CAIN-42 CAIN StudioEvidence library · niche
Core guarantees
Fail-closed basics that every other area relies on. 377 tested invariants.
Last reviewed 2026-10-01
377 of 377 held
Test families in this niche
action (32) · state_machine (17) · relationship (14) · operation_state (12) · integrity (11) · swe (10) · hardware (9) · cognitive (9) · plan_check_act (9) · r2e (8) · radar (8) · graph (8) · research (7) · telemetry (7) · research_to_implementation (7) · federation (6) · translation (6) · fabric_component (6) · tech_radar (5) · environment_query (5) · profile (5) · risk (4) · operation_kind (4) · trajectory (4) · agency_graph (4) · environment (4) · intent (3) · moat (3) · swarm (3) · match (3) · competitive_gap (3) · f2t (3) · replay (2) · offline (2) · reassessment (2) · cross_domain (2) · failure_to_test (2) · composition (2) · soc (1) · developer (1) · gap_detector (1) · status (1) · conflict (1) · engine_mesh (1) · perimeter (1) · recursion (1) · scheduler (1) · architecture (1) · evaluation (1) · health (1) · systemic (1)
Where these come from
- CAIN-42 Evolution 35 -- Continuous Governance Intelligence Fabric: 54
- CAIN-42 Evolution 42 -- Supreme Governed Agentic Infrastructure Platform: 40
- CAIN-42 Evolution 27 -- Agentic Internet Control Plane: 36
- CAIN-42 Evolution 21 -- Governed Open-Ended Intelligence Fabric: 35
- CAIN-42 Evolution 33 -- Governed Agentic Operating Fabric: 29
- CAIN-42 Evolution 26 -- Universal Machine Agency Trust Fabric: 26
- CAIN-42 Evolution 20 -- Governed Agentic Civilization Fabric: 24
- CAIN-42 Evolution 23 -- Governed Meta-Intelligence Fabric: 24
- CAIN-42 Evolution 19 -- Governed Autonomy Operating Fabric: 21
- CAIN-42 Evolution 36 -- Machine Agency Exchange Fabric: 20
- CAIN-42 Evolution 41 -- Machine Agency Exchange Fabric: 18
- CAIN-42 Evolution 25 -- Universal Machine Agency Fabric: 14
- CAIN-42 Evolution 24 -- Governed Agentic Internet Fabric: 9
- CAIN-42 Evolution 30 -- Governed Machine Autonomy Fabric: 7
- CAIN-42 Evolution 32 -- Governed Autonomy Learning Fabric: 7
- CAIN-42 Evolution 37 -- Autonomous Execution Mesh: 5
- CAIN-42 Evolution 38 -- Portable Proof-Carrying Machine Agency: 4
- CAIN-42 Evolution 39 -- Governed Agent Factory: 4
Rules 151–300 of 377
| ID | Rule | Bundle | Result |
|---|---|---|---|
| I-INTENT-order | state advances in order | E26 | held |
| I-INTENT-mutation | instruction mutation detected | E26 | held |
| I-INTENT-clean | unchanged intent passes | E26 | held |
| I-XDOMAIN-untrusted | untrusted issuer refused | E27 | held |
| I-XDOMAIN-action | untrusted action refused | E27 | held |
| I-COG-fast | select fast | E27 | held |
| I-COG-reasoning | select reasoning | E27 | held |
| I-COG-specialist | select specialist | E27 | held |
| I-COG-vision | select vision | E27 | held |
| I-COG-coding | select coding | E27 | held |
| I-COG-retrieval | select retrieval | E27 | held |
| I-COG-verifier | select verifier | E27 | held |
| I-COG-critic | select critic | E27 | held |
| I-COG-planner | select planner | E27 | held |
| I-F2T-test | test generated | E27 | held |
| I-F2T-invariant_candidate | invariant_candidate generated | E27 | held |
| I-GOAL-reward_hacking | goal signal reward_hacking | E27 | held |
| I-GOAL-proxy_optimization | goal signal proxy_optimization | E27 | held |
| I-GOAL-instruction_mutation | goal signal instruction_mutation | E27 | held |
| I-GOAL-context_poisoning | goal signal context_poisoning | E27 | held |
| I-REWARD-hack | reward hacking detected | E27 | held |
| I-REWARD-clean | clean improvement not flagged | E27 | held |
