A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
verdicts
UNVERDICTED 6representative citing papers
Simulations of Milky Way-mass galaxies reveal direction-dependent dynamical heating during stellar radial migration, with inward migrators heating, some cooling, and cold preservation uncommon especially for older stars.
Reprojects abundances of 199k stars into 4 patterns, identifying enrichment pathways with strong chemo-spatial, age, and vertical correlations plus a transition at ~6 Gyr.
New high-resolution spectra yield abundances for 7 neutron-capture elements in open cluster stars, revealing flat Milky Way gradients for second-peak s- and r-process species and shallower slopes for first-peak s-process.
Simulations show that observed rotation in 13.5-Gyr-old alpha-rich stars constrains the Gaia-Sausage-Enceladus merger to mass ratios below 1:4, with interaction and starburst times both near 11 Gyr.
Ages inferred for red giant stars via machine learning are generally insensitive to hyperparameters and architecture but somewhat sensitive to training set choice, especially for the oldest, coolest, and lowest-metallicity stars.
citing papers explorer
-
Homogeneous Stellar Parameters from Heterogeneous Spectra with Deep Learning
A single end-to-end Transformer model unifies stellar labels from heterogeneous spectroscopic surveys into a self-consistent scale without post-hoc recalibration.