Document architecture/model/task checkpoint layout

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+tags:
+- robotics
+- vision-language-action
+- rsci
+---
+
+# RSCI checkpoints
+
+Full 40,000-step training checkpoints for Rethinking State Conditioning in Vision-Language-Action Models.
+
+## Layout
+
+`newcheckpoint/<architecture>/<model>/<task>/<vlm-mode>/<run>/`
+
+- Architecture: `Psi0`.
+- Models: `VGQ-AE`, `(VGQ-AE-D)`; further variants retain their own names.
+- Tasks: `betweentables`, `hug`, `oven`, `faucet`, `xmovepick`, `handover`.
+- VLM mode: `frozen` or `lora`.
+
+Each published run includes `checkpoints/ckpt_40000/` with model weights, optimizer, scheduler and all distributed-rank random states, plus training configuration, launch contract and a SHA256 manifest. Runs and tasks are kept separate. Earlier intermediate checkpoints, training datasets and evaluation videos are not included.
+
+The accompanying configurations identify the actual model, data and source version. Checkpoint publication does not assert an evaluation success rate. See each run's manifest for provenance and exact file hashes.