Evidence library · family
Evolution
56 tested rules in the 'evolution' family, 56 held.
Last reviewed 2026-10-01
56 of 56 held niche Autonomy, control loops & recovery
What this family tests
Every rule the CAIN-42 test suites recorded under the family evolution, across 5 evidence bundles. Each rule links to its own page with the recorded result and an in-browser check of the file it came from.
| ID | Rule | Bundle | Result |
|---|---|---|---|
| I-EVO-candidate_id | candidate field candidate_id | E27 | held |
| I-EVO-problem | candidate field problem | E27 | held |
| I-EVO-proposal | candidate field proposal | E27 | held |
| I-EVO-code_digest | candidate field code_digest | E27 | held |
| I-EVO-benchmark | candidate field benchmark | E27 | held |
| I-EVO-security | candidate field security | E27 | held |
| I-EVO-performance | candidate field performance | E27 | held |
| I-EVO-risk | candidate field risk | E27 | held |
| I-EVO-rollback | candidate field rollback | E27 | held |
| I-EVO-evidence | candidate field evidence | E27 | held |
| I-EVO-no-confidence | model confidence not used in ranking | E27 | held |
| I-EVO-not-self-authorized | candidate not self-authorized | E27 | held |
| I-CODELAB-BASELINE | code lab stage BASELINE | E27 | held |
| I-CODELAB-GENERATE | code lab stage GENERATE | E27 | held |
| I-CODELAB-COMPILE | code lab stage COMPILE | E27 | held |
| I-CODELAB-TEST | code lab stage TEST | E27 | held |
| I-CODELAB-SECURITY_TEST | code lab stage SECURITY_TEST | E27 | held |
| I-CODELAB-BENCHMARK | code lab stage BENCHMARK | E27 | held |
| I-CODELAB-VERIFY | code lab stage VERIFY | E27 | held |
| I-CODELAB-RANK | code lab stage RANK | E27 | held |
| I-CODELAB-KEEP | code lab stage KEEP | E27 | held |
| I-CODELAB-no-prod | candidates do not enter production | E27 | held |
| E28-I83 | a self-improvement candidate cannot approve itself | E28 | held |
| E28-I84 | a candidate with any evaluation stage missing is not promoted | E28 | held |
| E35-EVOGATE-DISCOVERY | evolution gate DISCOVERY exists | E35 | held |
| E35-EVOGATE-DESIGN | evolution gate DESIGN exists | E35 | held |
| E35-EVOGATE-THREAT_MODEL | evolution gate THREAT_MODEL exists | E35 | held |
| E35-EVOGATE-SANDBOX | evolution gate SANDBOX exists | E35 | held |
| E35-EVOGATE-UNIT_TEST | evolution gate UNIT_TEST exists | E35 | held |
| E35-EVOGATE-ADVERSARIAL_TEST | evolution gate ADVERSARIAL_TEST exists | E35 | held |
| E35-EVOGATE-DIFFERENTIAL_TEST | evolution gate DIFFERENTIAL_TEST exists | E35 | held |
| E35-EVOGATE-CLEAN_ROOM_TEST | evolution gate CLEAN_ROOM_TEST exists | E35 | held |
| E35-EVOGATE-PERFORMANCE_TEST | evolution gate PERFORMANCE_TEST exists | E35 | held |
| E35-EVOGATE-GOVERNABILITY_TEST | evolution gate GOVERNABILITY_TEST exists | E35 | held |
| E35-EVOGATE-CANARY | evolution gate CANARY exists | E35 | held |
| E35-EVOGATE-OBSERVE | evolution gate OBSERVE exists | E35 | held |
| E35-EVOGATE-PROOF | evolution gate PROOF exists | E35 | held |
| E35-EVOGATE-HUMAN_ADMIN_APPROVAL | evolution gate HUMAN_ADMIN_APPROVAL exists | E35 | held |
| E35-EVOGATE-DEPLOY | evolution gate DEPLOY exists | E35 | held |
| E35-EVOGATE-MONITOR | evolution gate MONITOR exists | E35 | held |
| E35-EVOGATE-ROLLBACK | evolution gate ROLLBACK exists | E35 | held |
| evolution | every 'evolution' invariant in this bundle (8 of 8 held) | E39 | held |
| E42-EVOSTAGE-DISCOVER | governed evolution stage DISCOVER exists | E42 | held |
| E42-EVOSTAGE-HYPOTHESIZE | governed evolution stage HYPOTHESIZE exists | E42 | held |
| E42-EVOSTAGE-EXPERIMENT | governed evolution stage EXPERIMENT exists | E42 | held |
| E42-EVOSTAGE-EVALUATE | governed evolution stage EVALUATE exists | E42 | held |
| E42-EVOSTAGE-VERIFY | governed evolution stage VERIFY exists | E42 | held |
| E42-EVOSTAGE-PROPOSE | governed evolution stage PROPOSE exists | E42 | held |
| E42-EVOSTAGE-SANDBOX | governed evolution stage SANDBOX exists | E42 | held |
| E42-EVOSTAGE-CANARY | governed evolution stage CANARY exists | E42 | held |
| E42-EVOSTAGE-COMPARE | governed evolution stage COMPARE exists | E42 | held |
| E42-EVOSTAGE-AUTHORIZE | governed evolution stage AUTHORIZE exists | E42 | held |
| E42-EVOSTAGE-DEPLOY | governed evolution stage DEPLOY exists | E42 | held |
| E42-EVOSTAGE-OBSERVE | governed evolution stage OBSERVE exists | E42 | held |
| E42-EVOSTAGE-ROLLBACK | governed evolution stage ROLLBACK exists | E42 | held |
| E42-EVOSTAGE-REVERIFY | governed evolution stage REVERIFY exists | E42 | held |
Other families in this niche
loop · research · state_machine · autonomy · drift · fabric_component · integrity · graph · radar · risk · swe · learning_loop · operation_state · promotion_dominance · self_healing · self_test · profile · swarm · degradation · self_governance · autonomy_gradient · plan_check_act · self_improvement · promotion_stage
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