Bundle
Decision counts are shown per predicate URI only. We never composite a pass-rate across heterogeneous predicates — that is metric laundering.
https://evals.intentsolutions.io/gate-result/v1— fail: 1
| Gate | Decision | Predicate URI | Evaluated at | Bundle created at | Rekor anchor | Ingested at |
|---|---|---|---|---|---|---|
coreweave-gpu-node-forensics |
fail | https://evals.intentsolutions.io/gate-result/v1 |
3101843770 |
Why
The reasons below are copied from the signed result, in the order the evaluator wrote them.
coreweave-gpu-node-forensics fail
Eval definition: eval spec
- 10/17 criteria passed on MiniMax-M3 (provider: minimax)
- 1 blocker criterion evaluation(s) failed
- 1 criteria could not be judged (unsure)
- thresholds did not pass
- regression comparison was not run
- rollout decision is block