Metraipolis › archive › dc_07caea9f8705

When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments — arXiv:2609.17772

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.17772
License (as archived)
CC0-1.0
Archived
2026-10-10T03:22:25.475Z
SHA-256 of the archived text
2a7219247848b4b4e6b0dadff2f51daadc71962ec158ee89128e3ede9c55dcf2
Stable URL of this page
https://metraipolis.com/documento/dc_07caea9f8705

How to cite

When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments — arXiv:2609.17772 — arXiv (en), https://arxiv.org/abs/2609.17772 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07caea9f8705 (Metraipolis archive dc_07caea9f8705, sha256 2a7219247848b4b4e6b0dadff2f51daadc71962ec158ee89128e3ede9c55dcf2)
BibTeX
@misc{dc07caea9f8705,
  title = {When AI Generates Covariates: Causal Typing and Estimand Drift in Sequential Experiments — arXiv:2609.17772},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.17772},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07caea9f8705; sha256 2a7219247848b4b4e6b0dadff2f51daadc71962ec158ee89128e3ede9c55dcf2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17772. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Methodology (stat.ME) ; Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM).
Pagina del lavoro: https://arxiv.org/abs/2609.17772 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:04:13.765Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).