{
  "built_at": "2026-11-08T19:36:43.457Z",
  "build_mode": "jev-scored",
  "plugin_version": "2.0.0-beta.82",
  "theo_frameworks": 426,
  "jev_model": "jev-1.14.0",
  "confidence_floor": 0.7,
  "floor_basis": "swept over evals/icm/cases/turns.json (12 labeled turns), argmax top-3 hit rate",
  "floor_hit_rate": 0.4166666666666667,
  "wall_ms": 47247,
  "jev_calls": 12,
  "input_tokens": 26299,
  "output_tokens": 1905,
  "estimated_cost_usd": 0.001104558,
  "cost_basis": "vendor-claimed rate, unverified",
  "rows": {
    "design-solution|*|*": [
      {
        "command": "/mos:find-analogies",
        "framework": "Four Lenses of Innovation",
        "score": 1,
        "confidence": 0.4,
        "source": "framework-matched"
      },
      {
        "command": "/mos:systems-thinking",
        "framework": "Systems Thinking",
        "score": 0.9,
        "confidence": 0.31,
        "source": "framework-matched"
      },
      {
        "command": "/mos:find-connections",
        "framework": "Usher's Model of Cumulative Synthesis",
        "score": 0.88,
        "confidence": 0.37,
        "source": "framework-matched"
      },
      {
        "command": "/mos:analyze-systems",
        "framework": "Systems Thinking",
        "score": 0.82,
        "confidence": 0.34,
        "source": "framework-matched"
      },
      {
        "command": "/mos:rs-experts",
        "framework": "Reverse Salient Analysis",
        "score": 0.81,
        "confidence": 0.29,
        "source": "framework-matched"
      },
      {
        "command": "/mos:bono",
        "framework": "Six Thinking Hats",
        "score": 0.78,
        "confidence": 0.16,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-explain",
        "framework": "Reverse Salient Analysis",
        "score": 0.65,
        "confidence": 0.02,
        "source": "framework-matched"
      },
      {
        "command": "/mos:rs-fetch",
        "framework": "Reverse Salient Analysis",
        "score": 0.63,
        "confidence": 0.05,
        "source": "framework-matched"
      },
      {
        "command": "/mos:hat-briefing",
        "framework": "Six Thinking Hats",
        "score": 0.31,
        "confidence": 0.53,
        "source": "framework-matched"
      }
    ],
    "explore|*|*": [
      {
        "command": "/mos:think-hats",
        "framework": "Six Thinking Hats",
        "score": 1.79,
        "confidence": 0.7,
        "source": "ground-truth"
      },
      {
        "command": "/mos:explore-opportunity",
        "framework": null,
        "score": 1.71,
        "confidence": 0.55,
        "source": "ground-truth"
      },
      {
        "command": "/mos:explore-domains",
        "framework": "Domain Selection",
        "score": 1.64,
        "confidence": 0.48,
        "source": "ground-truth"
      },
      {
        "command": "/mos:discover",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 1.58,
        "confidence": 0.37,
        "source": "ground-truth"
      },
      {
        "command": "/mos:bono",
        "framework": "Six Thinking Hats",
        "score": 1.47,
        "confidence": 0.2,
        "source": "ground-truth"
      },
      {
        "command": "/mos:splash",
        "framework": null,
        "score": 1.38,
        "confidence": 0.05,
        "source": "ground-truth"
      },
      {
        "command": "/mos:opportunities",
        "framework": null,
        "score": 1.37,
        "confidence": 0.05,
        "source": "framework-matched"
      },
      {
        "command": "/mos:explore-trends",
        "framework": "S-Curve Analysis",
        "score": 1.33,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:eureka",
        "framework": null,
        "score": 1.3,
        "confidence": 0.19,
        "source": "ground-truth"
      },
      {
        "command": "/mos:beautiful-question",
        "framework": "Beautiful Question Framework",
        "score": 1.27,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scout",
        "framework": null,
        "score": 1.17,
        "confidence": 0.08,
        "source": "ground-truth"
      },
      {
        "command": "/mos:futures",
        "framework": "Futures Wheel",
        "score": 1.17,
        "confidence": 0.08,
        "source": "ground-truth"
      },
      {
        "command": "/mos:eureka-portfolio",
        "framework": null,
        "score": 1.16,
        "confidence": 0.26,
        "source": "ground-truth"
      },
      {
        "command": "/mos:auto-explore",
        "framework": null,
        "score": 1.1,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:whitespace",
        "framework": "HSI Semantic Surprise Analysis Assistant",
        "score": 1.08,
        "confidence": 0.22,
        "source": "ground-truth"
      },
      {
