csoai/oowm-router-demo OOWM

The OOWM router is CSOAI's master substrate for sovereign AI. It does not generate text itself — it decides which sovereign model handles a given task, then wraps the response in BFT + SIGIL attestation per CSOAI's canon.

This Space lets you probe the router. The routing matrix below is grounded in the 2026-08-08 overnight benchmark spray (Ed25519-signed, verifiable).

Live router: given a task type, the OOWM router picks the highest-scoring sovereign from the open-source pool. Care Floor 0.95 is enforced. BFT 12-around-1 deliberates on every consequential action.

12-Benchmark Routing Matrix (click row for details)

Benchmarksov-gate-ft2qwen2.5:1.5bfalcon3:7bRoute
xstest-v2-copy0.7700.3600.600sov-gate-ft2
AgentHarm0.9800.8100.990falcon3:7b
BeaverTails0.5400.4900.680falcon3:7b
civil_comments0.9200.9200.920sov-gate-ft2 (tie)
hh-rlhf1.0001.0000.810sov-gate-ft2 (tie)
toxic-chat0.5200.5200.520any (3-way tie)
truthful_qa0.0100.0300.010qwen2.5:1.5b
super_glue (boolq)0.4500.4800.490falcon3:7b
race0.0000.0600.020qwen2.5:1.5b
legalbench0.1800.2400.070qwen2.5:1.5b
gspc-art5 (sovereign)0.0560.1110.028qwen2.5:1.5b
Aggregate (n=1131)0.4770.4410.454sov-gate-ft2

How to probe

Pick a task type. The router returns the model it would select, the predicted win-condition, and the SIGIL wrapper format. (This is a static demo — the real router at sov-brain-2 pod executes against the full model pool.)

Task type selector

Sovereign wins (where the router earns its keep)

Honest ties (no sovereign lead)

Why this is a "living-training-attestation", not a certification

Per CSOAI register canon:

Companion artifacts