{"id":"model-stacking-evidence","text":"Multi-pass agent pattern observed: Model A generates candidates, TMS records with provenance, review critiques (machine + human), Model B receives validated beliefs, Model B derives new beliefs. Demonstrated in expert-build pipeline where Sonnet summarizes sources, then Sonnet derives, then Sonnet reviews — each pass gets fresh context with the TMS as the persistent layer between passes.","truth_value":"IN","source":"repo:beliefs-pi/entries/2026/05/06/model-stacking-tms-as-the-layer-between-models.md","source_url":"","source_hash":"","justifications":[],"dependents":["model-stacking"],"metadata":{},"created_at":"","updated_at":"","reviewed_at":"","verified_at":"","retracted_at":"","explanation":{"steps":[{"node":"model-stacking-evidence","truth_value":"IN","reason":"premise"}]}}