---
format: "aidr-story-markdown/v1"
id: "27d8f80030b34f456f3374e76d53971894934f0adc70cace5765c40c1bfb9909"
canonical_url: "https://aidr.today/27d8f800?lang=en"
title: "Market Impact Estimation via Causal Foundation Models"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-12T04:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://arxiv.org/abs/2610.12537"]
summary: "A proof-of-concept Causal Market Simulator, a continuous-time causal prior-data fitted network trained on a synthetic market prior with confounding strength as an exact per-episode knob, tracks the unbiased true-parameter oracle at high confounding while the naive estimator's bias reaches up to 68% overestimation."
---

# Market Impact Estimation via Causal Foundation Models

> [Open the canonical story](<https://aidr.today/27d8f800?lang=en>)

**Published:** 2026-10-12T04:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

A proof\-of\-concept Causal Market Simulator, a continuous\-time causal prior\-data fitted network trained on a synthetic market prior with confounding strength as an exact per\-episode knob, tracks the unbiased true\-parameter oracle at high confounding while the naive estimator's bias reaches up to 68% overestimation\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.12537>)