Decision summary
VLA training
Training data requirements are not structured enough for reliable dataset matching.
Run a checkpoint loading smoke test before marking the model pipeline-tested.
Evidence profile
A visual read of adoption evidence. Scores describe catalog evidence readiness, not task performance.
Published evaluation
4/6
dimensions scored
Unknown evidence remains visible and is never treated as a zero.
Why these scores
The strongest decision reasons behind the evidence profile.
Artifact availability
UsefulCheckpoint files were verified in the official repository metadata.
Training and loading reproducibility
UsefulConfiguration files are present; runtime loading is not tested.
Evaluation evidence
UnknownNo structured evaluation evidence has been verified.
Data requirements
Declared loop-data needs, missing evidence, and the next checks that matter.
Observation / ego video
Needs visual observations or other state streams before this model direction is actionable.
Language intent / task phase
Needs task intent, instructions, keysteps, or phase labels to connect behavior to goals.
Action / robot state
Needs executable actions, robot state, hand pose, or trajectory supervision.
Future state / dynamics
Needs future-state supervision or rollout structure to validate predictive dynamics.
Critical gaps
- Observation / ego video: Needs visual observations or other state streams before this model direction is actionable.
- Language intent / task phase: Needs task intent, instructions, keysteps, or phase labels to connect behavior to goals.
- Action / robot state: Needs executable actions, robot state, hand pose, or trajectory supervision.
Linked datasets
Signal-level links only. Verify runtime interfaces before use.
No related catalog datasets are linked to this model yet.
More evidenceShowHide
Additional data signals
Feedback / correction / failure
Needs success, failure, correction, or recovery signals to turn evaluation into better data.
Sim-real / embodiment metadata
Needs embodiment, calibration, or sim-real pairing metadata for transfer analysis.
Additional decision dimensions
Access and license are declared by the source.
75 · c85Training data requirements are not structured enough for reliable dataset matching.
— · c15Hardware, latency, dependencies, and checkpoint loading are not pipeline-tested.
70 · c55Artifact facts
- availability
- metadata_verified
- open
- repository metadata
- repository.files
- metadata_verified
- .gitattributes · README.md · config.json · model.safetensors · policy_postprocessor.json · policy_postprocessor_step_2_unnormalizer_processor.safetensors · policy_preprocessor.json · policy_preprocessor_step_3_normalizer_processor.safetensors
- repository file tree
- model.weight_files
- metadata_verified
- repository: lerobot/VLA-JEPA-Pretrain · count: 3 · sample files: model.safetensors · policy_postprocessor_step_2_unnormalizer_processor.safetensors · policy_preprocessor_step_3_normalizer_processor.safetensors
- Hugging Face model metadata siblings
- model.checkpoint_files
- metadata_verified
- repository: lerobot/VLA-JEPA-Pretrain · count: 3 · sample files: model.safetensors · policy_postprocessor_step_2_unnormalizer_processor.safetensors · policy_preprocessor_step_3_normalizer_processor.safetensors
- Hugging Face model metadata checkpoint files
- model.config_files
- metadata_verified
- repository: lerobot/VLA-JEPA-Pretrain · count: 1 · sample files: config.json
- Hugging Face model metadata siblings
- license.weights
- metadata_verified
- apache-2.0
- Hugging Face model card license metadata
- license
- metadata_verified
- apache-2.0
- Hugging Face model card license metadata
- release_timing
- metadata_verified
- 2026-05-28T08:55:09.000Z
- Existing published Catalog release-date evidence