Standard Reconstruction Shifts the Optimal Input Scale for CNN-Based Density-Field Reconstruction

We investigate convolutional neural network (CNN) methods for reconstructing the high-redshift density field from late-time large-scale structure, focusing on how the physical scale of the CNN input changes when standard first-order reconstruction is applied beforehand. Using dark-matter-only $N$-body simulations, we compare three approaches: a single-input CNN, a dual-input CNN combining two physical scales, and a single-input CNN applied to the density field after standard reconstruction. We vary the physical side length of the input sub-box over $L_\mathrm{sub}\sim38$-$380~h^{-1}\mathrm{Mpc}$ while keeping its numerical size fixed at $39^3$ voxels, allowing us to examine the trade-off between spatial context and resolution. For the CNN applied directly to the evolved density field, the reconstruction performs best at $L_\mathrm{sub}\sim150$-$200~h^{-1}\mathrm{Mpc}$. After standard reconstruction, however, the preferred scale shifts to $L_\mathrm{sub}\sim38$-$114~h^{-1}\mathrm{Mpc}$. The single-input CNN after standard reconstruction consistently outperforms both the single- and dual-input CNNs without standard reconstruction according to the normalized loss, density probability distribution, Kullback-Leibler divergence, residual field, and Fourier-space correlation. These results indicate that coherent large-scale displacements are more efficiently recovered by perturbative reconstruction, while the CNN is better suited to modelling the remaining quasi-linear and non-linear evolution on smaller scales. The preferred post-reconstruction input range includes the effective receptive scale of approximately $60~h^{-1}\mathrm{Mpc}$ adopted in previous hybrid reconstruction studies. Our findings therefore support a physically motivated separation of scales between analytic and data-driven reconstruction and demonstrate the advantage of combining the two approaches.