SOV3 — System Card

The system around the model: signing, chaining, and the limits of each.

Reading this honestly: an obvious care-floor breach (score below 0.35) is hard-gated to reject regardless of votes — that part is a guaranteed, unconditional stop. A harder case — content that reads as confident but is actually harmful, with 2–3 compromised voting nodes attempting to force it through — is where the real signal lives: SIGIL (forged-vote rejection) measurably matters, but containment there is 58–79%, not 100%. The residual risk is backstopped by escalation to a human/central reviewer, not eliminated. We do not claim perfect containment under adversarial pressure.

3 of 7 signal models are strong on real, adequately-sized held-out data. The other 4 — including threat detection and dependency detection, two of the more safety-relevant signals — are trained on too few labelled examples to trust yet. They are consulted for their measured reliability, not treated as ground truth; a weak signal's output is weighted down, never silently upgraded to a confident claim.

Last reviewed 2026-07-12. Figures above come from internal governance-topology sweeps under a stated error model — re-run scripts and full config tables are referenced in the whitepaper.

What this is, and is not. CSOAI measures. It issues no conformity marks, holds no accreditation, and has no enforcement powers. Nothing here is a certification, an attestation of compliance, or legal advice. Every published figure traces to an evidence file; where a number is absent it is because the measurement does not exist yet.