[
  {
    "number": 1,
    "id": "tab-benchmark_comparison",
    "label": "tab:benchmark_comparison",
    "caption": "Comparison with representative manipulation benchmarks. ✓: explicit target; ∼: partial; –: not targeted. Hidden: task information absent from the current observation.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Benchmark features",
          "colspan": 4,
          "bold": true
        },
        {
          "text": "Evidence seeking",
          "colspan": 3,
          "bold": true
        }
      ],
      [
        {
          "text": "Benchmark",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Focus",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Long hor.",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Hidden",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Memory",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Mobile",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Search",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Inspect",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Test",
          "colspan": 1,
          "bold": true
        }
      ],
      [
        {
          "text": "RLBench",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Visuomotor skills",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "ManiSkill3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Scalable manipulation",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "RoboTwin 2.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Bimanual manipulation",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "LIBERO",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Lifelong skill transfer",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "CALVIN",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Long-horizon manipulation",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "BEHAVIOR-1K",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Household activities",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "RoboCasa365",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Manipulation in kitchen",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "RMBench",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Memory-dependent manipulation",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "RoboQuest",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "Evidence-seeking manipulation",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 2,
    "id": "tab-capabilities",
    "label": "tab:capabilities",
    "caption": "Task capabilities and failure taxonomy. Left: ✓ marks a directly targeted capability, ∼ a supporting requirement, and – no designated requirement. DS: directed search. AP: active perception. EI: evidence integration. M: memory. AD: affordance discovery. XI: experimental identification. CI: physical causal inference. CA: consequential action. LP: long-horizon planning. Right: failures before action, during execution, and after feedback. Each failure type is linked to impairment in a likely set of capabilities defined on the left.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Evidence · acquisition",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Evidence · use",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Interactive · inference",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "Action · organization",
          "colspan": 2,
          "bold": false
        }
      ],
      [
        {
          "text": "Family",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "DS",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "AP",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "EI",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "M",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "AD",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "XI",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "CI",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "CA",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "LP",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Search Room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Blackout Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Inspect",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Test",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Puzzle Box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Wobbly Stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "∼",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 3,
    "id": "tab-main",
    "label": "tab:main",
    "caption": "Main results. SR: success rate. Prog: mean progress. Both in %, 50 episodes per cell. Best SR per row in bold. Overall w/o Puzzle Box excludes the easiest task, an outlier on which all three models score far above their other tasks.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Gemini 3.8 Flash",
          "colspan": 2,
          "bold": false
        }
      ],
      [
        {
          "text": "Family",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "52.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Search Room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "31.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "19.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "17.5",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Blackout Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "23.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.4",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Inspect",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "74.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "61.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.3",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "43.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "32.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.3",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Test",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Puzzle Box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "96.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "99.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "70.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "81.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "55.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.4",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Wobbly Stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "18.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "18.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Overall",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "19.4",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "44.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "29.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Overall w/o Puzzle Box",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "10.9",
          "colspan": 1,
          "bold": true
        },
        {
          "text": "38.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "23.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.5",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 4,
    "id": "tab-cost",
    "label": "tab:cost",
    "caption": "Cost and effort per episode. Sim / Wall: simulated / wall-clock minutes. In / Out: tokens in millions. Costs in USD at list prices.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Effort per episode",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "Tokens per episode",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "Cost (USD)",
          "colspan": 2,
          "bold": false
        }
      ],
      [
        {
          "text": "Model",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Decisions",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Sim min.",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Wall min.",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "In (M)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Out (M)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Cached (%)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "$/episode",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "$/success",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "143.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "53.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.82",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.02",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "91.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.30",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "58.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "148.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "54.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.55",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "94.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "19.22",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "192.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Gemini 3.8 Flash",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "160.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "19.66",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "89.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.37",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "168.3",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 5,
    "id": "tab-tools",
    "label": "tab:tools",
    "caption": "Action tools. Positions are in world metres; a tick is 0.05 s of simulated time. Every tool except stop accepts a tick count from 1 to 200.",
    "rows": [
      [
        {
          "text": "Tool",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Arguments",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Default ticks",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "arm",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "gripper-site position (required); orientation as a quaternion; gripper command in [-1,1], where -1 opens and +1 closes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "120",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "base",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "body-frame forward, left, and yaw velocity, each in [-0.5, 0.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "wait",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "optional gripper command; holds the arm and base",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "stop",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "none; abandons the episode, which fails",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 6,
