Composition Before Capability: Six Noetis Composition Topologies Compared on Release Safety, Abstention, and Calls per Decision

Holding the evidence questions fixed, which way of composing four witnesses into one release decision gives the fewest unsafe releases and the best abstention per model call: a single witness, a forced majority, extract then deterministic resolve, a role specialized pipeline, critique and revision, or a disagreement routed hybrid?

Compares six ways of composing four witnesses into one contract audit decision: single witness, forced majority, extract then deterministic resolve, role specialized pipeline, critique and revision, and a disagreement routed hybrid, scored on accuracy, unsafe releases, abstention calibration, and model calls per decision. An exact diagnostic (E40-A, 0 model calls) shows a forced majority releases 108/243 states unsafely, the same as one witness, and holds 0/16 HOLD-truth states when witnesses do not abstain; disagreement routing raises the fewest faults needed for an unsafe release to 2. Live, 330 calls over 17 authored packets (E40-B) and 16 real SEC EDGAR exhibits (E40-C) with Witness A (Max reasoning), Witness B, Witness C, and Witness D produced 0 unsafe releases in every topology. The one single witness unsafe answer (Witness B on N01) was removed by every multi-look topology, and the one composed error (a false hold on X24) was introduced by a validation stage that rewrote a correct ledger. Proposes five named propositions and a Rounds 41 to 50 path toward Theory v1; no production system changed.

• F40.1 (deterministic, E40-A): over 243 verdict states a forced majority releases 108 unsafely, the same as one witness, while raising the fewest faults for an unsafe release from 1 to 2; a 3-of-4 quorum releases 36 with 126 false holds.
• F40.2 (deterministic, E40-A): with witnesses that never return HOLD, single and majority topologies hold 0/16 HOLD-truth states and a 3-of-4 quorum holds 6/16.
• F40.3 (deterministic, E40-A): span checked extract then resolve releases 4/12 fault states unsafely (8/15 without the span check); disagreement routing limits unsafe releases to the 4/48 states with identical misreadings and needs 2 faults.
• F40.4 (live, E40-B and E40-C): across 33 items and 330 calls every topology made 0 unsafe releases; accuracy was 33/33 for five topologies and 32/33 for the role pipeline.
• F40.5 (live): Witness B alone released PASS on N01, two same-date lender letters that grant and decline one approval; majority, extraction, routed, and critique topologies all held it.
• F40.6 (live, E40-C): on X24 the validator added five covenants as conditions to a correct ledger and the decider held an instrument effective on its face, the only composed error.

• E40-A Exact composition topology enumeration Executed (diagnostic)
• E40-B Live six-topology benchmark on authored packets Executed (diagnostic)
• E40-C Live six-topology benchmark on real SEC exhibits Executed (bounded diagnostic)

• H40.1 A forced majority does not reduce unsafe releases when witnesses do not abstain.
• H40.2 Separating extraction from decision with a span check removes fabricated quotes as a route to release.
• H40.3 Routing extractor disagreement to review raises the fewest faults for an unsafe release from one to two.
• H40.4 Each added sequential model stage can introduce an error the single stage did not make.
• H40.5 Without lens instructions, witnesses return HOLD when the contract leaves a decisive conflict unresolved.

Research diagnostic and live benchmark only. Recommends, but does not adopt, a Noetis structure of two independent extractors, a deterministic span checked resolver, and disagreement routing to review. No production system, release gate, or Noetis behavior changed.

• On a hard pool selected for witness disagreement, with externally reviewed HOLD labels, do disagreement routed topologies keep their safety without excessive review load, and do flag only validators avoid the errors that rewriting validators introduce?

Builds on Round 39, Round 38, Round 37, Round 36, Round 35.