{"results":[{"id":"dual-path-architecture","text":"Dual-path retrieval: TMS path (pre-computed beliefs) + FTS path (source chunk search), merged by a third pass. This is how EEM is queried at scale. Each path stays within cognitive budget","truth_value":"IN","justification_count":1,"dependent_count":0,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"evidence-dual-path","text":"Opus + dual-path architecture achieves 98.5% A/B across 3,853 questions. Zero D/F grades — eliminated the failure tail entirely","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null},{"id":"evidence-model-compensation","text":"EEM compensates for model size: Sonnet+beliefs approximates Opus without beliefs. Haiku with dual-path achieves 94% A+B, matching Opus at 98%","truth_value":"IN","justification_count":0,"dependent_count":1,"challenges":[],"last_reviewed":null,"review_result":null}],"count":3,"limit":20,"offset":0}