        "command": "/mos:build-knowledge",
        "framework": "Ackoff Pyramid",
        "score": 0.87,
        "confidence": 0.33,
        "source": "ground-truth"
      },
      {
        "command": "/mos:trending-to-absurd",
        "framework": "Trending to the Absurd",
        "score": 0.81,
        "confidence": 0.32,
        "source": "ground-truth"
      },
      {
        "command": "/mos:new-surface",
        "framework": null,
        "score": 0.78,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:mos-reason",
        "framework": "The Pyramid Principle",
        "score": 0.72,
        "confidence": 0.34,
        "source": "ground-truth"
      },
      {
        "command": "/mos:research",
        "framework": "Hypothesis-Driven Problem Solving",
        "score": 0.71,
        "confidence": 0.24,
        "source": "ground-truth"
      },
      {
        "command": "/mos:mos",
        "framework": null,
        "score": 0.64,
        "confidence": 0.04,
        "source": "ground-truth"
      },
      {
        "command": "/mos:structure-argument",
        "framework": "The Pyramid Principle",
        "score": 0.54,
        "confidence": 0.18,
        "source": "ground-truth"
      },
      {
        "command": "/mos:ignite",
        "framework": null,
        "score": 0.51,
        "confidence": 0.25,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scenario-plan",
        "framework": "Scenario Planning",
        "score": 0.51,
        "confidence": 0.25,
        "source": "ground-truth"
      },
      {
        "command": "/mos:find-bottlenecks",
        "framework": "Reverse Salient Analysis",
        "score": 0.46,
        "confidence": 0.31,
        "source": "ground-truth"
      },
      {
        "command": "/mos:help",
        "framework": null,
        "score": 0.41,
        "confidence": 0.4,
        "source": "ground-truth"
      },
      {
        "command": "/mos:explore-futures",
        "framework": "Scenario Planning",
        "score": 0.39,
        "confidence": 0.4,
        "source": "framework-matched"
      },
      {
        "command": "/mos:qualify-opportunity",
        "framework": null,
        "score": 0.36,
        "confidence": 0.44,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-experts",
        "framework": "Reverse Salient Analysis",
        "score": 0.36,
        "confidence": 0.46,
        "source": "ground-truth"
      },
      {
        "command": "/mos:mva-option",
        "framework": null,
        "score": 0.35,
        "confidence": 0.48,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-explain",
        "framework": "Reverse Salient Analysis",
        "score": 0.35,
        "confidence": 0.48,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-thesis",
        "framework": "Reverse Salient Analysis",
        "score": 0.34,
        "confidence": 0.49,
        "source": "ground-truth"
      },
      {
        "command": "/mos:mva-brief",
        "framework": null,
        "score": 0.33,
        "confidence": 0.5,
        "source": "ground-truth"
      },
      {
        "command": "/mos:skill",
        "framework": null,
        "score": 0.33,
        "confidence": 0.51,
        "source": "ground-truth"
      },
      {
        "command": "/mos:operator",
        "framework": null,
        "score": 0.32,
        "confidence": 0.52,
        "source": "ground-truth"
      },
      {
        "command": "/mos:score-innovation",
        "framework": "HSI Semantic Surprise Analysis Assistant",
        "score": 0.32,
        "confidence": 0.52,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-fetch",
        "framework": "Reverse Salient Analysis",
        "score": 0.32,
        "confidence": 0.53,
        "source": "ground-truth"
      },
      {
        "command": "/mos:setup",
        "framework": null,
        "score": 0.31,
        "confidence": 0.52,
        "source": "ground-truth"
      },
      {
        "command": "/mos:leadership",
        "framework": "Adaptive Leadership",
        "score": 0.27,
        "confidence": 0.6,
        "source": "ground-truth"
      },
      {
        "command": "/mos:status",
        "framework": null,
        "score": 0.25,
        "confidence": 0.64,
        "source": "ground-truth"
      },
      {
        "command": "/mos:new-project",
        "framework": null,
        "score": 0.24,
        "confidence": 0.64,
        "source": "ground-truth"
      },
      {
        "command": "/mos:onboard",
        "framework": null,
        "score": 0.21,
        "confidence": 0.7,
        "source": "ground-truth"
      },
      {
        "command": "/mos:graph",
        "framework": null,
        "score": 0.16,
        "confidence": 0.74,
        "source": "ground-truth"
      },
      {
