Model: gemini-3-pro-preview

sample_run09

Select Configuration:

📊 Sample Metrics

🔍 Exploration

last_node_coverage: 1
last_edge_coverage: 0.585
n_exploration_steps: 18
action_counts:
move: 10
rotate: 10
return: 0
observe: 17
term: 1
forced_term: 0
query: 0
action_cost: 17
final_information_gain: 0.748
action_fail_ratio: 0.056
valid_action_ratio: 1
false_belief_steps: 10
false_belief_f1: 0.750
false_belief_f1_position: 0.800
false_belief_f1_facing: 0.667
false_belief_action_cost: 8
false_belief_action_cost_after_seen: None

✅ Evaluation

overall:
n_total: 27
total_score: 21.435
avg_accuracy: 0.794
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
PovEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
View2ActionTextEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.383
avg_accuracy: 0.794
RotEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
Location2ViewEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
View2LocationTextEvaluationTask:
n_total: 3
task_score: 1.552
avg_accuracy: 0.517

✅ Evaluation (prompt_cogmap)

overall:
n_total: 27
total_score: 18.856
avg_accuracy: 0.698
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
PovEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
View2ActionTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.139
avg_accuracy: 0.713
RotEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Location2ViewEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
View2LocationTextEvaluationTask:
n_total: 3
task_score: 1.217
avg_accuracy: 0.406

✅ Evaluation (use_gt_cogmap)

overall:
n_total: 27
total_score: 27
avg_accuracy: 1
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
PovEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
View2ActionTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
AlloMappingEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
RotEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Location2ViewEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
View2LocationTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1

✅ Evaluation (use_model_cogmap)

overall:
n_total: 27
total_score: 20.527
avg_accuracy: 0.760
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
PovEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
View2ActionTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.454
avg_accuracy: 0.818
RotEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Location2ViewEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
View2LocationTextEvaluationTask:
n_total: 3
task_score: 1.574
avg_accuracy: 0.525

🧠 Cognitive Map

exploration:
error:
local_vs_gt_local_avg:
dir: 0.902
facing: 1
pos: 0.855
overall: 0.919
global_vs_gt_global_avg:
dir: 0.768
facing: 0.754
pos: 0.743
overall: 0.755
agent_vs_gt_agent_avg:
dir: 0.444
facing: 1
pos: 0.736
overall: 0.727
newly_observed_vs_gt_local_avg:
dir: 0.873
facing: 1
pos: 0.894
overall: 0.922
correctness:
last_global_vs_gt_full:
dir: 0.867
facing: 1
pos: 0.744
overall: 0.870
consistency:
local_vs_global_avg:
dir: 0.657
facing: 0.857
pos: 0.784
overall: 0.766
position_update_avg: 0.664
facing_update_avg: 0.692
position_stability_avg: 0.664
facing_stability_avg: 0.692
fog_probe:
f1_avg: 0.599
precision_avg: 0.678
recall_avg: 0.594
cogmap_fb:
metrics:
changed:
dir: None
pos: 0.430
facing: 0
overall: None
retention:
dir: None
pos: 0.509
facing: 1
overall: None
unchanged:
dir: 0.436
facing: 0.574
pos: 0.538
overall: 0.516
inertia: 0.377
inertia_list: [0.3773423084209857]
unchanged_retention:
dir: None
pos: 0.737
facing: 0.800
overall: None
unchanged_retention_minus_retention:
pos: 0.523
facing: -0.562
unchanged_exploration:
dir: 0.855
facing: 1
pos: 0.750
overall: 0.868

🧭 False Belief CogMap

inertia: 0.377
changed:
dir: None
pos: 0.430
facing: 0
overall: None
retention:
dir: None
pos: 0.509
facing: 1
overall: None
unchanged:
dir: 0.436
facing: 0.574
pos: 0.538
overall: 0.516
unchanged_retention:
dir: None
pos: 0.737
facing: 0.800
overall: None
unchanged_retention_minus_retention:
pos: 0.523
facing: -0.562
unchanged_exploration:
dir: 0.855
facing: 1
pos: 0.750
overall: 0.868

