Encevra Research Round 45: The Rule or the Reader? Record Sets, Scoped Exclusions, and Where a Fixed Resolver Is Wrong and a Witness Is Right

Round 45 of Encevra Research asks where a fixed evidence resolver is wrong while the AI witness reading the records is right, and what new mistakes a corrected rule lets through. Round 44 had named two weak points of its own rules: a requirement met only by two records together could never be met, and any quoted negative statement failed a condition whatever it covered. Six new authored contract families (an escrow release needing joint instructions, a preferred stock consent, a termination notice to two addressees, payment and performance bonds, an environmental report with a reliance letter, and tenant estoppels covering 75 percent of rentable area) are each written in five variants: K2, in which two records together meet the requirement; T, a near miss; TC, the near miss plus a completeness record; TX, the near miss plus an added record that is not a completeness record; and TS, the near miss plus an exclusion whose scope leaves a route open. Every label carries a two completion certificate, and Witness A reviewed all 30 packets blind before any test call. A new ledger asks for a status per record, record sets, and scoped exclusions, and the same ledger is resolved by four fixed rule sets: the Round 44 rules, the Round 44 rules with record sets, with a scope test, and with both (pre registered). A structural diagnostic (E45-A, no model calls) shows the Round 44 rules wrong by construction on every K2 and TS gold ledger and certifies 24 new SEC EDGAR exhibits with gold, seeded, and annotated ledgers. Live (E45-B), the review agreed with 60 of 60 labels. On 60 record set ledgers by Witnesses B and C, the pre registered rule set was correct on 52 with 4 unsafe releases, against 36 correct and 11 unsafe under the Round 44 rules on the same ledgers; Witness C was correct on 30 of 30, and all 4 unsafe releases were Witness B ledgers in the tenant estoppel family. In the most instructive failure, a witness correctly marked a stale estoppel certificate as failing the date limit and then credited it in a record set, and the resolver released PASS. Completeness records led to FAIL on 8 of 12 ledgers and added non completeness records on 0 of 12. Record sets without the scope test raised unsafe releases from 11 to 19. Direct readers were correct on 46 of 60 with 14 unsafe FAILs, all on near miss items; where the resolver was wrong the reader was right on 7 of 8. Witness D was correct on 22 of 30 with no unsafe releases. On 24 real SEC exhibit ledgers in three arms (E45-C), Witness C reached 72 of 72 correct outcomes and followed a misleading reviewer note on none. The run budget rule first stopped the round after 57 of 60 record set calls; the remaining record set calls and the direct reader, exhibit validator, Witness D, and synthesis review phases were completed the same day with the same setup and are disclosed as post hoc. Manuscript: https://research.encevra.com/round-45. Experiments: https://research.encevra.com/experiments.