# From Forecasting to World Modeling: Can Temporal Foundation Models Recover Causal Response?

DevFeed: [From Forecasting to World Modeling: Can Temporal Foundation Models Recover Causal Response?](<https://devfeed.tech/articles/from-forecasting-to-world-modeling-can-temporal-foundation-models-recover-causal-response-132945.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.15009>)

Author: Juwon Hong, Minha Hwang, Venkatesh Shankar

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [AI Foundation Models](<https://devfeed.tech/topics/ai-foundation-models.md>), [Time Series](<https://devfeed.tech/topics/time-series.md>)

Tags: [computer-science](<https://devfeed.tech/tags/computer-science.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [effects](<https://devfeed.tech/tags/effects.md>), [forecast](<https://devfeed.tech/tags/forecast.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [foundation-model](<https://devfeed.tech/tags/foundation-model.md>), [foundation-models](<https://devfeed.tech/tags/foundation-models.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [retail](<https://devfeed.tech/tags/retail.md>), [sales](<https://devfeed.tech/tags/sales.md>), [temporal](<https://devfeed.tech/tags/temporal.md>), [time-series](<https://devfeed.tech/tags/time-series.md>), [time-series-foundation-models](<https://devfeed.tech/tags/time-series-foundation-models.md>), [variables](<https://devfeed.tech/tags/variables.md>)

## AI overview

Accurate sales forecasts do not establish that a model can predict how sales respond to a price change. The study reports this mismatch for released tabular and time-series foundation models and a model pretrained for causal-effect estimation, using simulated data with known effects and real retail sales records. For tabular models, added context improves forecasts but not predicted price effects. Instrumental variables reduce effect-prediction error only when provided in a specific form; under confounding, raw instruments increase error for every evaluated model.

## Source excerpt

arXiv:2611.15009v1 Announce Type: new Abstract: A model that forecasts sales accurately can still mislead a retailer about how sales respond to a price change. We evaluate released tabular and time-series foundation models, as well as a foundation model pretrained specifically to estimate causal effects. We report three findings. First, forecast accuracy does not indicate the accuracy of the predicted effect of price, both on simulated data in which the true effect is known and on real retail sales records. Second, for the tabular foundation models, additional context improves forecasts but not the predicted effect of price. Third, instrumental variables, the standard remedy in econometrics, reduce this error only when supplied in a specific form and increase it for every model under confounding when supplied as raw instruments.