📊 Performance Charts

Cognitive Map (Update)
Global Update Metrics
Cognitive Map (Full)
Global Full Metrics
Cognitive Map (Self-Tracking)
Global Self-Tracking Metrics
FB CogMap (Unchanged)
False Belief CogMap Unchanged per Turn
Fog Probe F1
Fog Probe F1 per Turn
Fog Probe Precision
Fog Probe Precision per Turn
Fog Probe Recall
Fog Probe Recall per Turn
Position Update
Position Update per Turn
Facing Update
Facing Update per Turn
Position Stability
Position Stability per Turn
Facing Stability
Facing Stability per Turn

🌍 Exploration Phase

🔄 Turn 1

💬 Assistant Action
Actions: [Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        1,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        1,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  }
}
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######+########
#....C.########
#...A.F#......#
#....*.#......#
#.E....#......#
#..D...+......#
#..B...#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: B, C, D, E
🎯 Ground Truth: E, B, D
🧠 Cognitive Map Metrics
Global:
dir: 1
facing: 1
pos: 1
overall: 1
Global (Full):
dir: 0.025
facing: 0.111
pos: 0.133
overall: 0.090
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
dir: 1
facing: 1
pos: 1
overall: 1
Fog Probe:
precision: 0.750
recall: 1
overall: 0.857
📈 Turn Metrics
node_coverage: 0.071
edge_coverage: 0.024
is_action_fail: False
step: 1
action_counts:
move: 0
rotate: 0
return: 0
observe: 1
term: 0
forced_term: 0
query: 0
information_gain: 0.071
reward: -0.100
is_done: False
is_valid_action: True
Current state
State at Turn 1

🔄 Turn 2

💬 Assistant Action
Actions: [JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ]
  },
  "plant": {
    "position": [
      0,
      7
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -1,
        2
      ],
      "facing": "+y"
    },
    "cap": {
      "position": [
        1,
        2
      ],
      "facing": "+x"
    },
    "basket": {
      "position": [
        1,
        4
      ]
    },
    "plant": {
      "position": [
        -1,
        4
      ]
    }
  }
}
🎯 Ground Truth
{
  "plant": {
    "position": [
      -1,
      6
    ],
    "facing": "east"
  },
  "cap": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      -1,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -1,
        2
      ],
      "facing": "+y"
    },
    "cap": {
      "position": [
        1,
        2
      ],
      "facing": "+x"
    },
    "basket": {
      "position": [
        1,
        4
      ]
    },
    "plant": {
      "position": [
        -1,
        4
      ]
    }
  }
}
🎯 Ground Truth
{
  "plant": {
    "position": [
      -1,
      6
    ],
    "facing": "east"
  },
  "cap": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      -1,
      2
    ],
    "facing": "north"
  }
}
🗺️ Symbolic Fog Map
###############
###.H....######
###......######
###......######
###.....D######
###I....A######
###C....G######
######*########
#....F.########
#....B.#......#
#...JE.#......#
#....K.#......#
#......+......#
#..L...#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: A, C, G, I, L
🎯 Ground Truth: L, K, J, G, C, I
🧠 Cognitive Map Metrics
Global:
dir: 0.952
facing: 1
pos: 0.871
overall: 0.941
Global (Full):
dir: 0.167
facing: 0.333
pos: 0.348
overall: 0.283
Local:
dir: 0.900
facing: 1
pos: 0.845
overall: 0.915
Local (Newly):
dir: 0.900
facing: 1
pos: 0.845
overall: 0.915
Fog Probe:
precision: 0.800
recall: 0.667
overall: 0.727
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.122
is_action_fail: False
step: 2
action_counts:
move: 1
rotate: 0
return: 0
observe: 2
term: 0
forced_term: 0
query: 0
information_gain: 0.332
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 2
Current state
State at Turn 2

🔄 Turn 3

💬 Assistant Action
Actions: [JumpTo(plant), Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      8
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ]
  },
  "plant": {
    "position": [
      0,
      8
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "basket": {
      "position": [
        1,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "basket": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "basket": {
      "position": [
        1,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###.H*...######
###.I....######
###.F....######
###......######
###G.....######
###D....J######
######+########
#......########
#...C.L#......#
#....B.#......#
#A.....#......#
#......+......#
#....KE#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: B, D, E, G, J, K, L
🎯 Ground Truth: K, E, A, J, G, D
🧠 Cognitive Map Metrics
Global:
dir: 1
facing: 1
pos: 0.907
overall: 0.969
Global (Full):
dir: 0.175
facing: 0.333
pos: 0.363
overall: 0.290
Local:
dir: 1
facing: 1
pos: 0.845
overall: 0.948
Local (Newly):
(none)
Fog Probe:
precision: 0.714
recall: 0.833
overall: 0.769
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.146
is_action_fail: False
step: 3
action_counts:
move: 2
rotate: 1
return: 0
observe: 3
term: 0
forced_term: 0
query: 0
information_gain: 0.343
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 3
Current state
State at Turn 3

🔄 Turn 4

💬 Assistant Action
Actions: [JumpTo(basket), Rotate(-90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      2,
      8
    ],
    "facing": "north"
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      8
    ]
  },
  "plant": {
    "position": [
      0,
      10
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      7
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      7
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "plant": {
      "position": [
        -1,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "plant": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "plant": {
      "position": [
        -1,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###..A...######
###...B*.######
###....I.######
###K.....######
###.D...E######
######+########
#...G.C########
#......#......#
#....F.#......#
#J.....#......#
#.....H+......#
#.L....#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: H, J, L
🎯 Ground Truth: J, H, L, E, D, K
🧠 Cognitive Map Metrics
Global:
dir: 0.952
facing: 1
pos: 0.887
overall: 0.947
Global (Full):
dir: 0.167
facing: 0.333
pos: 0.355
overall: 0.285
Local:
dir: 1
facing: 1
pos: 0.845
overall: 0.948
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 0.500
overall: 0.667
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.146
is_action_fail: False
step: 4
action_counts:
move: 3
rotate: 2
return: 0
observe: 4
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 4
Current state
State at Turn 4

🔄 Turn 5

💬 Assistant Action
Actions: [JumpTo(television), Rotate(-90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      3,
      7
    ],
    "facing": "north"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -1,
      4
    ],
    "facing": "east"
  },
  "cap": {
    "position": [
      3,
      4
    ],
    "facing": "west"
  },
  "basket": {
    "position": [
      3,
      7
    ]
  },
  "plant": {
    "position": [
      -1,
      8
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      7
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      7
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "plant": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "plant": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "plant": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###...L..######
###......######
###.K..*.######
###......######
###......######
###AG..BC######
######+########
#..E..F########
#..H.I.#......#
#..J...#......#
#......#......#
#D.....+......#
#......#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: J, I
🎯 Ground Truth: H, D, J, C, G, A
🧠 Cognitive Map Metrics
Global:
dir: 0.667
facing: 0.333
pos: 0.823
overall: 0.608
Global (Full):
dir: 0.117
facing: 0.111
pos: 0.329
overall: 0.186
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 0.167
overall: 0.250
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.146
is_action_fail: True
step: 5
action_counts:
move: 3
rotate: 2
return: 0
observe: 5
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 5
Current state
State at Turn 5

🔄 Turn 6

💬 Assistant Action
Actions: [JumpTo(plant), Rotate(180), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -2,
      8
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "television": {
    "position": [
      -2,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      8
    ]
  },
  "plant": {
    "position": [
      -2,
      8
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      9
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      9
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        0,
        3
      ],
      "facing": "-y"
    },
    "cap": {
      "position": [
        -4,
        5
      ],
      "facing": "-x"
    },
    "basket": {
      "position": [
        -3,
        3
      ]
    },
    "yellow door": {
      "position": [
        -2,
        6
      ]
    }
  }
}
🎯 Ground Truth
{
  "cap": {
    "position": [
      -2,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      6
    ],
    "facing": "north"
  },
  "basket": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      4
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        0,
        3
      ],
      "facing": "-y"
    },
    "cap": {
      "position": [
        -4,
        5
      ],
      "facing": "-x"
    },
    "basket": {
      "position": [
        -3,
        3
      ]
    },
    "yellow door": {
      "position": [
        -2,
        6
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###..*...######
###......######
###......######
###......######
###......######
###......######
######+########
#..A...########
#...B.E#......#
#......#......#
#F.....#......#
#..C..D+......#
#......#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, C
🎯 Ground Truth: F, C, D
🧠 Cognitive Map Metrics
Global:
dir: 0.810
facing: 1
pos: 0.766
overall: 0.858
Global (Full):
dir: 0.142
facing: 0.333
pos: 0.306
overall: 0.260
Local:
dir: 0.700
facing: 1
pos: 0.776
overall: 0.825
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.195
is_action_fail: False
step: 6
action_counts:
move: 4
rotate: 3
return: 0
observe: 6
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 6
Current state
State at Turn 6

