{
  "generated": "2026-08-14T15:50:46.232Z",
  "parseMode": "R1-R3 (headline)",
  "items": 21,
  "models": 15,
  "tally": {
    "asked": 594,
    "cells": 591,
    "silent": 9,
    "throttled": 0,
    "upstream": 60,
    "unserved": 1,
    "unreadable": 55,
    "readable": 470,
    "byRule": {
      "R1": 470
    }
  },
  "accuracy": {
    "A": {
      "n": 235,
      "correct": 204,
      "rate": 0.8680851063829788
    },
    "B": {
      "n": 235,
      "correct": 207,
      "rate": 0.8808510638297873
    }
  },
  "errorCompositionA": {
    "myth": 16,
    "d1": 10,
    "d2": 5,
    "n": 31,
    "mythShare": 0.5161290322580645,
    "test": {
      "k": 16,
      "n": 31,
      "p0": 0.3333333333333333,
      "pGreater": 0.027024092727703803,
      "pTwoSided": 0.036276323234845115
    }
  },
  "perItem": [
    {
      "item": "seasons",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "far-side",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "moon-illusion",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "water-blue",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "equal-transit",
      "n": 10,
      "myth": 3,
      "d1": 2,
      "d2": 5,
      "share": 0.3
    },
    {
      "item": "microwave",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "metal-cold",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "helium",
      "n": 1,
      "myth": 1,
      "d1": 0,
      "d2": 0,
      "share": 1
    },
    {
      "item": "glass-flow",
      "n": 3,
      "myth": 0,
      "d1": 3,
      "d2": 0,
      "share": 0
    },
    {
      "item": "concrete",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "veins",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "tongue-map",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "dog-colour",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "metabolism",
      "n": 7,
      "myth": 4,
      "d1": 3,
      "d2": 0,
      "share": 0.5714285714285714
    },
    {
      "item": "head-heat",
      "n": 2,
      "myth": 1,
      "d1": 1,
      "d2": 0,
      "share": 0.5
    },
    {
      "item": "ulcers",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "gum",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    },
    {
      "item": "five-second",
      "n": 3,
      "myth": 3,
      "d1": 0,
      "d2": 0,
      "share": 1
    },
    {
      "item": "cake",
      "n": 2,
      "myth": 2,
      "d1": 0,
      "d2": 0,
      "share": 1
    },
    {
      "item": "february",
      "n": 3,
      "myth": 2,
      "d1": 1,
      "d2": 0,
      "share": 0.6666666666666666
    },
    {
      "item": "redshifts",
      "n": 0,
      "myth": 0,
      "d1": 0,
      "d2": 0,
      "share": null
    }
  ],
  "signTest": {
    "items": 8,
    "above": 6,
    "below": 2,
    "ties": 0,
    "p": 0.2890625000000575
  },
  "bootstrap": {
    "iters": 20000,
    "lo95": 0.3409090909090909,
    "hi95": 0.7894736842105263,
    "median": 0.52,
    "pAboveThird": 0.02415
  },
  "neutralCompositionB": {
    "d3": 11,
    "d1": 11,
    "d2": 6,
    "n": 28,
    "uniformity": {
      "stat": 1.785714285714286,
      "p": 0.45298773506132467,
      "iters": 200000
    }
  },
  "pull": {
    "pairs": 220,
    "bothRight": 185,
    "aRightBWrong": 5,
    "aWrongBRight": 9,
    "bothWrong": 21,
    "pMcNemar": 0.42395019531379746
  },
  "ensemble": {
    "items": 21,
    "voteFloor": 5,
    "itemsBelowFloor": 0,
    "pluralityCorrect": 19,
    "majorityObserved": 19,
    "majorityExpectedUnderIndependence": 20.96448398614373,
    "meanSingleModel": 0.8680851063829788,
    "bestSingleModel": [
      "nvidia/nemotron-3-ultra-550b-a55b:free",
      {
        "n": 20,
        "rate": 1
      }
    ]
  },
  "perModelRate": {
    "openai/gpt-oss-20b:free": {
      "n": 18,
      "rate": 0.8333333333333334
    },
    "google/gemma-4-26b-a4b-it:free": {
      "n": 17,
      "rate": 0.9411764705882353
    },
    "cohere/north-mini-code:free": {
      "n": 20,
      "rate": 0.9
    },
    "liquid/lfm-2.5-2.6b:free": {
      "n": 6,
      "rate": 1
    },
    "poolside/laguna-s-2.1:free": {
      "n": 19,
      "rate": 0.8421052631578947
    },
    "poolside/laguna-xs-2.1:free": {
      "n": 21,
      "rate": 0.9047619047619048
    },
    "nvidia/nemotron-3-ultra-550b-a55b:free": {
      "n": 20,
      "rate": 1
    },
    "nvidia/nemotron-3-super-120b-a12b:free": {
      "n": 18,
      "rate": 0.8888888888888888
    },
    "nvidia/nemotron-3.5-lightning:free": {
      "n": 18,
      "rate": 1
    },
    "nvidia/nemotron-3-nano-30b-a3b:free": {
      "n": 21,
      "rate": 0.9047619047619048
    },
    "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free": {
      "n": 20,
      "rate": 0.8
    },
    "nvidia/nemotron-nano-12b-v2-vl:free": {
      "n": 16,
      "rate": 0.6875
    },
