zpe-robotics 0.1.0

Deterministic motion utility kernel for frozen wire-v1 robotics transport and replay.

ZPE-Robotics

SAL v6.2 — free below $100M annual revenue. See LICENSE.

---

What This Is

187× compression on real robot data. Red-team tested. pip install -e . from clone (PyPI publication pending).

ZPE-Robotics is motion telemetry infrastructure — deterministic logging, compressed replay, and PrimitiveIndex search over joint streams. Built for robotics infrastructure teams and simulation/replay platforms where motion logs are expensive to store, slow to search, and impossible to replay deterministically. The package is public. The governing engineering surface remains blocker-state.

Field	Value
Architecture	MANIFOLD_MOTION
Encoding	WIRE_V1

Key Metrics

Metric	Value	Baseline
COMPRESSION	187׆	vs zstd_l3 4.44× (42× better)

† Bounded-lossy (angular fidelity ≤ 0.5° on smooth trajectories; step/discontinuous inputs cause Gibbs ringing — 68° RMSE measured on unit-amplitude step signal); baselines are lossless. | ENCODE_P50 | 0.11 | ms | | DECODE_P50 | 0.09 | ms | | BENCHMARK_GATES | 4/5 | 3 datasets, 3 families |

Source: proofs/enterprise_benchmark/benchmark_result.json | proofs/enterprise_benchmark/GATE_VERDICTS.json | proofs/artifacts/lerobot_expanded_benchmarks/aggregate_spread_summary.json

Competitive Benchmarks

Full competitive analysis: BENCHMARKS.md | Source: proofs/enterprise_benchmark/benchmark_result.json | proofs/red_team/red_team_report.json

Tool	Compression Ratio	Notes
ZPE P8	187.13׆	governing LeRobot real-data benchmark; PrimitiveIndex search requires decode
zstd_l19	4.59×	strongest retained classical codec in the benchmark set
zstd_l3	4.44×	red-team attack 1 baseline; ZPE is 42.14× better
gzip_l9	3.97×	retained gzip baseline
mcap_zstd	3.99×	MCAP container baseline
lz4_default	3.00×	low-latency baseline
h5py_gzip9	2.69×	HDF5 gzip baseline
h5py_lzf	2.15×	HDF5 fast baseline

† Bounded-lossy (angular fidelity ≤ 0.5° on smooth trajectories; step/discontinuous inputs cause Gibbs ringing — 68° RMSE measured on unit-amplitude step signal); all other baselines are lossless.

What We Prove

Auditable guarantees backed by committed proof artifacts. Start at AUDITOR_PLAYBOOK.md.

• Spectral wire transport with directional reasoning layer for robot action sequences
• Search operates on decoded motion streams via PrimitiveIndex
• Red-team resilience: 3 attacks withstood, 3 failed, 1 skipped — transparently reported
• VLA tokenization aligns with vision-language-action model input formats
• Public package install surface verified (pip install -e . from clone; PyPI publication pending)

What We Don't Claim

• Full release readiness
• Bit-exact .zpbot round-trip replay
• B3 benchmark gate pass
• Red-team resilience on attacks 3 and 5
• Robotics Rust ABI
• Universal angular fidelity — the ≤ 0.5° bound holds on smooth trajectories only; FFT-based encoding causes Gibbs ringing on step/discontinuous inputs (68° RMSE measured on unit-amplitude step signal)
• Search-without-decode — PrimitiveIndex requires full packet decode before indexing

Commercial Readiness

Field	Value
Verdict	BLOCKED
Commit SHA	C7DED78
Confidence	58%
Source	proofs/FINAL_STATUS.md

Evaluators: Engineering blockers active — see proofs/ENGINEERING_BLOCKERS.md. pip install -e . from clone to evaluate today (PyPI publication pending). Contact [e-mail].

Tests and Verification

Code	Check	Verdict
V_01	BENCHMARK_GATE_B1_COMPRESSION	PASS
V_02	BENCHMARK_GATE_B2_ZSTD_BASELINE	PASS
V_03	BENCHMARK_GATE_B3_BIT-EXACT_+_SE...	FAIL
V_04	BENCHMARK_GATE_B4_ENCODE_LATENCY	PASS
V_05	BENCHMARK_GATE_B5_DECODE_LATENCY	PASS
V_06	RED-TEAM_ATTACK_1_BASELINE	PASS
V_07	RED-TEAM_ATTACK_2_ENTROPY	PASS
V_08	RED-TEAM_ATTACK_3_LOSSLESS_QUALI...	FAIL
V_09	RED-TEAM_ATTACK_4_CORPUS_ADEQUACY	INC
V_10	RED-TEAM_ATTACK_5_FALSE-POSITIVE...	FAIL
V_11	RED-TEAM_ATTACK_6_PYTHON_3.12_PA...	PASS
V_12	RED-TEAM_ATTACK_7_EXTERNAL_REPRO...	INC

Proof Anchors

Path	State
proofs/ENGINEERING_BLOCKERS.md	VERIFIED
proofs/enterprise_benchmark/GATE_VERDICTS.json	VERIFIED
proofs/red_team/red_team_report.json	VERIFIED
proofs/release_candidate/clean_clone_result.json	VERIFIED
proofs/release_candidate/it04_parity_matrix_result.json	VERIFIED
proofs/imc_audit/imc_architecture_audit.json	VERIFIED

• Runtime and proof artifacts outrank prose.
• GO and NO-GO language is reserved for named gates only.
• Historical proof bundles remain lineage only. They do not override the March 21 blocker-state evidence.
• No IMC runtime import is introduced by this repo.
• The current installable package artifact is zpe-robotics 0.1.0, but the repo's March 21 blocker-state docs remain the authority surface for engineering status.

