A Generalist Model Including Evolved Star Mass and Age

TL;DR

This paper presents a transformer-based foundation model that accurately predicts stellar parameters, including mass and age, from Gaia XP spectra, enabling large-scale Galactic archaeology with physical consistency and uncertainty estimation.

Contribution

It extends a foundation model to evolved stars, integrating mass and age prediction into a unified, physically consistent framework using spectral token sequences.

Findings

Achieves mass prediction scatter of ~0.114 solar masses.

Achieves age prediction scatter of ~1.334 Gyr.

Successfully disentangles extinction from temperature without explicit priors.

Abstract

Determining precise stellar ages and masses for evolved giants is crucial for Galactic archaeology but challenged by spectral degeneracies. Gaia's low-resolution XP spectra offer a unique opportunity to infer these parameters on a massive scale using data-driven methods. We extend a transformer-based astronomical foundation model to evolved stars, establishing a unified framework to simultaneously predict atmospheric parameters ($T_{\mathrm{eff}}$, $\log g$, $[\mathrm{M}/\mathrm{H}]$) and evolutionary labels (mass, age) with physical consistency. Treating spectra as token sequences, we integrated mass and age into the model's vocabulary. The model is trained on Gaia XP spectra cross-matched with the APOGEE DR17 DistMass catalog. Our generative approach enables flexible input handling, including spectral inpainting and parameter-to-spectrum generation. On an independent test set, the model achieves a prediction scatter of $\sigma \approx 0.114 \, M_{\odot}$ for mass and $\sigma \approx 1.334$ Gyr for age. Beyond numerical accuracy, it successfully reproduces the giant branch's mass-luminosity relation and autonomously disentangles interstellar extinction from intrinsic temperature variations without explicit physical priors. It also robustly recovers missing spectral data and estimates reliable uncertainties. Validating that foundation models can internalize stellar physics from data, this physically-aware, probabilistic framework offers a powerful tool for unraveling Milky Way history using large-scale spectroscopic surveys.