fix(g05): match released checkpoint oracle

docs/source/g05.mdx

@@ -100,11 +100,29 @@ lerobot-rollout \
 CPU unit tests cover factory loading, config incompatibilities, prompt pass-through,
 LIBERO and `atomic_4` mappings, padding masks, inverse action projection, strict
 conversion diagnostics, a finite forward/backward/update, and save/reload parity.
-Numerical author-oracle parity and 50-episode LIBERO/RoboTwin evaluation require
-licensed checkpoint access and suitable CUDA hardware; no benchmark number is
-claimed by this integration until those gates run.
+The opt-in author-oracle gate compares the exact prompt tokens, every image/state/action
+tensor and mask, seeded flow loss and samples, and de-normalized environment actions
+for batch sizes one and two:
 
 ```bash
 uv run pytest tests/policies/g05 tests/runtime/test_g05_adapter.py -q
 uv run ruff check src/lerobot/policies/g05 tests/policies/g05
+
+PYTHONPATH=/path/to/GalaxeaVLA/src uv run python benchmarks/g05_checkpoint_parity.py \
+  --author-source /path/to/GalaxeaVLA \
+  --checkpoint outputs/g05-libero-lerobot \
+  --batch-size 1 \
+  --compare-training-loss \
+  --output outputs/g05-libero-parity-b1.json
+
+PYTHONPATH=/path/to/GalaxeaVLA/src uv run python benchmarks/g05_checkpoint_parity.py \
+  --author-source /path/to/GalaxeaVLA \
+  --checkpoint outputs/g05-libero-lerobot \
+  --batch-size 2 \
+  --output outputs/g05-libero-parity-b2.json
 ```
+
+This command still requires licensed checkpoint access and suitable CUDA hardware.
+A 50-episode LIBERO/RoboTwin success-rate comparison additionally requires the
+matching simulator, task assets, reset seeds, and author evaluator; no task-level
+benchmark number is claimed until that separate gate runs.