Every artifact¶
24 artifacts are described below. Each links to its own repository, where the README carries the worked example and the honest-scope section for that tool.
27 artifacts are published in total; the 3 not described here are named in the warning at the foot of this page.
Tools¶
| artifact | what it answers |
|---|---|
abstain-bench |
how often does a verifier pass input it could not check? |
evidence |
run the whole portfolio over your repo — the weakest leg, never the mean |
floorgen |
what must your system remember? an exact lower bound |
formal-proof-mcp |
a proof kernel for your coding agent |
gatecount |
exactly how many states does removing this check admit? |
gridlock |
certify a wait-for relation cannot wedge |
honestbench |
measure your CI's escape rate |
kvleak |
cross-tenant leak scanner |
kvprobe |
model-substitution detector with a measured FPR |
preregister |
refuses to seal a plan whose conclusion is already fixed |
proof-carrying-ci |
the whole portfolio as one CI check, with SARIF |
proof-to-code-drift |
fail the build when the proof stops matching |
sf-verify |
re-derive admission decisions offline |
signoff-cert |
certificates that carry their own false-pass bound |
tokencount |
a token count both parties can recompute |
Benchmarks¶
| artifact | what it answers |
|---|---|
illusion-bench |
how many broken kernels does your oracle admit? |
kv-reuse-econ-bench |
recompute our economics headline |
llm-tenant-isolation-bench |
recompute our isolation figures |
Datasets¶
| artifact | what it answers |
|---|---|
abstain-corpus |
32 inputs a verifier must NOT pass |
kv-reuse-econ-traces |
per-workload reuse accounting + the closed form |
kv-tenant-isolation-bench |
isolation observations, uninterpretable rows included |
llm-precision-fingerprints |
precision-labelled logprobs with a negative control |
Spaces¶
| artifact | what it answers |
|---|---|
tenant-leak-demo |
the residency calculator |
wait-for-visualiser |
paste a wait-for graph, see the cycle |
Published but not described
certhead, docs-site, isolation-tax are live but have no entry in the canonical table, so they are missing from every cross-link footer. That is a bug in the publishing metadata.
Install everything¶
The distribution is evidence-runner; the module you import is evidence. pip install evidence fetches an unrelated third party's project.
Individual packages install from GitHub until the PyPI publisher is enabled: