ROSE (Red-giant Oscillations Spectra Estimator): A Modular Machine-Learning Framework for Automated Asteroseismic Characterisation. I. $ν_{\max}$ and $Δν$ from TESS
Space-based photometry from Kepler and TESS has delivered oscillation spectra for hundreds of thousands of red giants, and PLATO and the Roman Galactic Bulge Time-Domain Survey will add more. We present ROSE, a modular machine-learning framework for automated asteroseismic characterisation of red giants, and apply two of its modules to the frequency of maximum oscillation power, $ν_{\rm max}$, and the large frequency separation, $Δν$. Each module is a neural network bundled with its own preprocessing transform and output binning, so that each parameter is measured in the representation that displays it most effectively: $ν_{\rm max}$ from the power-density spectrum, and $Δν$ from the power spectrum of the power spectrum taken over a window centred on $ν_{\rm max}$. Both are trained only on synthetic spectra generated at a one-year baseline and both return probability distributions rather than point estimates. This enables us to retrieve asymmetric uncertainty and a reliability index. Validating against held-out synthetic spectra, Kepler spectra at the training resolution and TESS continuous-viewing-zone giants, we obtain robust dispersions of 1.4, 3.3 and 4.4% in $ν_{\rm max}$ and 0.35, 0.61 and 1.3% in $Δν$, with the $ν_{\rm max}$ uncertainties close to their nominal coverage. The fully automated pipeline was applied to 274,721 TESS red-giant candidates observed for at least ten sectors, the framework returning reliable $ν_{\rm max}$ for 56,224 stars and reliable $Δν$ for 39,939, taking 8 ms per star. The sample follows $Δν= 0.278 ν_{\rm max}^{0.757}$ with a scatter of 6.2%, and the red-clump phase stands out as a distinct overdensity, although neither module is provided an evolutionary label or asked to produce one.