    "id": "tab-vla_hyperparameters",
    "label": "tab:vla_hyperparameters",
    "caption": "π₀.₅ Training and Inference Hyperparameters.",
    "rows": [
      [
        {
          "text": "Category",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Hyperparameter",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Value",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Training",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Optimizer",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "AdamW (β₁=0.9, β₂=0.999, ε=10⁻⁸)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Weight Decay",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1× 10⁻⁴",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Peak Learning Rate",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.5× 10⁻⁵",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Learning Rate Schedule",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Cosine decay with 1000 warmup steps",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Global Batch Size",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "32",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Gradient Clipping Norm",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Flow Loss Multiplier",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Action Normalization",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Quantile (q₀₁, q₉₉)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Inference",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Replanning Frequency",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Once per 20 ticks (1.0 s)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Flow Denoising Steps",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 7,
    "id": "tab-task_overview",
    "label": "tab:task_overview",
    "caption": "Tasks and their main parameters. Occlusion: Visible (V), Look (L), Uncover (U), defined in the environment description. W, O, C: tasks used for analysis of workload, occlusion, and cover in the diagnostic analysis.",
    "rows": [
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Hidden information",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Main parameters",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "W",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "O",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "C",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search",
          "colspan": 7,
          "bold": true
        }
      ],
      [
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "target behind locks",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "chain depth 1/2/3",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search Room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "where the targets are",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "compartments 4/6/8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "targets 2/3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Blackout Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "targets in the dark",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "compartments 4/6/8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "targets 2/3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Inspect",
          "colspan": 7,
          "bold": true
        }
      ],
      [
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "marks on unseen faces",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "cubes 4/6/8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "occlusion V/L/U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "labels under vessels",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "vessels 3/4/5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "occlusion V/L/U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "how containers open",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "items 2/3/4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "occlusion V/L",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Test",
          "colspan": 7,
          "bold": true
        }
      ],
      [
        {
          "text": "Puzzle Box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "bolt blocking order",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "chain 4/5/6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "cover no/yes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "patterns and rotations",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "stamps 2/3/4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "occlusion V/L/U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Wobbly Stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "short legs and gaps",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "short legs 1/2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "shim choice no/yes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "which parcel is odd",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "parcels 4/6/8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "occlusion V/L/U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "✓",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 8,
    "id": "tab-progress-summary",
    "label": "tab:progress-summary",
    "caption": "Progress P at a glance. Every stage counts only in a passive state (released, supported, untouched where the predicate requires it); P is uncapped, frozen at the first Submit press and clipped to [0,1].",
    "rows": [
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Units",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Stages or terms",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Deduction δ",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "targets",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "opened / out / placed",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "non-target on tray",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Locked storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "chain links, target",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "links + opened / out / placed",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "non-target on tray",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Blackout search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "targets",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "opened / out / placed",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "non-target on tray",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "vessels",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "{0,0.5,1} per vessel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "correct captures",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "items",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "opened / out / in bowl",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "target cells",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "cell grades {0,0.5,1}, strays in the denominator",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "parcel set",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Jaccard of boxed set and odd set",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "pans loaded",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Puzzle box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "chain bolts, item",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "bolts + lid / out / tray",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Wobbly stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "tilt removed q, ball on top b",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "–",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 9,
    "id": "tab-outcomes_task_pct",
    "label": "tab:outcomes_task_pct",
    "caption": "Episode outcomes per task. Percentage of episodes by outcome, with absolute counts shown below in parentheses. Cell shading indicates the percentage within each model–task pair (darker indicates a larger percentage). C: correct submit. W: wrong submit. S: declared stop. A: text answer instead of a submit. T: timeout (out of decisions). Tasks are ordered as in Table 3.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 5,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 5,
          "bold": false
        },
        {
          "text": "Gemini 3.8 Flash",
          "colspan": 5,
          "bold": false
        }
      ],
      [
        {
          "text": "Family",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "C",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "W",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "S",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "A",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "T",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "C",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "W",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "S",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "A",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "T",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "C",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "W",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "S",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "A",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "T",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28% (14)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "44% (22)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20% (10)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8% (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8% (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42% (21)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36% (18)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14% (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20% (10)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "78% (39)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Search