🔄 Turn 7

💬 Assistant Action
Actions: [JumpTo(television), Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -2,
      6
    ],
    "facing": "west"
  },
  "yellow door": {
    "position": [
      1,
      4
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -2,
      6
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      4,
      6
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      4,
      9
    ]
  },
  "plant": {
    "position": [
      -2,
      10
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      5
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      5
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###..*...######
###......######
######+########
#....CB########
#..E...#......#
#....D.#......#
#.....F#......#
#A.....+......#
#......#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, E, F
🎯 Ground Truth: E, A, F
🧠 Cognitive Map Metrics
Global:
dir: 0.762
facing: 0.667
pos: 0.690
overall: 0.706
Global (Full):
dir: 0.133
facing: 0.222
pos: 0.276
overall: 0.211
Local:
(none)
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.195
is_action_fail: False
step: 7
action_counts:
move: 5
rotate: 4
return: 0
observe: 7
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 7
Current state
State at Turn 7

🔄 Turn 8

💬 Assistant Action
Actions: [Rotate(180), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -1,
      5
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -1,
      5
    ],
    "facing": "east"
  },
  "cap": {
    "position": [
      3,
      5
    ],
    "facing": "west"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "south"
  },
  "plant": {
    "position": [
      -1,
      9
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      5
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      5
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "cap": {
      "position": [
        0,
        2
      ],
      "facing": "+y"
    },
    "basket": {
      "position": [
        -2,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "cap": {
    "position": [
      0,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "cap": {
      "position": [
        0,
        2
      ],
      "facing": "+y"
    },
    "basket": {
      "position": [
        -2,
        3
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###..*...######
###......######
######+########
#......########
#....BC#......#
#....EF#......#
#.A....#......#
#......+......#
#.....D#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, C, D, E, F
🎯 Ground Truth: D, A, F
🧠 Cognitive Map Metrics
Global:
dir: 0.905
facing: 0.333
pos: 0.871
overall: 0.703
Global (Full):
dir: 0.158
facing: 0.111
pos: 0.348
overall: 0.206
Local:
dir: 0.667
facing: 1
pos: 0.887
overall: 0.851
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 1
overall: 0.667
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.244
is_action_fail: False
step: 8
action_counts:
move: 5
rotate: 5
return: 0
observe: 8
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 8
Current state
State at Turn 8

🔄 Turn 9

💬 Assistant Action
Actions: [JumpTo(cap), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "grid": "N x M",
  "agent": {
    "position": [
      3,
      6
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      2,
      4
    ]
  },
  "television": {
    "position": [
      1,
      6
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      3,
      6
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      3,
      8
    ]
  },
  "plant": {
    "position": [
      0,
      9
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###....*.######
###......######
######+########
#....C.########
#..EF.B#......#
#......#......#
#..D...#......#
#.A....+......#
#......#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, D
🎯 Ground Truth: D, E, A
🧠 Cognitive Map Metrics
Global:
dir: 0.810
facing: 0.667
pos: 0.804
overall: 0.760
Global (Full):
dir: 0.142
facing: 0.222
pos: 0.322
overall: 0.229
Local:
(none)
Local (Newly):
(none)
Fog Probe:
precision: 0.667
recall: 0.667
overall: 0.667
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.244
is_action_fail: False
step: 9
action_counts:
move: 6
rotate: 5
return: 0
observe: 9
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 9
Current state
State at Turn 9

🔄 Turn 10

💬 Assistant Action
Actions: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      3,
      5
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      8
    ]
  },
  "plant": {
    "position": [
      0,
      8
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      5
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      5
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        1,
        2
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      1,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        1,
        2
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###....*.######
###......######
######+########
#.....D########
#..F.AB#......#
#......#......#
#......#......#
#.E....+......#
#.C....#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, C, D, E, F
🎯 Ground Truth: C, E, F
🧠 Cognitive Map Metrics
Global:
dir: 0.857
facing: 0.667
pos: 0.871
overall: 0.798
Global (Full):
dir: 0.150
facing: 0.222
pos: 0.348
overall: 0.240
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 1
overall: 0.667
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.244
is_action_fail: False
step: 10
action_counts:
move: 6
rotate: 6
return: 0
observe: 10
term: 0
forced_term: 0
query: 0
information_gain: 0.357
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 10
Current state
State at Turn 10

