# OpenVLA: Bridge V2 WidowX policy evaluation

Pinned OpenVLA real-robot evaluation entrypoint using the separately configured Bridge V2 WidowX environment/controller service. Statically reviewed source only; not run and no Hub preparation adapter.

ID: `openvla-experiments-robot-bridge-run-bridgev2-eval-py`

Record version: `source-ee1a2acb0dd1d0d4a71cff4d29d4287c5e7542b6b5b37cd234243bb1fab0c2d3`

Hub commit: `66a13cd6ae8ab828219a4916587fb83d6dc71809`

## Access

Fetch the pinned repository, verify this source checksum, and use upstream installation and invocation. This record does not install or execute code.

Optional inert file retrieval: `python /PATH_TO_SKILL/scripts/rsh.py fetch-source openvla-experiments-robot-bridge-run-bridgev2-eval-py --expected-source-revision c8f03f48af692657d3060c19588038c7220e9af9 --expected-source-sha256 ee1a2acb0dd1d0d4a71cff4d29d4287c5e7542b6b5b37cd234243bb1fab0c2d3 --project ./experiment --json`. This verifies one file, preserves provenance and never installs or runs it. See [source-file retrieval](https://hub.superfastrobotics.com/source-files.md).

Hub preparation adapter: **false**. Runtime verification: **not_run**.

Upstream setup: https://github.com/openvla/openvla/blob/c8f03f48af692657d3060c19588038c7220e9af9/README.md

## Source and license

- Repository: https://github.com/openvla/openvla
- Pinned source: https://github.com/openvla/openvla/blob/c8f03f48af692657d3060c19588038c7220e9af9/experiments/robot/bridge/run_bridgev2_eval.py
- Revision: `c8f03f48af692657d3060c19588038c7220e9af9`
- Path: `experiments/robot/bridge/run_bridgev2_eval.py`
- Source SHA256: `ee1a2acb0dd1d0d4a71cff4d29d4287c5e7542b6b5b37cd234243bb1fab0c2d3`
- Source bytes: 6985
- Original authors: Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti
- License: [MIT](https://github.com/openvla/openvla/blob/c8f03f48af692657d3060c19588038c7220e9af9/LICENSE)
- License scope: Selected first-party Python workflow source only. Preserve upstream copyright and per-file notices. Model weights, datasets, third-party code, robot drivers/firmware and services retain separate terms; no rights for those assets are inferred.

License SHA256: `c4ee2ba5958af03d74b1d3dfa174e3749171d689fb4c23cc170749c05ae3eeb5`

## Artifact

```json
{
  "kind": "workflow",
  "format": "python",
  "workflow_role": "policy-evaluation"
}
```

## Requirements

```json
{
  "python": ">=3.8 in metadata; README installation uses Python 3.10; controller environment remains separate.",
  "packages": [
    "Pinned OpenVLA checkout",
    "Upstream PyTorch 2.2.0, transformers 4.40.1, timm 0.9.10 and tokenizers 0.19.1 pins",
    "Workflow-specific dependencies in pinned README and source"
  ],
  "display": "Hardware: README requires the BridgeData V2 WidowX setup, bridge_data_robot/widowx_envs, edgeml and the upstream Docker robot server. Compatible compute/controller and calibration are source-defined; no universal robot support is inferred. Weights: Requires a selected pretrained OpenVLA checkpoint; README demonstrates openvla/openvla-7b. Datasets: Consumes live robot observations; optional rollout-data/video output is separate from training data. Services/auth: Uses the separately running WidowX controller server with configured host/port. No named provider API key is declared by this entrypoint.",
  "execution_domain": "hardware",
  "source_imports": [
    "dataclasses",
    "draccus",
    "experiments.robot.bridge.bridgev2_utils",
    "experiments.robot.openvla_utils",
    "experiments.robot.robot_utils",
    "pathlib",
    "sys",
    "time",
    "typing"
  ],
  "notes": "This workflow can send real robot actions if an operator executes it; the Hub candidate does not execute, authorize or prepare it. Code licensing does not establish model, checkpoint, dataset or service permission.",
  "declared_requirements": {
    "python": ">=3.8 in metadata; README installation uses Python 3.10; controller environment remains separate.",
    "weights": "Requires a selected pretrained OpenVLA checkpoint; README demonstrates openvla/openvla-7b.",
    "datasets": "Consumes live robot observations; optional rollout-data/video output is separate from training data.",
    "hardware": "README requires the BridgeData V2 WidowX setup, bridge_data_robot/widowx_envs, edgeml and the upstream Docker robot server. Compatible compute/controller and calibration are source-defined; no universal robot support is inferred.",
    "external_services_and_auth": "Uses the separately running WidowX controller server with configured host/port. No named provider API key is declared by this entrypoint.",
    "evidence": [
      {
        "anchor": "def eval_model_in_bridge_env",
        "line": 82
      },
      {
        "anchor": "get_widowx_env",
        "line": 24
      },
      {
        "anchor": "env.step(action)",
        "line": 160
      }
    ],
    "license_scopes": {
      "code": "MIT for selected first-party workflow source.",
      "weights": "README explicitly says the released OpenVLA models derive from Llama-2 and are subject to the Llama Community License. No checkpoint/model card/base-model license was fetched or evaluated here; MIT is asserted only for the selected first-party Python source.",
      "datasets": "README names BridgeData V2, Open X-Embodiment and LIBERO datasets. Individual dataset terms were not reviewed, and repository MIT is not applied to them.",
      "third_party_code": "External dependencies retain their own licenses."
    },
    "interpretation": "Pinned upstream declarations only; no dependency resolution, model/data access, compatibility inference or runtime validation was performed."
  }
}
```

## Invocation

```json
{
  "entrypoint": "python experiments/robot/bridge/run_bridgev2_eval.py --model_family openvla --pretrained_checkpoint <approved-checkpoint>",
  "notes": "This workflow can send real robot actions if an operator executes it; the Hub candidate does not execute, authorize or prepare it."
}
```

## Compatibility

```json
[]
```

Missing environment fields remain unknown. Source discovery labels do not establish robot compatibility.

## Evidence

Level: **source_reviewed**. Runtime verification: **not_run**.

Verified exact source, applicable license and author/setup document bytes at a full Git commit; parsed the Python AST and reviewed this guarded operational entrypoint and its explicit license notices. No upstream code, installation, robot command, dataset, mesh or checkpoint was executed or loaded.

Source review and contributor reports do not establish task completion. Preserve upstream attribution and licenses.