Room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "56% (28)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8% (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36% (18)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "56% (28)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34% (17)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8% (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "32% (16)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "66% (33)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Blackout Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "76% (38)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12% (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12% (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46% (23)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "50% (25)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "56% (28)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6% (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "38% (19)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Inspect",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30% (15)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "70% (35)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14% (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "84% (42)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "82% (41)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16% (8)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10% (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "82% (41)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4% (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4% (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "80% (40)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20% (10)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "88% (44)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12% (6)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6% (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "66% (33)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6% (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22% (11)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "24% (12)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "68% (34)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8% (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36% (18)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "64% (32)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Test",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Puzzle Box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "96% (48)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4% (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "70% (35)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14% (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16% (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12% (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6% (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "82% (41)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14% (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "84% (42)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "74% (37)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22% (11)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "54% (27)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46% (23)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Wobbly Stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10% (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "86% (43)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6% (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "62% (31)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30% (15)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "96% (48)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "88% (44)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12% (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "82% (41)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10% (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4% (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4% (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2% (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "86% (43)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12% (6)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "All tasks",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "19.4% (97)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "65.6% (328)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.4% (27)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.6% (48)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0% (50)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55.0% (275)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28.6% (143)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.4% (27)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.0% (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0% (10)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55.6% (278)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.8% (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0% (0)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41.6% (208)",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 10,
    "id": "tab-dataset",
    "label": "tab:dataset",
    "caption": "Demonstration dataset. Scripted information gathering in each oracle's route, which the oracle performs although it knows the hidden information. Episodes: successful demonstrations. Hours: interaction time at 20 Hz.",
    "rows": [
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Scripted information gathering",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Episodes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Hours",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "follows the token chain",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "278",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search Room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "opens compartments nearest-first until the targets are seen",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "294",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46.8",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Blackout Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "carries the lamp along a nearest-first search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "201",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "53.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "removes covers and turns each cube face by face",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "276",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "50.3",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "lifts and tilts each vessel to read its label",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "312",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20.9",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "some episodes make one or two wrong tries before opening",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "398",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "76.9",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Puzzle Box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "tries sliders, one to three of which are blocked",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "447",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21.1",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "prints test impressions before the final one",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "363",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "32.6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Wobbly Stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "releases the ball, places a shim, and tests again",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "381",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "18.9",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "weighs parcels on the balance",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "261",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51.7",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Total",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3,211",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "405.5",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 11,
    "id": "tab-factor_estimates",
    "label": "tab:factor_estimates",
    "caption": "Factor estimates. Task-balanced aggregate success rate and progress (%) per factor level, and contrasts between levels, with cell-stratified paired bootstrap 95% confidence intervals (4,000 resamples). Workload uses the six workload tasks; occlusion uses the four occlusion tasks; the shared-task rows recompute the workload contrasts on the four occlusion tasks only, and the last block gives the direct difference between the workload penalty (Low - High) and each occlusion penalty (Visible - Look, Visible - Uncover) on those tasks.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 2,
          "bold": false
        }
      ],
      [
        {