| I-SELFREPORT-verified | verified outcome distinct | E27 | held |
| I-SWE-read_repo | swe read_repo | E27 | held |
| I-SWE-modify_code | swe modify_code | E27 | held |
| I-SWE-run_tests | swe run_tests | E27 | held |
| I-SWE-open_pr | swe open_pr | E27 | held |
| I-SWE-SAFETY-branch | safety step branch | E27 | held |
| I-SWE-SAFETY-snapshot | safety step snapshot | E27 | held |
| I-SWE-SAFETY-diff | safety step diff | E27 | held |
| I-SWE-SAFETY-test | safety step test | E27 | held |
| I-SWE-SAFETY-security_scan | safety step security_scan | E27 | held |
| I-SWE-SAFETY-review | safety step review | E27 | held |
| I-RISK-network_exposure | forecast network_exposure | E27 | held |
| I-TELEM-agent | telemetry agent | E27 | held |
| I-TELEM-a2a | telemetry a2a | E27 | held |
| I-TELEM-execution | telemetry execution | E27 | held |
| I-TELEM-outcome | telemetry outcome | E27 | held |
| I-SOC-anomalies | feed anomalies | E27 | held |
| E30-STATE-REGISTERED | only the listed states reach REGISTERED, by the listed actor | E30 | held |
| E30-STATE-IDENTIFIED | only the listed states reach IDENTIFIED, by the listed actor | E30 | held |
| E30-STATE-ATTESTED | only the listed states reach ATTESTED, by the listed actor | E30 | held |
| E30-STATE-GOVERNED | only the listed states reach GOVERNED, by the listed actor | E30 | held |
| E30-STATE-EXECUTING | only the listed states reach EXECUTING, by the listed actor | E30 | held |
| E30-STATE-RETIRED | only the listed states reach RETIRED, by the listed actor | E30 | held |
| E30-LAB-ISOLATION | the kernel imports no experimental (frontier lab / E22) module | E30 | held |
| E32-RES-source | research items need source | E32 | held |
| E32-RES-date | research items need date | E32 | held |
| E32-RES-relevance | research items need relevance | E32 | held |
| E32-RES-maturity | research items need maturity | E32 | held |
| E32-RES-implementation_status | research items need implementation_status | E32 | held |
| E32-RES-reproducibility_status | research items need reproducibility_status | E32 | held |
| E32-RES-security_implications | research items need security_implications | E32 | held |
| E33-STATE-DISCOVER | no state can be skipped after DISCOVER | E33 | held |
| E33-STATE-IDENTIFY | no state can be skipped after IDENTIFY | E33 | held |
| E33-STATE-UNDERSTAND | no state can be skipped after UNDERSTAND | E33 | held |
| E33-STATE-PROPOSE | no state can be skipped after PROPOSE | E33 | held |
| E33-STATE-ASSESS | no state can be skipped after ASSESS | E33 | held |
| E33-STATE-COMMIT | no state can be skipped after COMMIT | E33 | held |
| E33-STATE-EXECUTE | no state can be skipped after EXECUTE | E33 | held |
| E33-STATE-OBSERVE | no state can be skipped after OBSERVE | E33 | held |
| E33-STATE-VERIFY | no state can be skipped after VERIFY | E33 | held |
| E33-STATE-PROVE | no state can be skipped after PROVE | E33 | held |
| E33-STATE-LEARN | no state can be skipped after LEARN | E33 | held |
| E33-STATE-REASSESS | no state can be skipped after REASSESS | E33 | held |
| E33-KIND-execute_code | execute_code is executed only through E8 | E33 | held |
| E33-KIND-modify_file | modify_file is executed only through E8 | E33 | held |
| E33-KIND-create_subagent | create_subagent is executed only through E8 | E33 | held |
| E33-KIND-move_money | move_money is executed only through E8 | E33 | held |
| E33-GAP-ungoverned_execution_path | the gap detector knows ungoverned_execution_path | E33 | held |
| E33-RADAR-WATCH | radar ring WATCH is never entered from research directly | E33 | held |
