docs: final GPU readout in README + model card; add POM relation section

docs: tidy README + TODO — accurate quick-start, paper package, green tests, READY gate

docs: triplet expansion 8->20 + GPU A/B run in README and TODO

docs: open design decisions + training-readiness gate in README

pimt v9 substantivity gbm train publish path

Add Fraterworks ingestion and upload data split support

docs(readme): recommend t4-medium (30 GB RAM) to avoid OOM on full dataset

build: lower Python requirement to >=3.10 for official PyTorch image compatibility

docs(readme): add HF Hub card metadata and MIT LICENSE

docs(readme): overhaul public README for HF source repo

feat: add Milestone 5 generative inverse-design composer (CMA-ES)

feat: Milestone 4 clean code snapshot