    "nvidia/nemotron-nano-9b-v2:free": {
      "n": 21,
      "rate": 0.6666666666666666
    }
  },
  "makers": {
    "OpenAI": {
      "n": 18,
      "correct": 15,
      "wrongMyth": 1,
      "wrong": 3
    },
    "Cohere": {
      "n": 20,
      "correct": 18,
      "wrongMyth": 2,
      "wrong": 2
    },
    "Google": {
      "n": 17,
      "correct": 16,
      "wrongMyth": 0,
      "wrong": 1
    },
    "Liquid AI": {
      "n": 6,
      "correct": 6,
      "wrongMyth": 0,
      "wrong": 0
    },
    "Poolside": {
      "n": 40,
      "correct": 35,
      "wrongMyth": 2,
      "wrong": 5
    },
    "NVIDIA": {
      "n": 134,
      "correct": 114,
      "wrongMyth": 11,
      "wrong": 20
    }
  },
  "position": {
    "stat": 1.0508474576271187,
    "p": 0.605036974815126,
    "iters": 200000
  },
  "chosenSlots": [
    126,
    111,
    113,
    120
  ],
  "checkedSlotRealised": [
    172,
    136,
    146,
    140
  ],
  "votes": [
    {
      "item": "seasons",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "far-side",
      "n": 9,
      "counts": {
        "checked": 9
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "moon-illusion",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "water-blue",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "equal-transit",
      "n": 12,
      "counts": {
        "d2": 5,
        "d1": 2,
        "checked": 2,
        "myth": 3
      },
      "mode": "d2",
      "tie": false,
      "modeCorrect": false
    },
    {
      "item": "microwave",
      "n": 10,
      "counts": {
        "checked": 10
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "metal-cold",
      "n": 11,
      "counts": {
        "checked": 11
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "helium",
      "n": 11,
      "counts": {
        "checked": 10,
        "myth": 1
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "glass-flow",
      "n": 10,
      "counts": {
        "checked": 7,
        "d1": 3
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "concrete",
      "n": 10,
      "counts": {
        "checked": 10
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "veins",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "tongue-map",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "dog-colour",
      "n": 11,
      "counts": {
        "checked": 11
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "metabolism",
      "n": 9,
      "counts": {
        "myth": 4,
        "d1": 3,
        "checked": 2
      },
      "mode": "myth",
      "tie": false,
      "modeCorrect": false
    },
    {
      "item": "head-heat",
      "n": 12,
      "counts": {
        "checked": 10,
        "d1": 1,
        "myth": 1
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "ulcers",
      "n": 13,
      "counts": {
        "checked": 13
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "gum",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "five-second",
      "n": 10,
      "counts": {
        "myth": 3,
        "checked": 7
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "cake",
      "n": 12,
      "counts": {
        "myth": 2,
        "checked": 10
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "february",
      "n": 11,
      "counts": {
        "checked": 8,
        "myth": 2,
        "d1": 1
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    },
    {
      "item": "redshifts",
      "n": 12,
      "counts": {
        "checked": 12
      },
      "mode": "checked",
      "tie": false,
      "modeCorrect": true
    }
  ],
  "flagged": [
    {
      "item": "equal-transit",
      "n": 12,
      "checked": 2,
      "counts": {
        "d2": 5,
        "d1": 2,
        "checked": 2,
        "myth": 3
      },
      "question": "When air splits at the front of a wing, what happens to the two halves at the trailing edge?"
    }
  ],
  "sensitivityR1Only": {
    "tally": {
      "asked": 594,
      "cells": 591,
      "silent": 9,
      "throttled": 0,
      "upstream": 60,
      "unserved": 1,
      "unreadable": 55,
      "readable": 470,
      "byRule": {
        "R1": 470
      }
    },
    "accuracy": {
      "A": {
        "n": 235,
        "correct": 204,
        "rate": 0.8680851063829788
      },
      "B": {
        "n": 235,
        "correct": 207,
        "rate": 0.8808510638297873
      }
    },
    "errorCompositionA": {
      "myth": 16,
      "d1": 10,
      "d2": 5,
      "n": 31,
      "mythShare": 0.5161290322580645,
      "test": {
        "k": 16,
        "n": 31,
        "p0": 0.3333333333333333,
        "pGreater": 0.027024092727703803,
        "pTwoSided": 0.036276323234845115
      }
    },
    "pull": {
      "pairs": 220,
      "bothRight": 185,
      "aRightBWrong": 5,
      "aWrongBRight": 9,
      "bothWrong": 21,
      "pMcNemar": 0.42395019531379746
    }
  }
}