          "text": "Analysis",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Quantity",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Workload (6 tasks)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "23.1 [16.1, 30.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51.1 [44.9, 57.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.0 [4.9, 13.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30.9 [25.3, 36.7]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12.6 [7.5, 18.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "45.7 [40.0, 51.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.0 [0.0, 6.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.0 [22.9, 31.1]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.7 [3.0, 12.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "39.0 [33.9, 44.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0 [0.0, 0.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22.4 [18.9, 26.0]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid - Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-10.5 [-19.1, -1.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-5.3 [-13.5, 3.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.0 [-11.3, -0.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-3.9 [-10.8, 3.0]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High - Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-15.4 [-24.0, -6.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-12.1 [-20.1, -3.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-9.0 [-13.2, -4.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-8.5 [-15.4, -1.9]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Occlusion (4 tasks)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16.7 [9.7, 23.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51.1 [44.8, 57.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.6 [2.8, 8.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.2 [29.1, 39.3]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.8 [4.7, 17.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "45.6 [39.1, 51.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.7 [0.0, 9.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.6 [22.6, 32.8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Uncover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12.8 [6.4, 19.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "44.5 [38.7, 50.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.4 [0.0, 4.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "29.5 [24.0, 34.8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Look - Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-5.8 [-15.0, 3.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-5.6 [-14.3, 3.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.8 [-5.6, 5.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.6 [-13.8, 0.7]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Uncover - Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-3.9 [-13.9, 5.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.6 [-15.2, 1.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.2 [-8.3, 0.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.7 [-11.9, 2.7]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Workload, shared 4 tasks",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21.7 [13.6, 29.4]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "53.0 [46.3, 59.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.2 [2.8, 11.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "31.3 [25.3, 37.4]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12.8 [6.9, 18.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46.8 [41.0, 52.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.4 [0.0, 9.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33.0 [27.6, 38.3]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.8 [1.4, 11.4]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41.4 [35.4, 47.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0 [0.0, 0.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.1 [22.8, 31.4]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid - Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-8.9 [-19.2, 1.4]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.2 [-15.1, 2.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-2.8 [-8.9, 3.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.7 [-6.4, 9.7]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High - Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-15.8 [-25.6, -6.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-11.6 [-20.5, -2.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-7.2 [-11.7, -2.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.2 [-11.7, 3.3]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Difference of penalties",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Workload - Look penalty",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0 [-3.1, 23.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.1 [-6.0, 18.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.4 [1.4, 12.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-2.4 [-12.0, 7.6]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Workload - Uncover penalty",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.9 [-0.6, 24.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.0 [-6.9, 16.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.1 [0.0, 7.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.5 [-10.1, 9.3]",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 12,
    "id": "tab-access_per_task",
    "label": "tab:access_per_task",
    "caption": "Occlusion by task. Visible / Look / Uncover on the four tasks that share the occlusion design. Visible means no additional object search or cover removal is required; the deciding information (die faces, parcel mass, bottom labels, cube faces) is still hidden in every mode. Each mode is the mean of its workload cells. SR and Prog in %, Dec: mean decisions, T/O: timeout share (%).",
    "rows": [
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Policy",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR V / L / U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog V / L / U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Dec V / L / U",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "T/O V / L / U",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6 / 31 / 7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "62 / 63 / 39",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "110 / 86 / 119",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 6 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "39 / 36 / 38",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "143 / 139 / 143",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14 / 20 / 14",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "174 / 186 / 189",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "13 / 11 / 21",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9 / 4 / 7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "181 / 180 / 188",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7 / 0 / 5",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 0 / 13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "47 / 36 / 46",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "132 / 121 / 126",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21 / 15 / 15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "133 / 139 / 153",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "44 / 12 / 31",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "81 / 63 / 79",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "114 / 122 / 130",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22 / 13 / 6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "68 / 56 / 59",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "133 / 136 / 143",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Task-balanced mean",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16.7 / 10.8 / 12.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51.1 / 45.6 / 44.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "133 / 129 / 141",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.1 / 2.9 / 5.4",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.6 / 4.7 / 1.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.2 / 27.6 / 29.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "148 / 149 / 157",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.7 / 0.0 / 1.2",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 13,
    "id": "tab-factor_cells",
    "label": "tab:factor_cells",
    "caption": "Workload × occlusion cells. Success rate / progress (%) per design cell for the four tasks that cross both factors, with the number of episodes per cell in parentheses (the same instances for both models). Rows: workload level; columns: occlusion variant.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 3,
          "bold": false
        }
      ],
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Workload",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Uncover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Uncover",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 74 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "60 / 84 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 44 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 23 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 20 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 47 (5)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 47 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 71 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 50 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 72 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 44 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 19 (6)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 67 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 35 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 22 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 24 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 43 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 47 (5)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 26 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 26 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 13 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 (2)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 8 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 24 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 30 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 8 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 8 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 9 (7)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 9 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 9 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 13 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 5 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 5 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 11 (7)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 53 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 37 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 50 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 28 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 27 