docs: remove AI-writing tells from model card (style-only; frontmatter untouched)

README.md

@@ -31,7 +31,7 @@ model-index:
             value: 0.00206
 ---
 
-# π0.5 — YAM bimanual fine-tune on MolmoAct2 data
+# π0.5: YAM bimanual fine-tune on MolmoAct2 data
 
 [![Evaluate with Inspect Robots](https://img.shields.io/badge/evaluate%20with-Inspect%20Robots-indigo)](https://github.com/robocurve/inspect-robots)
 [![Adapters: YAM](https://img.shields.io/badge/adapters-inspect--robots--yam-blue)](https://github.com/robocurve/inspect-robots-yam)
@@ -51,38 +51,38 @@ fine-tune on the same data; full recipe at
 - **Intended use:** research and evaluation on I2RT YAM bimanual arms (2× 6-dof arms +
   grippers, three cameras) for the trained task families: block manipulation, box packing,
   cable charging.
-- **Out of scope:** any other embodiment or rig without fine-tuning — VLA policies do not
-  zero-shot transfer across embodiments; unattended operation; operation near people without
+- **Out of scope:** any other embodiment or rig without fine-tuning (VLA policies do not
+  zero-shot transfer across embodiments); unattended operation; operation near people without
   a hardware e-stop and enforced workspace/torque limits.
 - **Validation status:** open-loop MSE on one held-out recording session (see Losses &
-  evaluation) — no closed-loop sim or real-robot success rates reported. Users are
+  evaluation). No closed-loop sim or real-robot success rates reported. Users are
   responsible for safe integration (guardrails, e-stop, workspace limits) before deployment.
 
 ## Training
 
 | | |
 |---|---|
-| Data | 124 train repos / 5,145 episodes / 11.35M frames — no filtering (full dataset release); held-out val: the separate repo [`allenai/19012026-block-13`](https://huggingface.co/datasets/allenai/19012026-block-13) (session-level holdout) |
-| Embodiment | YAM bimanual: 14-dof state/action — 2× (6 joints + gripper), absolute joint positions; cameras top + left/right wrists, 360×640 |
+| Data | 124 train repos / 5,145 episodes / 11.35M frames; no filtering (full dataset release); held-out val: the separate repo [`allenai/19012026-block-13`](https://huggingface.co/datasets/allenai/19012026-block-13) (session-level holdout) |
+| Embodiment | YAM bimanual: 14-dof state/action, 2× (6 joints + gripper), absolute joint positions; cameras top + left/right wrists, 360×640 |
 | Image preprocessing | openpi `yam_pi05` config defaults (see training repo); per-repo loading with 5 ms decode tolerance |
 | Schedule | 20,000 steps @ batch 512, cosine LR (peak 2.5e-5, warmup 1k), EMA 0.99, 8× B200 (FSDP), ~17.5 h on Modal |
-| Checkpoint selection | best held-out val over milestone checkpoints every 1,000 steps → **step 10,000** |
-| Headline curve | open-loop val MSE at selection: **0.00206** (reference release on the same protocol: 0.00259 released / 0.00204 best) |
+| Checkpoint selection | best held-out val over milestone checkpoints every 1,000 steps → step 10,000 |
+| Headline curve | open-loop val MSE at selection: 0.00206 (reference release on the same protocol: 0.00259 released / 0.00204 best) |
 
 ## Losses & evaluation
 
 - **Training loss:** π0.5's flow-matching action objective (action expert predicts the
   velocity field for noised 16-step action chunks conditioned on VLM features + state).
-  Full fine-tune — nothing frozen; EMA 0.99 weights are the published ones.
-- **Eval regime: open-loop MSE** — predicted vs ground-truth actions over 16-step chunks on
+  Full fine-tune (nothing frozen); EMA 0.99 weights are the published ones.
+- **Eval regime:** open-loop MSE, predicted vs ground-truth actions over 16-step chunks on
   the held-out session repo, n=20 trajectories, quantile-normalized action space; protocol
   and script in the [training repo](https://github.com/robocurve/pi05-yam-replication)
   (`eval_mse.py`). Normalization parity: quantile (q01/q99) stats vendored from the
   reference release and used identically at train and eval time.
 - **Comparison:** the reference fine-tune's released checkpoint scores 0.00259 (best 0.00204)
   on this same protocol; see the training repo for the reference details.
-- **Scope:** open-loop MSE on a single near-distribution session — an action-prediction
-  proxy, not a closed-loop success rate or task-generalization benchmark.
+- **Scope:** open-loop MSE on a single near-distribution session (an action-prediction
+  proxy), not a closed-loop success rate or task-generalization benchmark.
 
 ## Provenance
 
@@ -101,8 +101,8 @@ fine-tune on the same data; full recipe at
 ## Format
 
 Orbax checkpoint (JAX):
-- `params/` — Orbax PyTree of model parameters (EMA weights, ~12 GB)
-- `assets/yam-bimanual-merged/norm_stats.json` — normalization stats used at train time
+- `params/`: Orbax PyTree of model parameters (EMA weights, ~12 GB)
+- `assets/yam-bimanual-merged/norm_stats.json`: normalization stats used at train time
 
 ## Usage
 
@@ -133,9 +133,9 @@ action_chunk = policy.infer({
 - All source repos are public AllenAI LeRobot v3 datasets (Apache-2.0); the fine-tune
   inherits Gemma terms via the PaliGemma backbone (see frontmatter license).
 - The videos carry small timestamp jitter and occasional frame deficits vs their metadata;
-  training used a 5 ms decode tolerance and per-repo loading (no physical merge — see the
+  training used a 5 ms decode tolerance and per-repo loading (no physical merge; see the
   training repo README for why merged videos drift).
-- Val split is a single held-out recording session of the block task — a near-distribution
+- Val split is a single held-out recording session of the block task: a near-distribution
   check, not a task-generalization benchmark. No closed-loop or real-robot results.
 
 ## Versioning & contact