Regression with Variables Generated by AI or Machine Learning](https://mlsanity.com/paper/2402.15585/) (2024)
- [The Micro-Randomized Trial for Developing Digital Interventions: Experimental Design and Data Analysis Considerations](https://mlsanity.com/paper/2107.03544/) (2021)
- [Deconfounding Scores: Feature Representations for Causal Effect Estimation with Weak Overlap](https://mlsanity.com/paper/2104.05762/) (2021)
- [Estimating Time-Varying Causal Excursion Effect in Mobile Health with Binary Outcomes](https://mlsanity.com/paper/1906.00528/) (2019)
- [Deconfounding Scores and Representation Learning for Causal Effect Estimation with Weak Overlap](https://mlsanity.com/paper/2604.00811/) (2026)

## Abstract (arXiv)

AI-generated covariates from notes, conversations, images, and wearable streams can change the causal question when their roles are left unspecified. A generated feature may represent a treatment version, pre-action state, history, design variable, mediator, outcome proxy, observation process, or intercurrent event; these roles are not interchangeable. We formulate a causal type discipline for sequential experiments: a versioned representation map, a causal role classifier, a claim-status filter, and an estimand lock. The lock fixes a standardized proximal effect before generated covariates enter the analysis. Under audit correctness and standard identification assumptions, admissible role assignments preserve this estimand. We apply the established conditional-covariance characterization of compression bias to substitution of generated representations for design-relevant states. A standardized decomposition separates compression, conditional-law, and standardization drift. Further results cover mediator adjustment, post-action leakage, marker-intervention conflation, outcome-guided discovery, and state-measurement error. Cluster-level orthogonal estimators distinguish empirical and superpopulation targets under repeated sessions and missing outcomes. Simulations show that refinement helps when it retains design-relevant information, whereas design erasure, leakage, and same-data marker selection can produce bias or undercoverage. The framework places causal semantics and claim status before confirmatory inference with generated representations.