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 30 (5)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 42 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 31 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 42 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 27 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 15 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 10 (5)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 47 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 40 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 46 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 7 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 3 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 4 (5)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67 / 88 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 65 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "60 / 90 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67 / 83 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 50 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 55 (5)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67 / 92 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 50 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33 / 75 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 67 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 57 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 61 (6)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 62 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 75 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 71 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 55 (5)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 60 (6)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 60 (6)",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 14,
    "id": "tab-factor_cells_other",
    "label": "tab:factor_cells_other",
    "caption": "Workload cells of the two remaining workload tasks. Success rate / progress (%) per design cell with episode counts in parentheses. Unfamiliar Containers crosses item count with visible / look; Locked Storage crosses chain depth with the presence of a dead-end link.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 2,
          "bold": false
        }
      ],
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Workload",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20 / 42 (10)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9 / 39 (11)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 17 (10)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 18 (11)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 36 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 21 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 26 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 13 (7)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High (4)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 27 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 19 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 15 (7)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 11 (7)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Workload",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No dead end",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Dead end",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No dead end",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Dead end",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Low (1)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "38 / 55 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "38 / 53 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "38 / 38 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12 / 48 (8)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Mid (2)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "38 / 56 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11 / 62 (9)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 8 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 12 (9)",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "High (3)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33 / 58 (9)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12 / 32 (8)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 19 (9)",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 6 (8)",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 15,
    "id": "tab-attribution_rules",
    "label": "tab:attribution_rules",
    "caption": "Attribution rules per task. Unit: what counts as one unmet requirement. The rules are applied in the order listed, and the first matching rule assigns the category. IEG: inadequate evidence gathering; MIS: misinterpretation of evidence; FRP: faulty reasoning or planning; FAE: failed action execution; FDE/IER: after an execution failure, no repair attempt or a failed one; IT: incorrect termination.",
    "rows": [
      [
        {
          "text": "Task and unit",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Rules",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search Room, Blackout Search; each missing target",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "On the tray but not upright: FAE. Carried and lost: FDE/IER. Hiding place never within 25 cm: IEG. Three or more grasp attempts at the target without carrying it: IER. Gripper within 15 cm of the target: MIS. Otherwise IEG. Last, a look-alike of the same colour or kind on the tray turns an IEG or MIS unit into MIS; an unpaired non-target on the tray is its own MIS unit.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Locked Storage; the target",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Chain progress is read off the progress score. If the target is reachable, as in Search Room. Otherwise, for the token of the first closed link: never approached, IEG; carried and lost, FDE/IER; placed on its reader but the link is closed at the press, FRP.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar Containers; each item not in the bowl",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Box never opened: IEG if never approached or probed fewer than three times, FRP if grasped three or more times. Box opened, item still inside: IER after two or more grasp attempts, else IT. Item out of its box: FDE/IER.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted Cubes; each misfiled or uncaptured cube",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fell into a bin when the grip was lost: FAE. Wrong bin chosen: IEG if some set of unseen faces explains the choice, else MIS. Hidden and never picked: IEG. In view and never picked, or set down and never binned: IT. Carried and lost: FDE/IER.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs; each failed vessel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Wrong pad: MIS if the vessel was tilted before placement, else IEG. Correct pad with another vessel's balls: FRP. Correct pad with own balls missing: IER if balls were picked up again, else FDE. Tipped over, or set down at its pad without resting on it: FAE. Never moved: IT.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition; each wrong cell",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Ink outside the grid, or dots across cell edges: FAE. Blank target cells with fewer final impressions than the solution needs: IT. Other wrong cells: IEG if a stamp reached the final board untested, else MIS.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel; each missing or extra parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Extra parcel in the box: FRP. Missing odd parcel: IEG if the agent made fewer pan placements than there are parcels, else FRP.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Puzzle Box; the stall",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "First unreleased part in the release order: blocked at the press, FRP; never grasped, IEG; grasped three or more times, FRP; else FAE. Lid never opened after all bolts: IEG if never grasped, else FAE. Item out but not in the tray: FAE.",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Wobbly Stand; the stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Tilt above 15°, shim beside a leg, or level without the ball: FAE. Shim under a leg that is not short: MIS. Short legs partly shimmed or wrong thickness: FRP. No shim placed: IT.",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 16,
    "id": "tab-failure_per_task",
    "label": "tab:failure_per_task",
    "caption": "Failure breakdown per task. Share (%) of unmet requirements in each category. Ep.: failed episodes; Req.: unmet requirements. IEG: inadequate evidence gathering; MIS: misinterpretation of evidence; FRP: faulty reasoning or planning; FAE: failed action execution; FDE: failure to detect errors; IER: ineffective error recovery; IT: incorrect termination; OOD: out of decisions.",
    "rows": [
