Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Berthelier, Gaspard, Baranova, Mariia, Pantea, Andrei-Tiberiu, Naour, Etienne Le, Petralia, Adrien, Nabil, Tahar, Palpanas, Themis
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2605.12200
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914559540854784
author Berthelier, Gaspard
Baranova, Mariia
Pantea, Andrei-Tiberiu
Naour, Etienne Le
Petralia, Adrien
Nabil, Tahar
Palpanas, Themis
author_facet Berthelier, Gaspard
Baranova, Mariia
Pantea, Andrei-Tiberiu
Naour, Etienne Le
Petralia, Adrien
Nabil, Tahar
Palpanas, Themis
contents Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings. Recent TSFM architectures, such as Chronos-2 and TabPFN-TS, aim to integrate covariates. In this paper, we design controlled experiments based on simple target-covariate relationships to assess this integration capability. Our results show that TabPFN-TS captures these relationships more effectively than Chronos-2, especially for short horizons, suggesting that the strong benchmark performance of Chronos-2 does not automatically translate into optimal modeling of simple covariate-target dependencies.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12200
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
Berthelier, Gaspard
Baranova, Mariia
Pantea, Andrei-Tiberiu
Naour, Etienne Le
Petralia, Adrien
Nabil, Tahar
Palpanas, Themis
Machine Learning
Time Series Foundation Models (TSFMs) have recently achieved state-of-the-art performance, often outperforming supervised models in zero-shot settings. Recent TSFM architectures, such as Chronos-2 and TabPFN-TS, aim to integrate covariates. In this paper, we design controlled experiments based on simple target-covariate relationships to assess this integration capability. Our results show that TabPFN-TS captures these relationships more effectively than Chronos-2, especially for short horizons, suggesting that the strong benchmark performance of Chronos-2 does not automatically translate into optimal modeling of simple covariate-target dependencies.
title Investigating simple target-covariate relationships for Chronos-2 and TabPFN-TS
topic Machine Learning
url https://arxiv.org/abs/2605.12200