🔄 Turn 11

💬 Assistant Action
Actions: [JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      1,
      3
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      -2,
      6
    ],
    "facing": "west"
  },
  "cap": {
    "position": [
      4,
      6
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      3,
      9
    ],
    "facing": "north"
  },
  "plant": {
    "position": [
      -1,
      9
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      -2,
      0
    ],
    "facing": "west"
  },
  "backpack": {
    "position": [
      -3,
      0
    ],
    "facing": "north"
  },
  "brown door": {
    "position": [
      4,
      1
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      3
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      3
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "scooter": {
      "position": [
        2,
        6
      ],
      "facing": "-x"
    },
    "backpack": {
      "position": [
        4,
        4
      ],
      "facing": "+y"
    },
    "brown door": {
      "position": [
        -2,
        6
      ],
      "facing": "+x"
    }
  }
}
🎯 Ground Truth
{
  "backpack": {
    "position": [
      5,
      6
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      1,
      6
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      -1,
      5
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "scooter": {
      "position": [
        2,
        6
      ],
      "facing": "-x"
    },
    "backpack": {
      "position": [
        4,
        4
      ],
      "facing": "+y"
    },
    "brown door": {
      "position": [
        -2,
        6
      ],
      "facing": "+x"
    }
  }
}
🎯 Ground Truth
{
  "backpack": {
    "position": [
      5,
      6
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      1,
      6
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      -1,
      5
    ],
    "facing": "east"
  }
}
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######*########
#.D..F.########
#......#......#
#BE....#......#
#....A.#......#
#......+......#
#.....C#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: D, F
🎯 Ground Truth: D, E, B
🧠 Cognitive Map Metrics
Global:
dir: 0.667
facing: 0.400
pos: 0.666
overall: 0.578
Global (Full):
dir: 0.250
facing: 0.222
pos: 0.400
overall: 0.291
Local:
dir: 0.667
facing: 1
pos: 0.759
overall: 0.809
Local (Newly):
dir: 0.667
facing: 1
pos: 0.759
overall: 0.809
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.571
edge_coverage: 0.317
is_action_fail: False
step: 11
action_counts:
move: 7
rotate: 6
return: 0
observe: 11
term: 0
forced_term: 0
query: 0
information_gain: 0.490
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 11
Current state
State at Turn 11

🔄 Turn 12

💬 Assistant Action
Actions: [JumpTo(brown door), Rotate(-90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      4,
      1
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      -1,
      1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -2,
      2
    ],
    "facing": "south"
  },
  "brown door": {
    "position": [
      4,
      1
    ]
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "television": {
    "position": [
      -1,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      3,
      8
    ]
  },
  "plant": {
    "position": [
      -1,
      9
    ]
  },
  "chair": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "table": {
    "position": [
      7,
      -2
    ]
  },
  "toilet": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      7,
      3
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "chair": {
      "position": [
        1,
        5
      ],
      "facing": "+x"
    },
    "toilet": {
      "position": [
        -1,
        5
      ],
      "facing": "+y"
    },
    "table": {
      "position": [
        2,
        2
      ]
    },
    "bike": {
      "position": [
        -3,
        4
      ],
      "facing": "+y"
    }
  }
}
🎯 Ground Truth
{
  "table": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "chair": {
    "position": [
      1,
      4
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      -1,
      6
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      -3,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "chair": {
      "position": [
        1,
        5
      ],
      "facing": "+x"
    },
    "toilet": {
      "position": [
        -1,
        5
      ],
      "facing": "+y"
    },
    "table": {
      "position": [
        2,
        2
      ]
    },
    "bike": {
      "position": [
        -3,
        4
      ],
      "facing": "+y"
    }
  }
}
🎯 Ground Truth
{
  "table": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "chair": {
    "position": [
      1,
      4
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      -1,
      6
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      -3,
      4
    ],
    "facing": "east"
  }
}
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######+########
#C.....########
#......#FK....#
#LB...G#E.....#
#..D...#.H....#
#......*..I..A#
#..J...#......#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: E, F, K
🎯 Ground Truth: B, L, C, F, E, K
🧠 Cognitive Map Metrics
Global:
dir: 0.604
facing: 1
pos: 0.609
overall: 0.738
Global (Full):
dir: 0.458
facing: 0.889
pos: 0.528
overall: 0.625
Local:
dir: 0.800
facing: 1
pos: 0.864
overall: 0.888
Local (Newly):
dir: 0.800
facing: 1
pos: 0.864
overall: 0.888
Fog Probe:
precision: 1
recall: 0.500
overall: 0.667
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.415
is_action_fail: False
step: 12
action_counts:
move: 8
rotate: 7
return: 0
observe: 12
term: 0
forced_term: 0
query: 0
information_gain: 0.630
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 12
Current state
State at Turn 12

