CAIN-42 CAIN Studio

CAIN-42 claim

C42-L5-TRAJECTORY-FAIL-OPEN-FOUND

Negative evidence: the first continuous-authorization implementation (uncommitted, published earlier on 2026-09-28) failed 13 of 13 probes -- self-signed, unsigned, foreign or unbounded leases, empty scope, missing policy/context, PAUSED/ESCALATED/REAUTHORIZATION_REQUIRED trajectories and unchecked plan binding were ALLOWed; containment could revive a TERMINATED trajectory. 5 of its 15 invariants were the constant True. All fixed in 040cee2 with regression tests.

Last reviewed 2026-10-01

IMPLEMENTED

The claim

Negative evidence: the first continuous-authorization implementation (uncommitted, published earlier on 2026-09-28) failed 13 of 13 probes -- self-signed, unsigned, foreign or unbounded leases, empty scope, missing policy/context, PAUSED/ESCALATED/REAUTHORIZATION_REQUIRED trajectories and unchecked plan binding were ALLOWed; containment could revive a TERMINATED trajectory. 5 of its 15 invariants were the constant True. All fixed in 040cee2 with regression tests.

Level IMPLEMENTED is how far the evidence goes: TESTED means a test suite exercised it, LIVE means it was observed on the hosted system. Nothing is claimed beyond its level.

categoryTRAJECTORY GOVERNANCE
statusTESTED
evidence level meaningadversarial verification
limitsthe 'before' column is the recorded probe output, not re-runnable from git history
verification methodtests/test_cain42_l5_trajectory_prompt3.py::test_R01..R13 (the pre-fix code was never committed; its outputs are the recorded probe run)
revalidate by2026-12-30T03:20:13Z
claim version1

Evidence files

Verify this signed claim in your browser

Checks the whole registry's Ed25519 signature against the published evidence-root key, then re-hashes this claim's artifact files. Same algorithm as the standalone verify_claims.py.

From CAIN-42 signed public claims registry.

Try CAIN-42 on your own agents

Create a free account and every new account starts with a 7-day trial of the full platform. Or try the sandbox first, with no account at all.

Create a free account →  ·  Try the sandbox  ·  See the whole ecosystem