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Policy",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Ep.",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Req.",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "IEG",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "MIS",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FRP",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FAE",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FDE",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "IER",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "IT",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "OOD",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Search Room",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "63",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "150",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "59",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "63",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "160",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "68",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "43",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "45",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "24",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "29",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "58",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "24",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "40",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "26",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Blackout Search",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "131",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "50",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "129",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "65",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "37",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "85",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "58",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "47",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "132",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "61",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "49",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "128",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "70",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "54",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "187",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "49",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "118",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "66",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "54",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "138",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "72",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "123",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "31",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "37",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "170",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "24",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "49",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "75",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "59",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "94",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "60",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "40",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Puzzle Box",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "53",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "47",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Wobbly Stand",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "44",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "44",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "75",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 17,
    "id": "tab-failure_breakdown",
    "label": "tab:failure_breakdown",
    "caption": "Failure breakdown by taxonomy category, in % of the unmet requirements of failed episodes. Overall: 95% bootstrap intervals. the attribution protocol gives the attribution rules.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Search",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Inspect",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Test",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "Overall",
          "colspan": 2,
          "bold": false
        }
      ],
      [
        {
          "text": "Phase",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Category",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Linked capabilities",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fable",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fable",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fable",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fable",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Before action",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Inadequate evidence gathering",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Acquisition, inference",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "50.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "59.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "39.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "40.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "25.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36.7 · [34, 40]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42.2 · [39, 45]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Misinterpretation of evidence",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Use",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.5 · [9, 14]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.0 · [7, 11]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Faulty reasoning or planning",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Use, inference, organization",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.4 · [6, 9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.4 · [5, 8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "During action",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Failed action execution",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Organization",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "29.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "24.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21.1 · [19, 23]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15.4 · [13, 17]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "After feedback",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Failure to detect errors",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Use, organization",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.3 · [5, 8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.5 · [2, 3]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Ineffective error recovery",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Inference, organization",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.0 · [4, 6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.9 · [3, 5]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Incorrect termination",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Use, organization",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "19.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.3 · [8, 15]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "20.5 · [17, 24]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Failed episodes",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "161",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "173",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "137",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "155",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "134",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "158",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "432",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "486",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unmet requirements (denominator)",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "326",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "347",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "331",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "457",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "244",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "325",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "901",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1129",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 18,
    "id": "tab-factors",
    "label": "tab:factors",
    "caption": "Workload and occlusion on the four tasks that vary both, pooled over both models. Brackets: 95% bootstrap intervals. Last block: workload drop minus occlusion drop.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 3,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fable",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Pooled",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Fable",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Pooled",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Workload",
          "colspan": 7,
          "bold": false
        }
      ],
      [
        {
          "text": "Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "53.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "31.3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42.1",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Mid",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "39.9",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "High",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "High - Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-15.8 · [-25.6, -6.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-7.2 · [-11.7, -2.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-11.5 · [-16.8, -6.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-11.6 · [-20.5, -2.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.2 · [-11.7, 3.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-7.9 · [-14.0, -1.8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Occlusion",
          "colspan": 7,
          "bold": false
        }
      ],
      [
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "16.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42.7",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "45.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36.6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Uncover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "12.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "44.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "29.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "37.0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Look - Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-5.8 · [-15.0, 3.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.8 · [-5.6, 5.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-3.3 · [-8.8, 1.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-5.6 · [-14.3, 3.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.6 · [-13.8, 0.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.1 · [-11.6, -0.4]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Uncover - Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-3.9 · [-13.9, 5.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.2 · [-8.3, 0.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.0 · [-9.3, 1.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-6.6 · [-15.2, 1.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-4.7 · [-11.9, 2.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-5.6 · [-11.6, 0.4]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Workload drop minus occlusion drop",
