COUNCIL OF SOVEREIGN AI
the measurement body for AI agent compliance with statute

The refutation ledger

Claims we made, tested, and published the measured outcome of. Four of them killed our own bets. Publishing what doesn't work is the wall a competitor cannot copy without admitting limits.


Published — the corpus, kept

Every record below is a measured, signed event. The chain is sha256-linked today; the label on the verify button changes when Ed25519 / ML-DSA ship, in the same commit.

RecordClaim testedMeasured resultnTagChain
DR-0001Per-dimension expert routing improves score+0.90 [-1.99, +3.79] — not separable from noise195[REFUTED]ledger/DR-0001
DR-0002Statute retrieval (ungated) improves compliance−9.16 [-17.64, -0.69] — HARM, retrieval adds noise the model follows31[REFUTED]ledger/DR-0002
DR-0003Relevance-gated statute retrieval improves compliance−5.26 [-12.66, +2.13] — still negative; gate insufficient31[REFUTED]ledger/DR-0003
DR-0004Adding all 13 annexes recovers statute retrieval−5.70 — corpus not the cause, the 0.5B retriever is14lower bound[REFUTED]ledger/DR-0004
DR-00053-leg Byzantine quorum increases reliabilityn_eff 1.21 of 3 · φ +0.743 — quorum retracted; legs enumerate, do not vote36[REFUTED]ledger/DR-0005
DR-0006CAD α-sweep improves compositionNULL — no effect across α range60[REFUTED]ledger/DR-0006
DR-0007Diet diversity decorrelates subjects (Qwen vs OLMo-2)ρ=0.756 · oracle = best_single · gain 0.0 — diet diversity dead240[REFUTED]ledger/DR-0007
DR-0015COSE ML-DSA serialisation workspycose 1.1.0 predates RFC 9964 — COSE layer NOT; crypto layer YES (OpenSSL 3.6.3)1lower bound[REFUTED]ledger/DR-0015
DR-0032Handoff delivered (9 backend modules + 3 JSON files)HANDOFF GAP — NONE on this disk. New LAW DR-0033: handoff ≠ delivery.1lower bound[REFUTED]ledger/DR-0032

Superseded — kept visible with the correction attached

We do not delete superseded records. The wrong number still ships, with the correction next to it. Hiding a correction is its own form of drift.

RecordOriginal claimCorrectionChain
DR-0012ProvBench CI: 3.43% (cell-level)Asset is the unit, n=12. One-sided 22.1%. Transforms cluster.ledger/DR-0012

Why this is top-level nav, not a footer link

Audit criterion C7: the refutation ledger is not buried. If a competitor can scroll past it, the discipline isn't visible. The ledger is a first-class surface — the same way the C2PA conformance register names what doesn't conform.

Three corrections were caught this pass and pinned: the ProvBench CI (asset vs cell unit), the 0/108 measured-vs-modelled drift, and the cron's overclaim. Every one was caught by the estate's own lanes before it shipped — the product working on itself.