Choose a workflow¶
make e2e trains and proves classifiers locally. Use make e2e-llm to prove
the TinyLlama response, or choose another workflow below.
| I want to… | Command | Where / resources | Success signal |
|---|---|---|---|
| Check software contracts | make check-conformance |
Linux/macOS; core environment; no account | 156 matched cases, 32 unavailable full-evidence obligations; no proof |
| Run a published classifier | scripts/predict_published_classifier.py |
Linux/macOS; core for MLP, train extra for CNN | Integer score after checking model hashes; native inference only |
| Train, prove and verify classifiers | make e2e |
Apple Silicon Mac; 12 GiB free; uv 0.9.18 | Nine Circle proofs, 63 public-input and 18 substitution rejections |
| Prove a complete TinyLlama response | make e2e-llm |
Mac preparation; 32 GB RAM, 16 GiB free; HF CPU jobs | 23 new segments, two honest verifications, 14 rejected mutations |
| Verify retained LLM proofs locally | make verify-llm LLM_RUN=… |
Mac; native Rust toolchain; 8 GiB free; no HF credentials | Two honest checks, 36 rejected mutations |
| Measure SIMD/CUDA proving | make benchmark-llm-gpu … |
Mac controller; HF CPU/H200 jobs; completed caller-owned LLM run | Matched full runs, 69 identical artifacts, fresh CPU/Mac checks |
| Bind LLM and classifier proofs | make e2e-composed |
Both sets of prerequisites; 32 GiB free | Same-request verified relations and classifier verdicts |
Prefer an interactive interface? Run make demo-tui or make demo-web from a
checkout. The workbench uses these same drivers and retains their
results; opening an interface does not start a proof or paid job.
Get the checkout¶
Python packages are not published. Trained classifiers are available on Hugging Face.
The smallest software check¶
uv sync --locked --python 3.12
uv run --locked hallmark validate-data fixtures/smoke.jsonl
make check-conformance
This validates data and software contracts. It does not generate a cryptographic proof or run hardware attestation.
A local proof workflow¶
With Git, Make, uv 0.9.18, Rust nightly-2025-07-14 and an Apple Silicon Mac:
Allow several minutes plus the first Rust build; the sampled worker cap is 30 GiB. No GPU, token, cloud account or pretrained checkpoint is needed. Read the outputs and troubleshooting guide.
A complete LLM response¶
Set your HF token in the environment or ignored .env, check prepaid credits,
then use the LLM workflow. It starts three sequential paid
CPU jobs, under a $2.50 startup-inclusive cost ceiling.
The GPU benchmark is separate: it reuses a completed reviewed public witness archive and starts CPU/H200 jobs under a $5 ceiling. It does not train a new model. Read the run plan and balance-input requirements before launching.
Related guides¶
- Learn the concepts: statements, witnesses and caller enrollment.
- Architecture: checks inside the circuits and in caller code.
- Research evidence: measurements, failed runs and limits.