          "colspan": 7,
          "bold": false
        }
      ],
      [
        {
          "text": "vs. Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0 · [-3.1, 23.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.4 · [1.4, 12.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8.2 · [1.5, 15.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.1 · [-6.0, 18.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-2.4 · [-12.0, 7.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.8 · [-6.3, 9.8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "vs. Uncover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11.9 · [-0.6, 24.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.1 · [0.0, 7.5]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.5 · [1.1, 13.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.0 · [-6.9, 16.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.5 · [-10.1, 9.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.3 · [-5.9, 10.5]",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 19,
    "id": "tab-factor_phases",
    "label": "tab:factor_phases",
    "caption": "Where the extra failures come from. Unmet requirements per episode by failure phase, on the tasks and instances of Table 18. Brackets: 95% bootstrap intervals.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Before action",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "During action",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "After feedback",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "All",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Workload",
          "colspan": 5,
          "bold": false
        }
      ],
      [
        {
          "text": "Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.66",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.48",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.49",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.63",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Mid",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.01",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.61",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.72",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.36",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "High",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.42",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.67",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.10",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.19",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "High - Low",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.75 · [0.53, 0.96]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.19 · [0.05, 0.33]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.61 · [0.29, 0.95]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.55 · [1.23, 1.89]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Occlusion",
          "colspan": 5,
          "bold": false
        }
      ],
      [
        {
          "text": "Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.91",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.65",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.64",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.22",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Look",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.06",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.49",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.90",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.44",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Uncover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.61",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.77",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.53",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Look - Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.15 · [-0.08, 0.36]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.17 · [-0.30, -0.03]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.25 · [-0.05, 0.55]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.22 · [-0.11, 0.61]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Uncover - Visible",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.23 · [-0.01, 0.46]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.04 · [-0.17, 0.09]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.13 · [-0.16, 0.48]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.31 · [-0.07, 0.68]",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 20,
    "id": "tab-puzzle_cover",
    "label": "tab:puzzle_cover",
    "caption": "Puzzle Box: effect of hiding the locks, on chain lengths 4 and 5. Δ: Covered minus No cover, with 95% bootstrap interval. Last row: Claude Fable 5.1's Δ minus GPT-6 Astra's.",
    "rows": [
      [
        {
          "text": "Policy",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Decisions",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "94.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "99.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "84.7",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Covered",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "96.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "99.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "119.5",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Δ",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0 · [-8.7, 16.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-0.1 · [-1.4, 1.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.8 · [14.0, 55.8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "106.7",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Covered",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "59.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "174.6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Δ",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-65.4 · [-83.7, -46.2]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-40.9 · [-56.3, -26.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67.9 · [46.8, 86.1]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Gemini 3.8 Flash",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "45.2",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "172.2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Covered",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "25.5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "199.8",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Δ",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-27.8 · [-44.4, -11.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-19.7 · [-37.9, -1.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "27.6 · [8.5, 48.8]",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Difference in Δ",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "-67.3 · [-89.8, -44.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "-40.8 · [-56.2, -26.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33.1 · [5.0, 63.6]",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 21,
    "id": "tab-outcomes",
    "label": "tab:outcomes",
    "caption": "How episodes end, in % of 500 episodes per model. Stop, Text answer, and Timeout end without a SUBMIT and all fail. Precision: share of submissions that were correct.",
    "rows": [
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Submitted",
          "colspan": 2,
          "bold": false
        },
        {
          "text": "No submit",
          "colspan": 3,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Model",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Correct",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Wrong",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Stopped",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Text answer",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Timeout",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Submit rate",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Precision",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "19.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "65.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "85.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "22.8",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "65.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15.4",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Gemini 3.8 Flash",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "57.6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.5",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 22,
    "id": "tab-workload_per_task",
    "label": "tab:workload_per_task",
    "caption": "Workload by task. Each cell gives Low / Mid / High. SR, Prog, and T/O (share of episodes that ran out of decisions) are in %; Dec is the mean number of decisions per episode. Workload levels are listed in the methods. Each level has about 17 episodes per model, so single-task trends are noisy.",
    "rows": [
      [
        {