        "command": "/mos:suggest-next",
        "framework": null,
        "score": 0.09,
        "confidence": 0.86,
        "source": "ground-truth"
      },
      {
        "command": "/mos:show",
        "framework": null,
        "score": 0.08,
        "confidence": 0.86,
        "source": "ground-truth"
      }
    ],
    "find-bottleneck|*|*": [
      {
        "command": "/mos:find-bottlenecks",
        "framework": "Reverse Salient Analysis",
        "score": 1.94,
        "confidence": 0.91,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scientific-roadmap",
        "framework": "Scientific Roadmapping",
        "score": 1.6,
        "confidence": 0.4,
        "source": "ground-truth"
      },
      {
        "command": "/mos:systems-thinking",
        "framework": "Systems Thinking",
        "score": 1.45,
        "confidence": 0.19,
        "source": "ground-truth"
      },
      {
        "command": "/mos:analyze-systems",
        "framework": "Systems Thinking",
        "score": 1.35,
        "confidence": 0.3,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-experts",
        "framework": "Reverse Salient Analysis",
        "score": 1.27,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-fetch",
        "framework": "Reverse Salient Analysis",
        "score": 1.15,
        "confidence": 0.15,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-thesis",
        "framework": "Reverse Salient Analysis",
        "score": 1.15,
        "confidence": 0.08,
        "source": "ground-truth"
      },
      {
        "command": "/mos:rs-explain",
        "framework": "Reverse Salient Analysis",
        "score": 1.12,
        "confidence": 0.16,
        "source": "ground-truth"
      },
      {
        "command": "/mos:causal",
        "framework": "Root Cause Analysis",
        "score": 0.69,
        "confidence": 0.22,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scenario-plan",
        "framework": "Scenario Planning",
        "score": 0.05,
        "confidence": 0.94,
        "source": "ground-truth"
      }
    ],
    "find-problem|*|*": [
      {
        "command": "/mos:user-needs",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 1.86,
        "confidence": 0.79,
        "source": "ground-truth"
      },
      {
        "command": "/mos:analyze-needs",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 1.83,
        "confidence": 0.73,
        "source": "ground-truth"
      },
      {
        "command": "/mos:beautiful-question",
        "framework": "Beautiful Question Framework",
        "score": 1.81,
        "confidence": 0.72,
        "source": "ground-truth"
      },
      {
        "command": "/mos:explore-domains",
        "framework": "Domain Selection",
        "score": 1.7,
        "confidence": 0.53,
        "source": "ground-truth"
      },
      {
        "command": "/mos:root-cause",
        "framework": "Root Cause Analysis",
        "score": 1.66,
        "confidence": 0.5,
        "source": "framework-matched"
      },
      {
        "command": "/mos:auto-explore",
        "framework": null,
        "score": 1.64,
        "confidence": 0.44,
        "source": "ground-truth"
      },
      {
        "command": "/mos:causal",
        "framework": "Root Cause Analysis",
        "score": 1.6,
        "confidence": 0.4,
        "source": "framework-matched"
      },
      {
        "command": "/mos:diagnose",
        "framework": "Problem Definition Transformation Framework",
        "score": 1.27,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:futures",
        "framework": "Futures Wheel",
        "score": 0.63,
        "confidence": 0.25,
        "source": "ground-truth"
      },
      {
        "command": "/mos:validate",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 0.52,
        "confidence": 0.22,
        "source": "framework-matched"
      },
      {
        "command": "/mos:map-unknowns",
        "framework": "Knowns and Unknowns Matrix Framework",
        "score": 0.43,
        "confidence": 0.36,
        "source": "framework-matched"
      },
      {
        "command": "/mos:whitespace",
        "framework": "HSI Semantic Surprise Analysis Assistant",
        "score": 0.4,
        "confidence": 0.4,
        "source": "ground-truth"
      },
      {
        "command": "/mos:research",
        "framework": "Hypothesis-Driven Problem Solving",
        "score": 0.25,
        "confidence": 0.64,
        "source": "framework-matched"
      },
      {
        "command": "/mos:build-knowledge",
        "framework": "Ackoff Pyramid",
        "score": 0.21,
        "confidence": 0.67,
        "source": "framework-matched"
      },
      {
        "command": "/mos:trending-to-absurd",
        "framework": "Trending to the Absurd",
