Metadata-Version: 2.4
Name: orbit-robotics
Version: 0.7.2
Summary: Data engineering copilot for robot imitation learning datasets
Author: Rahil Lasne
License-Expression: MIT
Project-URL: PyPI, https://pypi.org/project/orbit-robotics/
Keywords: robotics,machine-learning,data-quality,imitation-learning,lerobot
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: click>=8.0
Requires-Dist: rich>=13.0
Requires-Dist: numpy>=1.24
Requires-Dist: pandas>=2.0
Requires-Dist: scipy>=1.10
Requires-Dist: huggingface-hub>=0.20
Requires-Dist: pyarrow>=14.0
Requires-Dist: scikit-learn>=1.3
Requires-Dist: httpx>=0.24
Provides-Extra: vision
Requires-Dist: torch>=2.0; extra == "vision"
Requires-Dist: transformers>=4.36; extra == "vision"
Requires-Dist: opencv-python>=4.8; extra == "vision"
Requires-Dist: decord>=0.6; extra == "vision"
Requires-Dist: Pillow>=10.0; extra == "vision"
Provides-Extra: vlm
Requires-Dist: google-generativeai>=0.5; extra == "vlm"
Provides-Extra: claude
Requires-Dist: anthropic>=0.25; extra == "claude"
Provides-Extra: openai
Requires-Dist: openai>=1.0; extra == "openai"
Provides-Extra: assist
Requires-Dist: google-genai>=1.0; extra == "assist"
Provides-Extra: assist-claude
Requires-Dist: claude-code-sdk>=0.1; extra == "assist-claude"
Provides-Extra: rlds
Requires-Dist: tfrecord>=1.14; extra == "rlds"
Provides-Extra: hdf5
Requires-Dist: h5py>=3.8; extra == "hdf5"
Provides-Extra: rosbag
Requires-Dist: mcap>=1.1; extra == "rosbag"
Requires-Dist: mcap-ros2-support>=0.5; extra == "rosbag"
Provides-Extra: rosbag-ros1
Requires-Dist: rosbag>=1.16; extra == "rosbag-ros1"
Provides-Extra: formats
Requires-Dist: orbit-robotics[hdf5,rlds,rosbag]; extra == "formats"
Provides-Extra: sim
Requires-Dist: mujoco>=3.0; extra == "sim"
Provides-Extra: monitor
Requires-Dist: tbparse>=0.0.8; extra == "monitor"
Provides-Extra: watch
Requires-Dist: foxglove-sdk>=0.20; extra == "watch"
Provides-Extra: watch-audio
Requires-Dist: simpleaudio>=1.0; extra == "watch-audio"
Provides-Extra: watch-speech
Requires-Dist: pyttsx3>=2.90; extra == "watch-speech"
Provides-Extra: config
Requires-Dist: pyyaml>=6.0; extra == "config"
Provides-Extra: causal
Requires-Dist: pgmpy>=0.0.21; extra == "causal"
Provides-Extra: signature
Requires-Dist: iisignature>=0.24; extra == "signature"
Provides-Extra: dev
Requires-Dist: pytest>=7.0; extra == "dev"
Requires-Dist: pytest-timeout>=2.1; extra == "dev"
Requires-Dist: ruff>=0.1; extra == "dev"
Requires-Dist: h5py>=3.8; extra == "dev"
Requires-Dist: pyyaml>=6.0; extra == "dev"
Provides-Extra: all
Requires-Dist: orbit-robotics[assist,causal,config,formats,monitor,openai,sim,vision,vlm]; extra == "all"
Dynamic: license-file

# ORBIT (`orbit-robotics`) — RETIRED

**This package is no longer maintained. Version 0.7.2 is its final release.**
All earlier versions have been yanked. Please do not build on it.

---

## Why it was retired

ORBIT was sold on a claim that turned out to be false.

Versions through 0.8.0 stated that ORBIT's A–F dataset grades were *"calibrated
against 82 real training runs with known success rates,"* that ORBIT could
predict whether training on your dataset would succeed, and that per-episode
scoring could identify which demonstrations to keep or remove to improve a
policy. **Those claims are retracted.**

They were retracted because we tested them ourselves and they did not hold:

- We trained **701 policies** on controlled demonstration subsets — Diffusion
  Policy and ACT from scratch, SmolVLA and π₀.₅ fine-tuned — evaluated on PushT,
  two bimanual ALOHA tasks, and two ten-task LIBERO suites, every batch
  pre-registered.
- **No score we built for a demonstration predicted whether keeping it improved
  the policy.**
- Retraining on *byte-identical data* with only a different seed moved one LIBERO
  task's success rate by a standard deviation of **20.4 percentage points**, and
  the ten-task average by **4.23**. A calibration against 82 observational
  outcomes could not have measured what it claimed to, because the noise is the
  same size as the effect.

The mechanical parts of ORBIT were never the problem. Dead-joint detection,
joint clipping, NaN and schema checks, temporal-alignment measurement and format
conversion all report real, measurable properties of a dataset. What was wrong
was the layer built on top of them that claimed to predict training outcomes.

## What replaced it

The measurement programme that produced the retraction continues, and the honest
part of the work — **statistics for robot-policy evaluation**, not predictions
about datasets — moved to a separate package:

> **`orbit-eval`** — noise floors, power analysis, correctly-paired comparisons,
> per-task release selection, and refusal logic that returns *no number* when a
> design cannot support one.

The full study is *"Noise Floors and Non-Portable Value: What Robot Imitation
Data Curation Can and Cannot Measure"* (Lasne, 2026).

## If you are still using this package

Pin `orbit-robotics==0.7.2` if you depend on the loaders or the mechanical
checks; they work and they are honest. Do not rely on any grade, prediction,
"fit" score, sim2real transfer estimate, or episode-value output from any
version — those are the retracted surfaces.

## Why this release exists at all

A package that shipped a false claim for over a year should not simply vanish.
Deleting the project would free the name for someone else and would read as
hiding. This release exists so that anyone who installs `orbit-robotics` — or
who finds it in an old requirements file — is told plainly what was wrong.

## The research in this repository

This repo is also the measurement programme behind the retraction — the only
replicate-retraining variance corpus in robot imitation learning, with the
pre-registrations, the scored results, and the negative findings kept in.

- [`RETRAIN_LOTTERY.md`](RETRAIN_LOTTERY.md) — the flagship result and the
  8-retrain measurement protocol
- [`research/`](research/) — pre-registered designs, scored results, freeze chains
- [`experiments/forecast/atlas.csv`](experiments/forecast/atlas.csv) — the
  16-regime variance atlas
- [`paper/DRAFT.md`](paper/DRAFT.md) — *Noise Floors and Non-Portable Value*

## Author

Rahil Lasne ([@Rahillasne](https://github.com/Rahillasne)) — ORBIT Research.

## License

MIT (unchanged).