          "text": "Task",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Policy",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "SR L / M / H",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Prog L / M / H",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Dec L / M / H",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "T/O L / M / H",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Stamp Composition",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "32 / 6 / 6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67 / 56 / 41",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "104 / 113 / 98",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 6 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30 / 45 / 38",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "138 / 142 / 146",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Odd Parcel",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 21 / 11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "171 / 186 / 192",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21 / 7 / 18",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4 / 8 / 7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "179 / 180 / 190",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 11",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Marked Mugs",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6 / 12 / 12",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46 / 38 / 44",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "111 / 132 / 136",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 6 / 6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28 / 17 / 5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "136 / 150 / 139",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Painted Cubes",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "49 / 33 / 6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "81 / 72 / 69",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "95 / 129 / 142",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "29 / 12 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "63 / 61 / 59",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "121 / 133 / 158",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Unfamiliar Containers",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41 / 28 / 23",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "183 / 189 / 151",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10 / 41 / 21",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17 / 20 / 13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "170 / 181 / 150",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Locked Storage",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "38 / 24 / 23",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "54 / 59 / 45",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "140 / 162 / 149",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6 / 11 / 6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "25 / 0 / 0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "43 / 10 / 13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "113 / 135 / 119",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0 / 0 / 0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Task-balanced mean",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "23.1 / 12.6 / 7.7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "51.1 / 45.7 / 39.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "134 / 152 / 145",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.2 / 10.7 / 8.4",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.0 / 3.0 / 0.0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30.9 / 27.0 / 22.4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "143 / 153 / 150",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0 / 0.0 / 1.9",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 23,
    "id": "tab-puzzle_stages",
    "label": "tab:puzzle_stages",
    "caption": "Puzzle Box: how far episodes get. Share of episodes (%) that reach each stage, on chain lengths 4 and 5, weighted as in Table 20. All bolts: every chain bolt was released at some point. Extracted: the item left the box. Gave up: the episode ended with a declared Stop or a text answer. Timeout: the episode ran out of decisions.",
    "rows": [
      [
        {
          "text": "Policy",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "All bolts",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Extracted",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Solved",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Gave up",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Timeout",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "94",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Covered",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "96",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "96",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "100",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Covered",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "47",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "40",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "35",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "65",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Gemini 3.8 Flash",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "No cover",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "39",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "39",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "28",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "67",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Covered",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "13",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "95",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  },
  {
    "number": 24,
    "id": "tab-cubes_direction",
    "label": "tab:cubes_direction",
    "caption": "Painted Cubes: direction of wrong-bin commitments. Cube counts by final outcome. A positive cube satisfies the rule and belongs in the blue bin. FN: positive in yellow; FP: negative in blue. FNR = FN/(TP+FN) and FPR = FP/(TN+FP) over committed cubes, in %, with 95% bootstrap intervals over episodes. Uncaptured cubes (positive / negative) are counted separately.",
    "rows": [
      [
        {
          "text": "Policy",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Rule",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "TP",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FN",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FNR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "TN",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FP",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "FPR",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Uncaptured",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "GPT-6 Astra",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Has a colour",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4.5 · [0.0, 16.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "49",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.5 · [0.0, 17.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7 / 4",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Has a shape",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "33.3 · [12.5, 55.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.1 · [2.5, 19.4]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2 / 2",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Has a colour + shape",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "55.0 · [23.8, 82.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "36",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7.7 · [0.0, 17.1]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2 / 7",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Exactly one mark",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "25",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3.8 · [0.0, 12.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "42",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.3 · [4.3, 25.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "7 / 14",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "All rules",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "65",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "18",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "21.7 · [11.9, 31.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "157",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "17",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.8 · [5.5, 14.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "18 / 27",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "Claude Fable 5.1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Has a colour",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "11",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "45.0 · [23.1, 64.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "50",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "1",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "2.0 · [0.0, 5.8]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9 / 6",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Has a shape",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "57.1 · [20.0, 83.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "26",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "0.0 · [0.0, 0.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3 / 9",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Has a colour + shape",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "52.6 · [27.3, 78.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "30",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "5",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "14.3 · [2.7, 30.6]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "3 / 11",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "Exactly one mark",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "15",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "8",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "34.8 · [21.1, 48.0]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "37",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "4",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "9.8 · [2.4, 18.9]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10 / 22",
          "colspan": 1,
          "bold": false
        }
      ],
      [
        {
          "text": "",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "All rules",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "41",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "35",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "46.1 · [34.2, 57.3]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "143",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "10",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "6.5 · [2.9, 10.7]",
          "colspan": 1,
          "bold": false
        },
        {
          "text": "25 / 48",
          "colspan": 1,
          "bold": false
        }
      ]
    ]
  }
]