Crystalite checkpoint trained for 10K steps on the full Alex-MP-20 dataset (540K structures, 97.9% metals). This is the diversity-optimized model used for the Pareto sweep experiments.

Architecture: 67.8M-parameter Diffusion Transformer with subatomic tokenizer and GEM attention bias (Crystalite, Hadzi Veljkovic et al.).

Every guidance weight Pareto-dominates the baseline. 18,432 structures across 6 weights, 3 seeds, 1,024 per batch. No mode collapse.

Band gap probe AUROC: 0.957 (256 parameters, trained on atom-mean hidden states).

Requires the Crystalite codebase and probe-gradient-guidance scripts.

This checkpoint was used as an upstream generation asset in the open-world environment pipeline for Training Scientific Judgment with Verified Environments for Autonomous Science.