🔄 Turn 13

💬 Assistant Action
Actions: [JumpTo(table), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      7,
      0
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      1,
      1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      1,
      3
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      2,
      5
    ]
  },
  "brown door": {
    "position": [
      5,
      2
    ]
  },
  "television": {
    "position": [
      0,
      7
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      4,
      7
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      10
    ]
  },
  "basket": {
    "position": [
      4,
      10
    ]
  },
  "chair": {
    "position": [
      9,
      0
    ],
    "facing": "south"
  },
  "table": {
    "position": [
      7,
      0
    ]
  },
  "toilet": {
    "position": [
      7,
      4
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      4
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "chair": {
      "position": [
        0,
        2
      ],
      "facing": "+x"
    },
    "toilet": {
      "position": [
        -3,
        6
      ],
      "facing": "+y"
    }
  }
}
🎯 Ground Truth
{
  "chair": {
    "position": [
      0,
      2
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      -2,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "chair": {
      "position": [
        0,
        2
      ],
      "facing": "+x"
    },
    "toilet": {
      "position": [
        -3,
        6
      ],
      "facing": "+y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######+########
#......########
#KH....#.FG...#
#.J.B..#E.....#
#.D....#.C....#
#......+......#
#..I...#.*.L..#
########A.....#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: A, F, G
🎯 Ground Truth: H, K, J, F, A, E
🧠 Cognitive Map Metrics
Global:
dir: 0.604
facing: 1
pos: 0.497
overall: 0.700
Global (Full):
dir: 0.458
facing: 0.889
pos: 0.431
overall: 0.593
Local:
dir: 1
facing: 1
pos: 0.766
overall: 0.922
Local (Newly):
(none)
Fog Probe:
precision: 0.667
recall: 0.333
overall: 0.444
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.463
is_action_fail: False
step: 13
action_counts:
move: 9
rotate: 7
return: 0
observe: 13
term: 0
forced_term: 0
query: 0
information_gain: 0.633
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 13
Current state
State at Turn 13

🔄 Turn 14

💬 Assistant Action
Actions: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      6,
      0
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      0,
      3
    ],
    "facing": "north"
  },
  "brown door": {
    "position": [
      3,
      1
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      -2,
      5
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "south"
  },
  "plant": {
    "position": [
      -2,
      7
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      -2,
      1
    ],
    "facing": "west"
  },
  "backpack": {
    "position": [
      -3,
      2
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      6,
      0
    ],
    "facing": "east"
  },
  "chair": {
    "position": [
      8,
      0
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      7,
      3
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      3
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######+########
#.....I########
#.A....#EF....#
#DH....#J.....#
#.C....#.....L#
#......+...K..#
#.....G#.*.B..#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: A, E, F, L
🎯 Ground Truth: D, H, A, E, F, J
🧠 Cognitive Map Metrics
Global:
dir: 0.516
facing: 0.375
pos: 0.586
overall: 0.493
Global (Full):
dir: 0.392
facing: 0.333
pos: 0.508
overall: 0.411
Local:
(none)
Local (Newly):
(none)
Fog Probe:
precision: 0.750
recall: 0.500
overall: 0.600
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.463
is_action_fail: False
step: 14
action_counts:
move: 9
rotate: 8
return: 0
observe: 14
term: 0
forced_term: 0
query: 0
information_gain: 0.633
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 14
Current state
State at Turn 14