        "score": 0.13,
        "confidence": 0.8,
        "source": "framework-matched"
      }
    ],
    "model-business|*|*": [
      {
        "command": "/mos:lean-canvas",
        "framework": "Lean Canvas",
        "score": 1.44,
        "confidence": 0.14,
        "source": "ground-truth"
      },
      {
        "command": "/mos:mullins",
        "framework": "Mullins Model",
        "score": 0.97,
        "confidence": 0.33,
        "source": "framework-matched"
      },
      {
        "command": "/mos:validate-proposition",
        "framework": "PWS Value Proposition",
        "score": 0.69,
        "confidence": 0.26,
        "source": "ground-truth"
      },
      {
        "command": "/mos:analyze-systems",
        "framework": "Systems Thinking",
        "score": 0.43,
        "confidence": 0.37,
        "source": "framework-matched"
      },
      {
        "command": "/mos:explore-futures",
        "framework": "Scenario Planning",
        "score": 0.35,
        "confidence": 0.48,
        "source": "framework-matched"
      }
    ],
    "model-finances|*|*": [
      {
        "command": "/mos:grade",
        "framework": "PWS Triple Validation Compass",
        "score": 1.14,
        "confidence": 0,
        "source": "framework-matched"
      },
      {
        "command": "/mos:deep-grade",
        "framework": "PWS Triple Validation Compass",
        "score": 1.07,
        "confidence": 0.05,
        "source": "framework-matched"
      },
      {
        "command": "/mos:build-thesis",
        "framework": "PWS Value Proposition",
        "score": 0.23,
        "confidence": 0.64,
        "source": "ground-truth"
      }
    ],
    "plan-execution|*|*": [
      {
        "command": "/mos:act",
        "framework": null,
        "score": 1.87,
        "confidence": 0.8,
        "source": "ground-truth"
      },
      {
        "command": "/mos:pipeline",
        "framework": null,
        "score": 1.81,
        "confidence": 0.7,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scheduled-tasks",
        "framework": null,
        "score": 1.64,
        "confidence": 0.46,
        "source": "ground-truth"
      },
      {
        "command": "/mos:suggest-next",
        "framework": null,
        "score": 1.49,
        "confidence": 0.24,
        "source": "ground-truth"
      },
      {
        "command": "/mos:intel-pipeline",
        "framework": null,
        "score": 1.47,
        "confidence": 0.22,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scenario-plan",
        "framework": "Scenario Planning",
        "score": 0.51,
        "confidence": 0.24,
        "source": "ground-truth"
      },
      {
        "command": "/mos:grade",
        "framework": "PWS Triple Validation Compass",
        "score": 0.39,
        "confidence": 0.41,
        "source": "framework-matched"
      },
      {
        "command": "/mos:think-hats",
        "framework": "Six Thinking Hats",
        "score": 0.35,
        "confidence": 0.48,
        "source": "framework-matched"
      },
      {
        "command": "/mos:deep-grade",
        "framework": "PWS Triple Validation Compass",
        "score": 0.29,
        "confidence": 0.58,
        "source": "framework-matched"
      },
      {
        "command": "/mos:leadership",
        "framework": "Adaptive Leadership",
        "score": 0.19,
        "confidence": 0.72,
        "source": "ground-truth"
      },
      {
        "command": "/mos:hat-briefing",
        "framework": "Six Thinking Hats",
        "score": 0.19,
        "confidence": 0.72,
        "source": "framework-matched"
      },
      {
        "command": "/mos:analyze-needs",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 0.15,
        "confidence": 0.79,
        "source": "framework-matched"
      },
      {
        "command": "/mos:funding",
        "framework": null,
        "score": 0.15,
        "confidence": 0.79,
        "source": "framework-matched"
      },
      {
        "command": "/mos:mullins",
        "framework": "Mullins Model",
        "score": 0.14,
        "confidence": 0.79,
        "source": "framework-matched"
      }
    ],
    "protect-assets|*|*": [
      {
        "command": "/mos:challenge-assumptions",
        "framework": "Red Teaming",
        "score": 0.49,
        "confidence": 0.26,
        "source": "framework-matched"
      }
    ],
    "understand-market|*|*": [
      {
        "command": "/mos:macro-trends",
        "framework": "PEST Analysis",
        "score": 1.86,
        "confidence": 0.8,
        "source": "framework-matched"
      },
      {
        "command": "/mos:explore-trends",
        "framework": "S-Curve Analysis",
        "score": 1.67,
        "confidence": 0.51,
        "source": "framework-matched"
      },