Use these files together:

Need	Read first
Current blocker truth	proofs/ENGINEERING_BLOCKERS.md
Benchmark verdicts	proofs/enterprise_benchmark/GATE_VERDICTS.json
Adversarial findings	proofs/red_team/red_team_report.json
Package/runtime boundary	proofs/runbooks/TECHNICAL_RELEASE_SURFACE.md
Release-candidate note	docs/RELEASE_CANDIDATE.md
Citation record	CITATION.cff
Docs registry	docs/DOC_REGISTRY.md
Historical lineage	proofs/artifacts/historical/README.md

Expanded LeRobot Benchmark Coverage

The expanded benchmark sweep is recorded in proofs/artifacts/lerobot_expanded_benchmarks/. The current qualified surface covers 3 real datasets across 3 materially distinct families, with compression ratios spanning 58.70x to 186.05x.

Dataset	Family	Compression ratio	Status
lerobot/columbia_cairlab_pusht_real	pusht	186.05x	qualified
lerobot/aloha_mobile_shrimp	aloha	61.27x	qualified
lerobot/umi_cup_in_the_wild	umi	58.70x	qualified
lerobot/pusht_image	pusht	n/a	skipped: insufficient joint dimension

Read proofs/artifacts/lerobot_expanded_benchmarks/aggregate_spread_summary.json for the rollup verdict and proofs/artifacts/lerobot_expanded_benchmarks/dataset_manifest.json for the full attempt ledger, including qualification misses that were preserved rather than averaged away.

Repo Shape

Field	Value
Proof Anchors	6
Modality Lanes	3
Authority Source	proofs/ENGINEERING_BLOCKERS.md

The modality-lane count reflects the three recorded parity lanes (arm64-qemu, macos, ubuntu-x86) in proofs/release_candidate/it04_parity_matrix_result.json.

Area	Purpose
src/zpe_robotics/	package implementation, CLI, packet handling, search, anomaly, and audit logic
tests/	release-surface, CLI, codec, and regression checks
scripts/	replay, benchmark, falsification, and clean-clone helpers
docs/	front-door, architecture, support, legal, and family-linkage docs
proofs/	blockers, benchmark artifacts, red-team outputs, release runbooks, and historical bundles
.github/workflows/	CI, clean-clone, parity, comparator, and publish workflows

Quick Start

Surface	Current truth
Repository	https://github.com/Zer0pa/ZPE-Robotics.git
Package / import / CLI	zpe-robotics / zpe_robotics / zpe-robotics
Acquisition surface	pip install -e . from clone (PyPI publication pending)
License	LicenseRef-Zer0pa-SAL-6.2
Contact	[e-mail]
Release state	public repo and published package; engineering surface remains blocker-governed
Engineering	not complete
Current authority	proofs/ENGINEERING_BLOCKERS.md

Authority layer	File
governing blocker state	proofs/ENGINEERING_BLOCKERS.md
benchmark gate verdicts	proofs/enterprise_benchmark/GATE_VERDICTS.json
adversarial verdicts	proofs/red_team/red_team_report.json
package/runtime boundary	proofs/runbooks/TECHNICAL_RELEASE_SURFACE.md
IMC integration boundary	proofs/imc_audit/imc_architecture_audit.json

Install from clone (PyPI publication pending):

pip install -e .
zpe-robotics --version

Repo-local engineering surface:

python -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade pip setuptools wheel
python -m pip install -e ".[dev,benchmark,telemetry,netnew]"
python -m pytest tests -q
python -m build

If you need the shortest honest verification route, use docs/AUDITOR_PLAYBOOK.md. If you need the release workflow boundary, use RELEASING.md.

Need	Route
Contributor workflow	CONTRIBUTING.md
Security reporting	SECURITY.md
Governance and claim policy	GOVERNANCE.md
Support routing	docs/SUPPORT.md
Docs index	docs/README.md
Operator commands	docs/OPERATOR_RUNBOOK.md

Ecosystem

ZPE-Robotics follows the portfolio release-hygiene pattern used by ZPE-IMC, but it does not inherit IMC runtime claims, benchmark verdicts, or release readiness by association.

Need	Route
Robotics-to-IMC boundary	docs/family/ROBOTICS_RELEASE_LINKAGE.md
Frozen proof lineage note	proofs/README_LINEAGE_PATHS.md
Reference core repo	https://github.com/Zer0pa/ZPE-IMC

Observability: Comet dashboard (public)

Who This Is For

Ideal first buyer	Robotics infrastructure team or simulation/replay platform
Pain	Robot telemetry archives grow fast and can only be searched after full decompression — replay pipelines lack determinism guarantees
Deployment	Public Python package — pip install zpe-motion-kernel
Family position	Product candidate in the Zer0pa deterministic encoding family. ZPE-IMC is the umbrella integration layer