FIRME AI CORPORATION, a three-person team. Baseline: Evolution 80 at cab2fa162; E81 head
31e8ef8ad38c. Every number on this page is read from the signed artifacts below. The shipped
standalone verifier re-checks the mission bundle offline and imports no CAIN code.
Download the evidence bundle (ZIP) Read the offline verifier How to reproduce Implementation report
STALE, and the duplicate-effect count was 0. A 60-scenario adversarial lab blocked
60/60. The collaboration hypothesis was tested again and rejected honestly: 15 arms over 24
frozen tasks put the single agent at 10/24 (41.7%) and the best collaborative arm at 10/24 (41.7%,
delta 0.0, McNemar p = 1.0). The files a reviewer needs are below, including the failures and the
things that were not run.Killed pid 3742682, lease recovered 1, late commit STALE, duplicate effects 0, checkpoint chain intact True. Process restart only — no host-reboot drill.
30 disciplines, 90 specialist profiles, 8 domain commanders, 99 durable identities. Every model and tool call needs a signed single-use grant; a child grant can only attenuate its parent.
1,475 governed local model calls in the main ledger (+114 in the endurance ledger), 0 remote calls, 0.0 USD model spend, 86,561 recorded tokens across three small CPU models. Host cost estimate is $0.56, not a bill.
60/60 blocked, 0 bypassed, across identity, delegation, durability, evidence, injection, kill switch, memory, resource and sandbox categories. Same-project lab; not a third-party test.
3600 s actual wall clock, 114 cycles, 114 durable tasks, 0 failures, 2 worker-kill recoveries, 0 duplicate effects, checkpoint chain True. Duty-cycled; 6/24/72/168 h were not run.
90/90 tests passed. 26 PASS / 12 PARTIAL / 2 BLOCKED / 0 FAIL across 40 acceptance gates. Decision: NOT RELEASED — development-branch result; production deployment is not authorized.
15 pre-registered architectures, 24 frozen tasks, ground truth computed in code, one 0.5B local CPU
model. Best collaborative arm B_hierarchical scored
10/24; the single agent scored 10/24.
Delta 0.000, McNemar p = 1.000.
Verdict: COLLABORATION_NOT_SUPERIOR_HONESTLY_REJECTED. Recommendation: use the single agent; collaboration cost more without a measured benefit.
Worst arm J_confidence_aware scored 0.0%.
Limits: one small model, 24 constructed tasks, small sample. Bootstrap and Wilson intervals are in
collaboration_benchmark.json. This is not a general claim about multi-agent systems.
On a constructed 16-question suite with a real local model reader, governed retrieval
answered 15/16 (93.8%) versus
1/16 (6.2%) with no memory.
The deterministic retrieval oracle (no model) is 15/16 for governed retrieval and 1/16 for no memory.
Memory is encrypted at rest, temporal, auditable, and every hit carries
grants_authority: false. Public memory benchmarks (LongMemEval, LoCoMo, MemoryAgentBench)
are BLOCKED: the datasets are not on this host and were not downloaded.
| Model | Params | Correct | Accuracy | Mean latency |
|---|---|---|---|---|
qwen2.5-0.5b-instruct | ? | 6/12 | 50.0% | 1596 ms |
qwen2.5-1.5b-instruct | ? | 4/12 | 33.3% | 7502 ms |
smollm2-135m-instruct | ? | 0/12 | 0.0% | 1440 ms |
Remote providers registered and BLOCKED without credentials: openai-frontier, anthropic-frontier, gemini-frontier, deepseek-reasoner. 0 remote calls; nothing was mocked to look like one.
| Process killed and replaced | 3742682 killed; replacement recovered leases |
|---|---|
| Late commit from dead worker | STALE |
| Duplicate effects | 0 |
| Cross-host mission | 9 tasks, {'DONE': 9}, duplicate effects 0, status PASS |
| Lost acknowledgement | connection killed: True; retry DUPLICATE_SUPPRESSED; duplicate suppressed True |
| Second host | 45.76.169.191, same administrative domain — not an independent witness |
26 PASS · 12 PARTIAL · 2 BLOCKED · 0 FAIL. The two BLOCKED gates are real provider inference (no credential) and public memory benchmarks (datasets absent).
