coreai-fabric: act-aloha-cube card + license + reports

README.md

@@ -0,0 +1,129 @@
+---
+license: apache-2.0
+base_model: lerobot/act_aloha_sim_transfer_cube_human
+pipeline_tag: robotics
+library_name: coreai
+tags:
+- coreai
+- core-ai
+- coreai-fabric
+- aimodel
+- coreml
+- apple
+- apple-silicon
+- on-device
+- robotics
+- vla
+- vision-language-action
+- action
+---
+
+> **Canonical:** [`kevinqz/ACT-Aloha-TransferCube-CoreAI`](https://huggingface.co/kevinqz/ACT-Aloha-TransferCube-CoreAI) — source of truth. 
+
+# ACT ALOHA Transfer-Cube (fabric)
+
+> ⚠️ **Robot policy — needs a matching robot to actuate.** This is
+> [lerobot/act_aloha_sim_transfer_cube_human](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human) converted to an
+> Apple Core AI `.aimodel`. Its output is a **normalized action chunk** for
+> **aloha_bimanual_14dof_sim**. Run it on any other robot, or with mismatched calibration /
+> normalization stats, and it emits floats that *look* valid but **actuate
+> garbage** — the most dangerous silent-failure mode. It is a **base checkpoint**:
+> fine-tune on your robot's data before expecting useful behavior.
+
+An Apple Core AI conversion of
+[lerobot/act_aloha_sim_transfer_cube_human](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human) — a **robot policy**
+that maps images + proprioceptive state (+ a language instruction, when the model
+uses one) to a continuous action chunk (act sampler). Produced by
+[coreai-fabric](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/act-aloha-cube.yaml) and indexed by
+[coreai-catalog](https://github.com/kevinqz/coreai-catalog).
+
+## Model facts
+
+| Field | Value |
+|---|---|
+| Parameters | 51.6M |
+| Architecture | transformer |
+| Capabilities | robotics |
+| Embodiment | aloha_bimanual_14dof_sim |
+| Sampling | act |
+| Quantization / precision | none / float16 |
+| On-disk size | 131 MB |
+| Asset kind | single-graph policy + norm_stats sidecar |
+| assetVersion | 2.0 |
+
+
+## Use it — this needs host code you supply
+
+A policy is **not** a chat model: there is no stock high-level Swift runtime for
+it. The bundle is the split-export shape — an `encode` graph (run once per
+observation) + a `denoise_step` graph (the host drives it `num_steps` times) +
+`norm_stats.json` (un-normalization). **You supply the host loop** (the N-step
+sampler + un-normalization) in Swift. Recommended integration: keep LeRobot's
+Python `RobotClient` for the servos/cameras/calibration, and run inference
+on-device — see the `io_contract` in the catalog for the exact tensors.
+
+```bash
+pip install coreai-catalog && coreai-catalog install act-aloha-cube
+```
+
+## Requirements
+
+- **Deployment: macOS 27.0+ / iOS 27.0+, Xcode 27+.** The asset serializes with `minimum_os v27`,
+  so the on-device Swift runtime requires macOS/iOS 27+. A Mac on macOS 26 can
+  convert and inspect it but not run it on-device.
+- Apple Silicon. A matching robot to actuate (see the banner).
+
+## Verification (action parity)
+
+- **Gate A (structure): passed** — the bundle's layout + metadata were
+  validated on real hardware; the graphs load.
+- **Gate B — action_parity: 100.0% min chunk-cosine · 0.0 max normalized MAE** vs the fp16 reference over 8 frames of `8 fixed-seed observations (deterministic ACT: the export is exact regardless of input; realistic-episode eval is future work)`, 1-step, fixed-noise (measured on Apple M4 Max).
+- This certifies the export is **numerically faithful to the source policy** — it
+  does **NOT** certify real-world task success, embodiment transfer, or
+  closed-loop stability. Closed-loop success-rate eval (LIBERO/ManiSkill):
+  **not_run** (a separate future gate). Reproduce with `coreai-fabric verify`.
+
+## Provenance
+
+| Field | Value |
+|---|---|
+| Base model | [lerobot/act_aloha_sim_transfer_cube_human](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human) @ `ba73b2766f1371cdc133ca4efb97eb090d744625` |
+| Converted by | `models/act/export.py` (version not reported) |
+| Recipe | [act-aloha-cube](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/act-aloha-cube.yaml) (recipe_source: fabric) |
+| Precision / quantization | float16 / none |
+| Conversion date | 2026-07-04 |
+
+Machine-readable, in this repo:
+[`parity-report.json`](./parity-report.json) (gate results) ·
+[`reproduce-manifest.json`](./reproduce-manifest.json) · [`LICENSE`](./LICENSE)
+(upstream terms).
+
+## License and attribution
+
+Weights licensed **apache-2.0** — see the bundled `LICENSE`. This artifact is a **converted derivative** of the base policy: its
+weights were converted to Apple Core AI format. The conversion itself is
+community work.
+
+## Links
+
+- **Base model:** [lerobot/act_aloha_sim_transfer_cube_human](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human)
+- **Reproduce:** [recipe `act-aloha-cube`](https://github.com/kevinqz/coreai-fabric/blob/main/recipes/act-aloha-cube.yaml)
+- **Index:** [coreai-catalog](https://github.com/kevinqz/coreai-catalog) — the
+  neutral registry tying upstream ↔ this asset ↔ mirror together
+
+
+## The on-device Core AI ecosystem
+
+- [coreai-fabric](https://github.com/kevinqz/coreai-fabric) — the reproducible
+  recipe → `.aimodel` pipeline that produced this asset.
+- [coreai-catalog](https://github.com/kevinqz/coreai-catalog) — the index of Core
+  AI models across the community, with provenance and integration snippets.
+- [apple/coreai-models](https://github.com/apple/coreai-models) — Apple's official
+  exporters and runtimes.
+- [LeRobot](https://huggingface.co/lerobot) — the upstream robotics ecosystem.
+
+## Not affiliated with Apple
+
+Community conversion. Not produced, hosted, or endorsed by Apple. Apple and Core
+AI are trademarks of Apple Inc., used here only to describe the target
+runtime/format. This is an independent community conversion.

parity-report.json

@@ -0,0 +1,39 @@
+{
+  "gate_a": {
+    "status": "passed",
+    "checks": [
+      "bundle_files_present",
+      "metadata_json_parses",
+      "asset_loads_and_runs"
+    ]
+  },
+  "gate_b": {
+    "metric": "action_parity",
+    "status": "passed",
+    "value": 1.0,
+    "min_action_cosine": 1.0,
+    "mean_action_cosine": 1.0,
+    "mean_cosine_ci95": [
+      1.0,
+      1.0
+    ],
+    "max_normalized_mae": 0.0,
+    "mean_normalized_mae": 0.0,
+    "first_action_mae": 0.0,
+    "num_steps": 1,
+    "reference_dtype": "float16",
+    "n_obs": 8,
+    "chunk_len": 100,
+    "dataset": "8 fixed-seed observations (deterministic ACT: the export is exact regardless of input; realistic-episode eval is future work)",
+    "noise_seed": 0,
+    "greedy_token_exact": false,
+    "runner": "coreai-fabric-parity-runner/0.1.0 (act direct, deterministic)",
+    "environment": {
+      "chip": "Apple M4 Max",
+      "os": "macOS 26.6",
+      "coreai_torch": "0.4.1",
+      "torch": "2.9.0",
+      "lerobot": "0.5.1"
+    }
+  }
+}