card: document ARC-MIX 9.42B corpus (32M/64M runs) + v2 FineWeb-Edu-dominant blend plan

card: confirmed board entry (#16 32M / #21 16M, maintainer-verified); all models + results; ARC lever = value residuals (competitive intel); 64M A/B roadmap

card: Positioning CONFIRMED on board #16/#21 + Roadmap VR-ARC-lever/data-stack/64M-A/B

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub

Usage: reference in-repo train_gpt_ref.py and glint_parity_eval.py

Polished professional card: model-details, usage, evaluation-protocol, key-findings, roadmap, limitations

Add Usage section (merge best-of-both cards)

Proper English model card: Glint-protocol metrics, honest positioning, corrected corpus/positions

Upload README.md with huggingface_hub

Upload README.md with huggingface_hub