Skip to content

Constraint Learnability Public Release v1.0.2

Latest

Choose a tag to compare

@crabsatellite crabsatellite released this 30 Jun 11:37
· 2 commits to master since this release

Patch release for the FDG 2026 constraint-learnability artifact.

Changes since v1.0.1:

  • Fix structural-feature extraction to validate manifest-referenced processed files instead of a nonexistent data/processed/builds directory.
  • Make scripts/generate.py use the learned any-mask structural prefix when loading a conditioned checkpoint for unconditioned generation.
  • Allow scripts/train_ar_conditioned.py to run from existing latent/features files when checkpoints/vqvae/config.json is unavailable, using --num_codes or the paper default of 2048.

Checkpoint assets are unchanged from v1.0.1 and are reattached here for convenience:

  • vqvae_step100000.pt SHA256 c9caf9e76a1f1ef8512897cd2aafaa6099d4aa1e7a514cb5203707028e77e019
  • ar_cond_step80000.pt SHA256 919b0c1190f940c98cdcd0c58e52c86b3c66702ae8d35b3b7926b2fb8aaec1e7

This release does not change the paper PDF, archived output JSON files, figures, or checkpoint contents.