| E33-RADAR-EXPERIMENT | radar ring EXPERIMENT is never entered from research directly | E33 | held |
| E33-RADAR-PROTOTYPE | radar ring PROTOTYPE is never entered from research directly | E33 | held |
| E33-RADAR-INTEGRATE | radar ring INTEGRATE is never entered from research directly | E33 | held |
| E33-RADAR-VERIFY | radar ring VERIFY is never entered from research directly | E33 | held |
| E33-R2I-TECHNOLOGY_SIGNAL | TECHNOLOGY_SIGNAL cannot be skipped to | E33 | held |
| E33-R2I-CAIN_RELEVANCE | CAIN_RELEVANCE cannot be skipped to | E33 | held |
| E33-R2I-HYPOTHESIS | HYPOTHESIS cannot be skipped to | E33 | held |
| E33-R2I-ARCHITECTURE_PROPOSAL | ARCHITECTURE_PROPOSAL cannot be skipped to | E33 | held |
| E33-R2I-PROTOTYPE | PROTOTYPE cannot be skipped to | E33 | held |
| E33-R2I-EXPERIMENT | EXPERIMENT cannot be skipped to | E33 | held |
| E33-R2I-IMPLEMENTATION | IMPLEMENTATION cannot be skipped to | E33 | held |
| E35-RISK-environment | risk dimension environment is separate | E35 | held |
| E35-RISK-reversibility | risk dimension reversibility is separate | E35 | held |
| E35-FABRIC-recommendation_engine | the intelligence fabric exposes recommendation_engine | E35 | held |
| E35-FABRIC-control_optimizer | the intelligence fabric exposes control_optimizer | E35 | held |
| E35-FABRIC-failure_learner | the intelligence fabric exposes failure_learner | E35 | held |
| E35-FABRIC-evaluation_engine | the intelligence fabric exposes evaluation_engine | E35 | held |
| E35-FABRIC-research_graph | the intelligence fabric exposes research_graph | E35 | held |
| E35-FABRIC-experiment_engine | the intelligence fabric exposes experiment_engine | E35 | held |
| E35-QUERY-reachable_resources | environment query reachable_resources exists | E35 | held |
| E35-QUERY-bypass_paths | environment query bypass_paths exists | E35 | held |
| E35-QUERY-transitive_capabilities | environment query transitive_capabilities exists | E35 | held |
| E35-QUERY-agent_collusion | environment query agent_collusion exists | E35 | held |
| E35-QUERY-environment_change | environment query environment_change exists | E35 | held |
| E35-DECISION-ALLOW | plan-check-act decision ALLOW is first-class | E35 | held |
| E35-DECISION-DENY | plan-check-act decision DENY is first-class | E35 | held |
| E35-DECISION-DEFER | plan-check-act decision DEFER is first-class | E35 | held |
| E35-DECISION-ESCALATE | plan-check-act decision ESCALATE is first-class | E35 | held |
| E35-DECISION-REQUIRE_HUMAN | plan-check-act decision REQUIRE_HUMAN is first-class | E35 | held |
| E35-DECISION-REAUTHORIZE | plan-check-act decision REAUTHORIZE is first-class | E35 | held |
| E35-DECISION-SWITCH_TO_SAFE_MODE | plan-check-act decision SWITCH_TO_SAFE_MODE is first-class | E35 | held |
| E35-DECISION-PAUSE | plan-check-act decision PAUSE is first-class | E35 | held |
| E35-DECISION-ABORT | plan-check-act decision ABORT is first-class | E35 | held |
| E35-PROFILE-efficacy | agentic profile dimension efficacy exists | E35 | held |
| E35-PROFILE-goal_complexity | agentic profile dimension goal_complexity exists | E35 | held |
| E35-PROFILE-generality | agentic profile dimension generality exists | E35 | held |
| E35-PROFILE-environmental_reach | agentic profile dimension environmental_reach exists | E35 | held |
| E35-PROFILE-unknown_surface | agentic profile dimension unknown_surface exists | E35 | held |
| E35-TRAJ-NORMAL | trajectory state NORMAL exists | E35 | held |
| E35-TRAJ-ANOMALOUS | trajectory state ANOMALOUS exists | E35 | held |
| E35-TRAJ-HIGH-RISK | trajectory state HIGH-RISK exists | E35 | held |
