Initialize ai_rfm documentation and cu126 uv scaffolding.

Set up project policy files, baseline best-practice tracking, and a pre-commit performance gate so future train.py commits require measured RMSD improvement.

Made-with: Cursor

README.md

@@ -0,0 +1,38 @@
+# ai_rfm
+
+RFM overfitting sandbox for a single ligand sample, with hard quality gates.
+
+## Environment first (UV, cu126 only)
+
+1. Ensure Python 3.12 is available.
+2. Install env and deps:
+   - `uv sync`
+3. Install git hooks:
+   - `uv run pre-commit install`
+
+This repository is intentionally pinned to CUDA 12.6 PyTorch wheels and matching PyG wheels.
+
+## Repository policy
+
+- Every attempt must update this README (append a short entry in `## Attempt Log`).
+- Commits touching `train.py` must include:
+  - `reports/latest_eval.json`
+  - `BEST_PRACTICE.json`
+  - better or equal `mean_rmsd_100` compared to previous best (enforced by pre-commit).
+
+## Evaluation target
+
+- Metric: mean RMSD over 100 runs (`batchsize=100` style aggregated evaluation).
+- Success criterion: `mean_rmsd_100 <= 1.0`.
+
+## Key files
+
+- `train.py`: training/evaluation entry point.
+- `GUIDELINES.md`: operating rules and workflow.
+- `BEST_PRACTICE.json`: current best-known metric and config.
+- `reports/latest_eval.json`: most recent measured metric.
+- `scripts/precommit_performance_gate.py`: pre-commit guard for train-related commits.
+
+## Attempt Log
+
+- 2026-04-16: Bootstrapped docs/environment policy and cu126 UV config. Added best-practice/performance gating scaffolding before the next training run.