Shear estimation results for galaxies with m_i < 25.3 under variations in image noise level (top row), PSF ellipticity (middle row), and PSF FWHM (bottom row). The left panels show the multiplicative bias m₁ (blue) and m₂ (red), while the right panels show the additive bias c₁ (blue) and c₂ (red). The data points are horizontally slightly shifted from the original value to avoid overlap. The points indicate the mean bias estimates, with error bars corresponding to 1σ (deep color) and 3σ (light color) statistical uncertainties, with bootstrap resampling 20 times. The shaded gray region in the multiplicative-bias panels denotes the LSST requirement of ∣m∣ < 0.002. Across all tested observing conditions, both multiplicative and additive biases remain consistent with zero within the errors, demonstrating the accuracy of the calibrated ML-based shear estimator.