{"id":"model-stacking","text":"Multi-pass agent pattern: Model A generates candidates → TMS records with provenance → Review critiques (machine + human) → Model B receives validated beliefs → Model B derives new beliefs → Review critiques derivations → Repeat. Each level is a full model pass with fresh context and critique pipeline as quality gate","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":[{"type":"SL","antecedents":["hybrid-tms","derive-then-review"],"outlist":[],"label":""}],"dependents":[],"metadata":{},"explanation":{"steps":[{"node":"model-stacking","truth_value":"IN","reason":"SL justification valid","antecedents":["hybrid-tms","derive-then-review"],"label":""},{"node":"hybrid-tms","truth_value":"IN","reason":"SL justification valid","antecedents":["ftl-reasons-is-tms","llm-as-problem-solver"],"label":""},{"node":"ftl-reasons-is-tms","truth_value":"IN","reason":"SL justification valid","antecedents":["tms-doyle-1979"],"label":""},{"node":"tms-doyle-1979","truth_value":"IN","reason":"premise"},{"node":"llm-as-problem-solver","truth_value":"IN","reason":"SL justification valid","antecedents":["tms-doyle-1979"],"label":""},{"node":"tms-doyle-1979","truth_value":"IN","reason":"premise"},{"node":"derive-then-review","truth_value":"IN","reason":"SL justification valid","antecedents":["hybrid-tms"],"label":""},{"node":"hybrid-tms","truth_value":"IN","reason":"SL justification valid","antecedents":["ftl-reasons-is-tms","llm-as-problem-solver"],"label":""},{"node":"ftl-reasons-is-tms","truth_value":"IN","reason":"SL justification valid","antecedents":["tms-doyle-1979"],"label":""},{"node":"tms-doyle-1979","truth_value":"IN","reason":"premise"},{"node":"llm-as-problem-solver","truth_value":"IN","reason":"SL justification valid","antecedents":["tms-doyle-1979"],"label":""},{"node":"tms-doyle-1979","truth_value":"IN","reason":"premise"}]}}