{
 "counts": {
  "BLOCKED": 1,
  "FAIL": 2,
  "NOT EVALUABLE": 1,
  "PARTIAL": 15,
  "PASS": 20
 },
 "decision": "NOT RELEASED",
 "gates": [
  {
   "class": "LOCAL",
   "evidence": "baseline.json",
   "id": "G01",
   "name": "E84 baseline reproducible",
   "note": "6 E84 tests pass; clean-copy receipt verifies (exit 0), tampered copy exit 40; same project, not a third party",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "baseline.json, governed/summary.json",
   "id": "G02",
   "name": "Existing governance reused without duplication",
   "note": "0 changed lines under cain/receipt, cain/action_commit, cain/identity_federation, cain/mcp_proxy.py, scripts/evolution84, cain/cain2027/e81, cain/cain2027/e80 since the E84 commit; E85 receipts pass the unmodified E84 verifier (62 checks)",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "docs/evolution-85/VERTICAL_AGI_ARCHITECTURE.md",
   "id": "G03",
   "name": "Intelligence architecture documented",
   "note": "component map with a status for each capability; a document, not an implementation",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/summary.json (providers, arms, routing)",
   "id": "G04",
   "name": "Model-agnostic reasoning interface",
   "note": "one interface drove 3 local models (qwen2.5-0.5b-instruct, qwen2.5-1.5b-instruct, smollm2-135m-instruct) and a deterministic tool; router selects on measured accuracy; no remote provider was exercised (no credential), so provider-neutrality is shown for local models only",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/learning_events.json, tests.json",
   "id": "G05",
   "name": "Persistent memory provenance",
   "note": "34 E85 tests incl. ledger: every item has source, evidence reference, status, creator; {'VERIFIED': 27} usable; signed hash-chained events",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/strategy_history.json",
   "id": "G06",
   "name": "Verified knowledge updates",
   "note": "18 strategy decisions, each with a validation measurement and an approver different from the proposer; 1 promoted, 17 rejected; untrusted/injected/held-out content quarantined in tests",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/rows.jsonl, eval/summary.json",
   "id": "G07",
   "name": "Cross-domain evaluation harness",
   "note": "100 held-out tasks, 10 families, 9 arms, code-computed truth with a second implementation; constructed tasks, not a public benchmark",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/tasks.json, eval/summary.json",
   "id": "G08",
   "name": "Held-out generalization tests",
   "note": "held-out seeds disjoint from train/validation (checked at run time and by the verifier); unseen-domain family: single 2/10, with transferred strategy 2/10. The gate is that the test exists and ran, not that transfer succeeded",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/summary.json (comparisons.B_learned)",
   "id": "G09",
   "name": "Learning improvement measurements",
   "note": "held-out: single 24/100, with promoted strategies 25/100 (delta +0.010, exact McNemar p=1.0); measured, but not a statistically significant improvement",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/summary.json",
   "id": "G10",
   "name": "Single-agent baseline",
   "note": "A_single 24/100 = 0.24 (Wilson 95% [0.1669, 0.3323]); floor 0.3",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "eval/summary.json",
   "id": "G11",
   "name": "Multi-agent collaboration comparison",
   "note": "comparison ran with cost and latency; result: C_specialist_verifier 0.24 (delta +0.000, p=1.0, 2.58x tokens); C_hierarchical 0.26 (delta +0.020, p=0.831812, 4.12x tokens); D_selfconsistency3 0.26 (delta +0.020, p=0.774414, 3.03x tokens)",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "verticals/summary.json, eval/summary.json",
   "id": "G12",
   "name": "Mission planning and decomposition",
   "note": "three fixed mission templates executed end to end; a model-written plan arm was measured (C_hierarchical 0.26); no dynamic decomposition engine was built or evaluated in this evolution",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "swarm/identities.json",
   "id": "G13",
   "name": "Persistent workforce identities",
   "note": "10000 Ed25519 identities registered and stable across re-open; these are records, not workers",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "swarm/stages.json",