      {
        "command": "/mos:analyze-timing",
        "framework": "S-Curve Analysis",
        "score": 1.49,
        "confidence": 0.24,
        "source": "framework-matched"
      },
      {
        "command": "/mos:radar",
        "framework": null,
        "score": 1.42,
        "confidence": 0.14,
        "source": "ground-truth"
      },
      {
        "command": "/mos:mullins",
        "framework": "Mullins Model",
        "score": 1.11,
        "confidence": 0.17,
        "source": "framework-matched"
      },
      {
        "command": "/mos:dominant-designs",
        "framework": "Dominant Design",
        "score": 1.06,
        "confidence": 0.67,
        "source": "framework-matched"
      },
      {
        "command": "/mos:diffusion",
        "framework": "Adoption-Capacity Theory",
        "score": 0.94,
        "confidence": 0.62,
        "source": "framework-matched"
      },
      {
        "command": "/mos:trending-to-absurd",
        "framework": "Trending to the Absurd",
        "score": 0.93,
        "confidence": 0.66,
        "source": "ground-truth"
      },
      {
        "command": "/mos:research",
        "framework": "Hypothesis-Driven Problem Solving",
        "score": 0.49,
        "confidence": 0.26,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scenario-plan",
        "framework": "Scenario Planning",
        "score": 0.44,
        "confidence": 0.33,
        "source": "framework-matched"
      },
      {
        "command": "/mos:challenge-assumptions",
        "framework": "Red Teaming",
        "score": 0.41,
        "confidence": 0.38,
        "source": "framework-matched"
      },
      {
        "command": "/mos:explore-domains",
        "framework": "Domain Selection",
        "score": 0.23,
        "confidence": 0.64,
        "source": "ground-truth"
      },
      {
        "command": "/mos:user-needs",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 0.21,
        "confidence": 0.68,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scout",
        "framework": null,
        "score": 0.19,
        "confidence": 0.7,
        "source": "ground-truth"
      },
      {
        "command": "/mos:compare-ventures",
        "framework": "PWS Triple Validation Compass",
        "score": 0.18,
        "confidence": 0.73,
        "source": "ground-truth"
      },
      {
        "command": "/mos:analyze-needs",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 0.16,
        "confidence": 0.76,
        "source": "ground-truth"
      },
      {
        "command": "/mos:auto-explore",
        "framework": null,
        "score": 0.09,
        "confidence": 0.86,
        "source": "ground-truth"
      }
    ],
    "validate-idea|*|*": [
      {
        "command": "/mos:validate-proposition",
        "framework": "PWS Value Proposition",
        "score": 1.9,
        "confidence": 0.86,
        "source": "ground-truth"
      },
      {
        "command": "/mos:challenge-assumptions",
        "framework": "Red Teaming",
        "score": 1.87,
        "confidence": 0.8,
        "source": "framework-matched"
      },
      {
        "command": "/mos:map-unknowns",
        "framework": "Knowns and Unknowns Matrix Framework",
        "score": 1.66,
        "confidence": 0.49,
        "source": "ground-truth"
      },
      {
        "command": "/mos:validate",
        "framework": "Jobs to Be Done (JTBD)",
        "score": 1.64,
        "confidence": 0.44,
        "source": "ground-truth"
      },
      {
        "command": "/mos:feynman-timeline-refresh",
        "framework": null,
        "score": 1.3,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:dial-memory-refresh",
        "framework": null,
        "score": 1.23,
        "confidence": 0,
        "source": "ground-truth"
      },
      {
        "command": "/mos:structure-argument",
        "framework": "The Pyramid Principle",
        "score": 1.1,
        "confidence": 0.52,
        "source": "ground-truth"
      },
      {
        "command": "/mos:compare-ventures",
        "framework": "PWS Triple Validation Compass",
        "score": 0.87,
        "confidence": 0.17,
        "source": "ground-truth"
      },
      {
        "command": "/mos:score-innovation",
        "framework": "HSI Semantic Surprise Analysis Assistant",
        "score": 0.32,
        "confidence": 0.52,
        "source": "ground-truth"
      },
      {
        "command": "/mos:scientific-roadmap",
        "framework": "Scientific Roadmapping",
        "score": 0.3,
        "confidence": 0.55,
        "source": "ground-truth"
      },
      {
        "command": "/mos:lean-canvas",
        "framework": "Lean Canvas",
        "score": 0.29,
        "confidence": 0.56,
        "source": "ground-truth"
      }
    ]
  }
}