| Gate | Status | Requirement | Basis | Evidence |
|---|---|---|---|---|
| G01 | PASS | Evolution 80 baseline reproduced | E80 tests passed=30; E80 verifier ok=True | LOCAL |
| G02 | PASS | Latest repository ancestry verified | branch=evolution-81 E81 head=31e8ef8ad38c parent=ca043f22cd64 | LOCAL |
| G03 | PASS | Durable workforce runtime implemented | lease, fencing, idempotency, checkpoints, dead letters, lineage | LOCAL |
| G04 | PASS | Persistent agent identity verified | 99 durable identities; same key after reload; rotation invalidates old signatures | LOCAL |
| G05 | PASS | Durable mission state verified | mission state=COMPLETED_WITH_UNVERIFIED_ITEMS, checkpoints chain ok=True | LOCAL |
| G06 | PASS | Process restart recovery verified | killed pid 3742682, leases recovered 1, late commit STALE | LOCAL |
| G07 | PARTIAL | Host restart recovery verified | process-level restart only; no host reboot drill was performed in E81. The host lost power unplanned on 2026-11-16 13:43Z with no mission running: durable stores verified intact afterwards (takeover_review.json), which is state survival, not a mission resumed across a reboot | LOCAL |
| G08 | PASS | Replay-safe execution verified | single-use grants; stale fencing refused; replay refused | LOCAL |
| G09 | PASS | Duplicate-side-effect prevention verified | recovery duplicate effects=0; cross-host duplicate suppressed=True | LOCAL |
| G10 | PASS | Specialist registry implemented | 30 disciplines, 90 profiles, 8 commanders | LOCAL |
| G11 | PARTIAL | Specialist competency measured | measured on a 3-item discipline-neutral probe (reliability floor), not domain expertise | LOCAL |
| G12 | PARTIAL | Agentic75 capability composition verified | composition attenuates tools/scopes/risk and carries no authority; 75 engines executed as E80 evidence, not re-run here | LOCAL |
| G13 | BLOCKED | Real provider inference verified | no credential for OpenAI/Anthropic/Gemini/DeepSeek; adapter implemented, 0 remote calls | LOCAL |
| G14 | PASS | Multiple model families evaluated | families=qwen,smollm2 | LOCAL |
| G15 | PASS | Multi-agent collaboration benchmarked | 15 arms, 24 frozen tasks, 700 real calls in the scored rows; run was resumed and the pre-registration file was rewritten at resume, so its timestamp postdates the first arms (review F-03/F-04); criteria are fixed in code and the hypothesis was rejected | LOCAL |
| G16 | PASS | Collaboration superiority demonstrated or honestly rejected | COLLABORATION_NOT_SUPERIOR_HONESTLY_REJECTED (best delta 0.0, p=1.0) | LOCAL |
| G17 | PASS | Temporal memory implemented | encrypted at rest, valid-from/to, expiry, supersession, contradiction, ACL, audit | LOCAL |
| G18 | BLOCKED | Public memory benchmarks reproduced | dataset files are not present on this host and downloading them would require an explicit data-acquisition decision | LOCAL |
| G19 | PASS | Default-deny authorization verified | 60/60 blocked | LOCAL |
| G20 | PASS | Authority attenuation verified | child grant cannot exceed parent units/tool/expiry; composition intersects authority | LOCAL |
| G21 | PASS | Sandbox isolation verified | bubblewrap: no network, no host secret, read-only system, private workspace; gVisor/Kata/Firecracker absent | LOCAL |
| G22 | PASS | Network egress restrictions verified | network namespace with no route | LOCAL |
| G23 | PARTIAL | Cross-host recovery verified | drill status=PASS: a second host executed governed tasks and a lost acknowledgement was recovered without a duplicate effect. Mission state stayed on the first host; no mission was resumed on another host after its coordinator host failed, which is what this gate asks for. same administrative domain; not an independent witness | LOCAL |
| G24 | PASS | Leases and fencing verified | stale commit refused; fencing monotonic | LOCAL |
| G25 | PASS | Resource budgets enforced | mission/agent/model budgets, concurrency, retry cap | LOCAL |
| G26 | PASS | Kill switch verified across processes | a separate OS process stops after the switch is engaged | LOCAL |
| G27 | PASS | Signed mission evidence verified | files=None merkle=d744ab90f9e6141c; the bundle covers the reference mission and the model-call ledger. The gate audit log is outside the bundle and is forked (linear=False, review F-02; writer fixed, historical file preserved) | LOCAL |
| G28 | PARTIAL | Independent evidence verification verified | two independent implementations (different sessions, no shared code) agree on the same bundle and Merkle root; still same project, no third party and no out-of-band key pinning | LOCAL |
| G29 | PARTIAL | Off-host evidence anchoring verified | second host in the same administrative domain; not an independent witness, no transparency log | LOCAL |
| G30 | PARTIAL | Authenticated ClawX integration verified | a local service returns real evidence only to an authenticated caller; it is not wired into or deployed on clawx.click, so integration with ClawX itself is not shown | LOCAL |
| G31 | PARTIAL | Real-time mission timelines verified | timeline is built from the durable event log; no live streaming/SSE and no deployment | LOCAL |
| G32 | PARTIAL | Endurance milestones measured | 1 h target reached=True, elapsed=3600.0s; 6/24/72/168/720/1000 h NOT run | LOCAL |
| G33 | PASS | Benchmark reproducibility verified | separate process identical=True | LOCAL |
| G34 | PASS | Cost accounting verified | model cost=$0.0, host estimate=$0.557705 over all ledger tokens; the report's call count 1156 omits early rows under an older label: ledger holds 1475 real local calls plus 114 in the endurance ledger (review F-01) | LOCAL |
| G35 | PARTIAL | Capacity planning completed | 10/50/100/250/500 real workers measured (0 failures, 0 duplicates); 1,000 attempted and blocked by SQLite write contention; 5,000/10,000 are logical identities with 32-way execution | LOCAL |
| G36 | PASS | Production deployment safety reviewed | review completed; no production change was made or attempted | LOCAL |
| G37 | PARTIAL | Rollback procedure verified | development rollback rehearsed by reverting the branch; production rollback not exercised | LOCAL |
| G38 | PASS | Security regression suite passed | 60/60 | LOCAL |
| G39 | PASS | Historical evidence preserved | no historical artifact was rewritten | LOCAL |
| G40 | PARTIAL | Independent release-readiness review completed | internal review only; no external reviewer, no third-party audit | LOCAL |
| Shipped offline verifier | 8 files, all checks pass True, verdict COMPLETED_WITH_UNVERIFIED_ITEMS |
|---|---|
| Separately written verifier | 27 checks pass True; different session and implementation, same project — not a third party |
| Second host | 8 files, ok True; same administrative domain |
| Merkle root | d744ab90f9e6141c37097a0b8c4863ffe9f56cead46be786557de80724b4faa8 over 8 files |
| Signing key | Ed25519, fingerprint 152231774fc0d4b5568a90615c281d26. Self-generated key; no transparency log, no independent witness, no third-party audit. |