   "id": "G14",
   "name": "Real worker execution measurements",
   "note": "real OS worker processes: [10, 50, 100, 250, 500]; 0 duplicate effects; 1,000/2,500/5,000 processes not run; concurrent model inference measured separately = 1",
   "status": "FAIL"
  },
  {
   "class": "LOCAL",
   "evidence": "endurance/endurance.json",
   "id": "G15",
   "name": "Long-running mission recovery",
   "note": "1 h actual wall clock (3600.0 s), 11 worker crashes recovered, 14400 tasks, 0 duplicate effects; 6/24/72 h and host reboot not run",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/lab.json",
   "id": "G16",
   "name": "Delegation attenuation",
   "note": "scope escalation, undelegated capability, wrong agent, expired and revoked chains refused before any decision; chain re-checked offline by the E84 verifier",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "clawx/clawx.json, tests.json",
   "id": "G17",
   "name": "Tenant isolation",
   "note": "tenant A's evidence refused by tenant B's resource and enforcement point; evidence store cross-tenant reads refused (24 refusals, 0 leaks); one host",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "mcp/integration.json",
   "id": "G18",
   "name": "Live MCP enforcement integration",
   "note": "the unmodified MCP interceptor ran in a sandboxed dev instance in front of E85 execution: 9/9 expectations met. The hosted production proxy was not changed and does not emit these receipts",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/package_local",
   "id": "G19",
   "name": "Effect-bound E84 receipts",
   "note": "receipt binds action, delegation, policy, authorization, enforcement, execution and the resource's signed read-back; altering the observation digest is rejected (exit 40)",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/summary.json (remote_host), governed/package_remote",
   "id": "G20",
   "name": "External resource observation",
   "note": "resource ran on a second host (machine 1e54e16d7b5b), key generated there, observation verified, everything removed afterwards; same administrative domain, not a third-party system; the kill switch is not attached at the remote resource",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/package_local",
   "id": "G21",
   "name": "Standalone receipt verification",
   "note": "E84 verifier (imports no CAIN code) run with python -I from a copy: 62 checks, 0 failed",
   "status": "PASS"
  },
  {
   "class": "SIMULATED",
   "evidence": "governed/package_local/receipt.json",
   "id": "G22",
   "name": "Independent witness readiness",
   "note": "checkpoints are cosigned by an operator-run witness (SIMULATED_LOCAL) with consistency checks; independent cosignatures: 0. No independently administered witness exists",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "swarm/stages.json, endurance/endurance.json",
   "id": "G23",
   "name": "Global kill switch",
   "note": "GLOBAL kill stopped every worker in 5 stages (up to 500 processes) and at the end of the 1 h run; a new action afterwards is DENIED; the kill is a signed chained event",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/lab.json, tests.json",
   "id": "G24",
   "name": "Tenant and swarm kill switch",
   "note": "all ten scopes block their own target and nothing else (tests); TENANT, SWARM, MISSION, TOOL, CAPABILITY, ORG, AGENT, RESOURCE, DELEGATION kills refused new actions in the lab",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "swarm/stages.json, governed/lab.json, endurance/endurance.json",
   "id": "G25",
   "name": "Worker fencing and revocation",
   "note": "agents revoked before start completed 0 tasks; pre-kill grants stay refused after reinstate (STALE_GRANT_EPOCH); 5 mid-run revocations all stopped their process; 0 duplicate effects",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "swarm/stages.json, governed/summary.json",
   "id": "G26",
   "name": "Kill-switch latency benchmark",
   "note": "measured: in-process denial p95 0.982 ms after engage; across processes, slowest worker stop 5373.96 ms from the kill request at up to 500 workers; latest in-flight commit 5215.49 ms after the engage transaction; one host, shared file, no network propagation measured. The 1000 ms target is met at <=100 workers, not at 500.",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "endurance/endurance.json",