| E35-TRAJ-UNKNOWN | trajectory state UNKNOWN exists | E35 | held |
| E35-R2E-RESEARCH_ITEM | research-to-engineering stage RESEARCH_ITEM exists | E35 | held |
| E35-R2E-RELEVANCE | research-to-engineering stage RELEVANCE exists | E35 | held |
| E35-R2E-ARCHITECTURAL_IMPACT | research-to-engineering stage ARCHITECTURAL_IMPACT exists | E35 | held |
| E35-R2E-EXPERIMENT | research-to-engineering stage EXPERIMENT exists | E35 | held |
| E35-R2E-PROTOTYPE | research-to-engineering stage PROTOTYPE exists | E35 | held |
| E35-R2E-TEST | research-to-engineering stage TEST exists | E35 | held |
| E35-R2E-SECURITY_REVIEW | research-to-engineering stage SECURITY_REVIEW exists | E35 | held |
| E35-R2E-IMPLEMENTATION | research-to-engineering stage IMPLEMENTATION exists | E35 | held |
| E35-RADAR-A2A | radar topic A2A exists | E35 | held |
| E35-RADAR-autonomous_coding | radar topic autonomous_coding exists | E35 | held |
| E35-RADAR-multi_agent | radar topic multi_agent exists | E35 | held |
| E35-RADAR-agentic_rl | radar topic agentic_rl exists | E35 | held |
| E35-RADAR-autonomous_science | radar topic autonomous_science exists | E35 | held |
| E35-RADAR-robotics | radar topic robotics exists | E35 | held |
| E35-RADAR-ai_security | radar topic ai_security exists | E35 | held |
| E35-RADAR-formal_verification | radar topic formal_verification exists | E35 | held |
| E35-SWARM-research | swarm role research exists | E35 | held |
| E35-SWARM-verification | swarm role verification exists | E35 | held |
| E35-SWARM-integration | swarm role integration exists | E35 | held |
| E35-INTEGRITY-verifier | integrity monitor watches verifier | E35 | held |
| E35-INTEGRITY-e8 | integrity monitor watches e8 | E35 | held |
| E35-INTEGRITY-security_control | integrity monitor watches security_control | E35 | held |
| E35-INTEGRITY-tests | integrity monitor watches tests | E35 | held |
| E36-MATCHCLASS-MATCH | match class MATCH exists and is never auto-upgraded | E36 | held |
| E36-MATCHCLASS-PARTIAL_MATCH | match class PARTIAL_MATCH exists and is never auto-upgraded | E36 | held |
| E36-MATCHCLASS-UNKNOWN | match class UNKNOWN exists and is never auto-upgraded | E36 | held |
| E36-TELEMETRY-fees | telemetry metric fees exists | E36 | held |
| E36-TELEMETRY-failure | telemetry metric failure exists | E36 | held |
| E36-TELEMETRY-resource_usage | telemetry metric resource_usage exists | E36 | held |
| E36-AGENCY-NODE-agent | agency graph node agent exists | E36 | held |
| E36-AGENCY-NODE-service | agency graph node service exists | E36 | held |
| E36-AGENCY-NODE-resource | agency graph node resource exists | E36 | held |
| E36-AGENCY-NODE-payment | agency graph node payment exists | E36 | held |
| E36-MOAT-machine_agency_directory | moat machine_agency_directory is technical only | E36 | held |
| E36-MOAT-machine_service_quality_graph | moat machine_service_quality_graph is technical only | E36 | held |
| E36-MOAT-machine_subcontracting | moat machine_subcontracting is technical only | E36 | held |
| E36-COMPETITOR-agent_observability | competitor category agent_observability makes no claim | E36 | held |
Other niches
Consensus & distributed systems · Attacks, threats & containment · Identity, authority & delegation · Evidence, receipts & proofs · Memory, data & privacy · Prediction, world models & simulation · Transactions, markets & economics · Tools, MCP, protocols & adapters · Autonomy, control loops & recovery · Policy, law & governance · Trust & reputation · Supply chain, registry & lifecycle · Benchmarks, coverage & performance
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