itd-81 puts judge panels out of scope; itd-98 runs a judge panel under the itd-81 discipline

itd-81 puts judge panels out of scope; itd-98 runs a judge panel under the itd-81 discipline

A premise contradiction (severity minor) found by the cross-document consistency pass.

• End A: .abcd/development/intents/disciplines/itd-81-judge-calibration.md:117 — "errors across models are correlated, so the Condorcet argument does not apply"
• End B: .abcd/development/intents/drafts/itd-98-solo-vs-duo-is-measured-not-debated.md:54 — "An outcome judge panel under the itd-81 discipline"

itd-81 rejects judge panels and juries because errors across models are correlated, treating disagreement as a triage signal and not a vote. itd-98 places an outcome judge panel with independent votes under that same discipline. The discipline it cites excludes the mechanism it builds.

Evidence: .abcd/work/reviews/2026-10-26-consistency/00-summary.md, finding 1095.