   "id": "G27",
   "name": "Multi-agent endurance benchmark",
   "note": "1 h completed (3600.0 s actual, 24 worker processes over the run, 120 governed receipts); 6 h, 24 h and 72 h not run; deterministic tasks, no model calls in the endurance run",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "clawx/clawx.json",
   "id": "G28",
   "name": "ClawX evidence persistence",
   "note": "21 records (15 receipts) persisted idempotently in a local hash-chained store; this is not the deployed ClawX service",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "clawx/clawx.json",
   "id": "G29",
   "name": "ClawX tenant-isolated access",
   "note": "3 tenants; 24 cross-tenant attempts refused, 0 leaks; public view carries digests only; local store, no network interface or deployment",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "verticals/*/result.json",
   "id": "G30",
   "name": "Three vertical prototypes",
   "note": "evidence_pack: precision 1.0, recall 1.0 on 12 labelled items; fabrication_audit: precision 1.0, recall 0.7 on 20 labelled items; mcp_tool_review: precision 0.8889, recall 0.8 on 20 labelled items. Deterministic engines, fixtures written for this evolution; not real-world precision and not model reasoning",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "scripts/evolution85/run_verticals.py, docs/evolution-85/COMMERCIALIZATION_PLAN.md",
   "id": "G31",
   "name": "Customer-facing demonstration",
   "note": "a runnable demonstration and a customer explanation exist; no customer has seen it",
   "status": "PARTIAL"
  },
  {
   "class": "-",
   "evidence": "docs/evolution-85/COMMERCIALIZATION_PLAN.md",
   "id": "G32",
   "name": "Commercial readiness",
   "note": "offer, pricing hypotheses, pilot proposal and onboarding checklist are written; no paid assessment, pilot or payment resulted from this evolution, so there is no market validation",
   "status": "PARTIAL"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/lab.json, docs/evolution-85/THREAT_MODEL.md",
   "id": "G33",
   "name": "Security and threat-model review",
   "note": "33/33 adversarial scenarios refused; threat model written; all testing by the same project, no independent review",
   "status": "PARTIAL"
  },
  {
   "class": "-",
   "evidence": "replication.json",
   "id": "G34",
   "name": "Reproducible clean-environment verification",
   "note": "replication.json missing: no clean clone on a second host was recorded",
   "status": "NOT EVALUABLE"
  },
  {
   "class": "LOCAL",
   "evidence": "scripts/evolution85/docs_e85.py, verify_e85_offline.py",
   "id": "G35",
   "name": "Documentation accuracy",
   "note": "numeric documents are generated from the artifact files; the offline verifier checks the headline numbers in the final report against the raw rows",
   "status": "PASS"
  },
  {
   "class": "LOCAL",
   "evidence": "tests.json",
   "id": "G36",
   "name": "Regression testing",
   "note": "E85 34 passed; E84 6; E81 64; E80 30; 0 failed",
   "status": "PASS"
  },
  {
   "class": "-",
   "evidence": "-",
   "id": "G37",
   "name": "Independent evidence review",
   "note": "the offline verifier is written by the same project; no independent reviewer, witness or auditor has examined this evidence",
   "status": "BLOCKED"
  },
  {
   "class": "-",
   "evidence": "this matrix",
   "id": "G38",
   "name": "Production release readiness",
   "note": "not ready: no remote model result, no independent witness or review, 1 h endurance only, the hosted MCP proxy is not integrated, nothing is deployed. Decision: NOT RELEASED",
   "status": "FAIL"
  },
  {
   "class": "LOCAL",
   "evidence": "governed/lab.json",
   "id": "E84-G38",
   "name": "E84 gap: kill switch and bypass path",
   "note": "kill switch: implemented and enforced at decision, enforcement and resource (was missing). Bypass: the resource refuses any call without pinned enforcement evidence; a direct file write is DETECTED by the seal audit; a sandboxed worker cannot open the store. Not prevented: a same-user process outside a sandbox can still write the file",
   "status": "PARTIAL"
  }
 ],
 "note": "E84-G38 is listed for traceability and is counted.",
 "schema": "cain2027.e85.acceptance.v1"
}