The audited
surface.

Every instrument we have read line by line. A defect is named only where a public receipt exists. Everything else is counted, not claimed.

The surface
Targets56Instruments read in full, across four sectors
Receipts18Named findings with a public URL anyone can open
Clean2Read adversarially and held. We publish these too
02Coverage

And 38 more, read in full.

Reproduced defects in these exist in the private record and appear in the ledger without a name, either because disclosure is still on the vendor's clock or because the report is not filed yet. Listed, not claimed.

Benchmarks20 targets
openai/mle-benchsierra-research/tau-benchweb-arena-x/webarenaaymeric-roucher/GAIAarcprize/ARC-AGIHazyResearch/legalbenchpatronus-ai/financebenchLiveBench/LiveBenchNVIDIA/RULERMETR/RE-BenchMETR/public-taskssierra-research/tau2-benchsierra-research/mu-benchopenai/gpt-ossdeepseek-ai/DeepSeek-Mathdeepseek-ai/DeepSeek-CoderServiceNow/WorkArenaServiceNow/BrowserGymsalesforce/xLAMogx-ai/ogx
Harnesses and scoring libraries9 targets
stanford-crfm/helmArize-ai/phoenixMETR/vivariamlcommons/modelgaugeMETR/task-protected-scoringharbor-framework/harborMercor-io/terminal-benchtruera/trulensmlflow/mlflow (genai)
Judges, arenas, and leaderboards8 targets
lmarena/arena-hard-autolm-sys/FastChatallenai/reward-benchethz-spylab/agentdojoMETR/eval-analysis-publicMETR/metr-inspect-agentslmarena/copilot-arenasgl-project/sglang (benchmark)
Safety and guardrail tooling1 target
Giskard-AI/giskard

Gold = read adversarially and held

03Method

How we read.

Line by line

We read the scoring path, not the README. The grader, the parser, the aggregation, the cache, the reset.

Proven or dropped

Every candidate defect must reproduce against the genuine code path. Hypotheses that fail to execute are recorded as refuted and never reported.

Deduped against the record

Every finding is checked against the project's own tracker and the public literature before it is counted. Known issues are cited, not re-claimed.

Private first

Reports go to the maintainer before anywhere else, with the reproduction and a fix. Publication follows on the vendor's clock.

Is your instrument on this map?

If it is, you can read what we found. If it is not, it can be.

What happens
01

You send one public claim. A benchmark score, a safety rate, a leaderboard position.

02

We read the instrument, not the number. Harness, judge, grading code.

03

One page back: what holds, what is unverifiable, what is broken. Each with a reproduction.