8 inputs → 58 body params: putting a body-model forward pass inside the training loss [P]

Small MLP (2 layers × 256 units, ~85 KB) that accurately predicts 58 Anny body-shape parameters from 8 questionnaire inputs: height, weight, gender, body shape, build, belly, cup size, ancestry. Trains in ~120 minutes on a laptop. Architecturally boring — the loss is the interesting part. Results (female / male, held-out synthetic test set): Female Male Height MAE (mean / p95) 0.3 / 0.8 cm 0.3 / 0.8 cm Mass MAE (mean / p95) 0.4 / 1.0 kg 0.5 / 1.2 kg Bust / Waist / Hips MAE (mean