🔄 Turn 15

💬 Assistant Action
Actions: [Rotate(180), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      7,
      0
    ],
    "facing": "north"
  },
  "yellow door": {
    "position": [
      0,
      3
    ],
    "facing": "south"
  },
  "brown door": {
    "position": [
      4,
      0
    ],
    "facing": "west"
  },
  "television": {
    "position": [
      -2,
      5
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -2,
      7
    ]
  },
  "basket": {
    "position": [
      2,
      7
    ]
  },
  "scooter": {
    "position": [
      -2,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -2,
      1
    ],
    "facing": "south"
  },
  "table": {
    "position": [
      7,
      0
    ]
  },
  "chair": {
    "position": [
      9,
      0
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      7,
      3
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      9,
      3
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "bike": {
      "position": [
        4,
        4
      ],
      "facing": "+x"
    }
  }
}
🎯 Ground Truth
{
  "bike": {
    "position": [
      2,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "bike": {
      "position": [
        4,
        4
      ],
      "facing": "+x"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######+########
#AC.B..########
#......#......#
#.D....#......#
#...E..#......#
#...F..+......#
#......#.*....#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: D, F
🎯 Ground Truth: D, C, A
🧠 Cognitive Map Metrics
Global:
dir: 0.538
facing: 0.875
pos: 0.583
overall: 0.665
Global (Full):
dir: 0.408
facing: 0.778
pos: 0.505
overall: 0.564
Local:
dir: 1
facing: 1
pos: 0.713
overall: 0.904
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.488
is_action_fail: False
step: 15
action_counts:
move: 9
rotate: 9
return: 0
observe: 15
term: 0
forced_term: 0
query: 0
information_gain: 0.636
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 15
Current state
State at Turn 15

🔄 Turn 16

💬 Assistant Action
Actions: [Rotate(-90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      6,
      0
    ],
    "facing": "west"
  },
  "yellow door": {
    "position": [
      0,
      3
    ],
    "facing": "north"
  },
  "brown door": {
    "position": [
      3,
      1
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      -2,
      -2
    ],
    "facing": "left"
  },
  "backpack": {
    "position": [
      -2,
      2
    ],
    "facing": "forward"
  },
  "television": {
    "position": [
      -2,
      5
    ],
    "facing": "backward"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "left"
  },
  "basket": {
    "position": [
      2,
      8
    ],
    "facing": "north"
  },
  "plant": {
    "position": [
      -2,
      8
    ],
    "facing": "south"
  },
  "table": {
    "position": [
      6,
      0
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      8,
      0
    ],
    "facing": "right"
  },
  "toilet": {
    "position": [
      7,
      2
    ],
    "facing": "forward"
  },
  "bike": {
    "position": [
      8,
      3
    ],
    "facing": "right"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      4,
      -3
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "brown door": {
      "position": [
        2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "brown door": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "brown door": {
      "position": [
        2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
###......######
###......######
###......######
###......######
###......######
###......######
######+########
#.....A########
#.....E#......#
#DC....#......#
#B..F..#......#
#......+......#
#......#.*....#
########......#
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, C
🎯 Ground Truth: C, D, B
🧠 Cognitive Map Metrics
Global:
dir: 0.659
facing: 0.250
pos: 0.609
overall: 0.506
Global (Full):
dir: 0.500
facing: 0.222
pos: 0.528
overall: 0.417
Local:
dir: 1
facing: 1
pos: 0.788
overall: 0.929
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.488
is_action_fail: False
step: 16
action_counts:
move: 9
rotate: 10
return: 0
observe: 16
term: 0
forced_term: 0
query: 0
information_gain: 0.636
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 16
Current state
State at Turn 16

🔄 Turn 17

💬 Assistant Action
Actions: [JumpTo(brown door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "grid": "Small map of 3 rooms",
  "agent": {
    "position": [
      4,
      1
    ],
    "facing": "west"
  },
  "scooter": {
    "position": [
      0,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -1,
      0
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      2,
      3
    ]
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "brown door": {
    "position": [
      4,
      1
    ]
  },
  "television": {
    "position": [
      -2,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      3,
      8
    ]
  },
  "plant": {
    "position": [
      -2,
      8
    ]
  },
  "table": {
    "position": [
      6,
      -1
    ]
  },
  "chair": {
    "position": [
      8,
      -1
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      8,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "scooter": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    },
    "shoes": {
      "position": [
        1,
        6
      ],
      "facing": "-x"
    },
    "backpack": {
      "position": [
        -1,
        6
      ],
      "facing": "-x"
    },
    "wine": {
      "position": [
        3,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "shoes": {
    "position": [
      1,
      6
    ],
    "facing": "south"
  },
  "backpack": {
    "position": [
      -1,
      6
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      -1,
      2
    ],
    "facing": "east"
  },
  "wine": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "scooter": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    },
    "shoes": {
      "position": [
        1,
        6
      ],
      "facing": "-x"
    },
    "backpack": {
      "position": [
        -1,
        6
      ],
      "facing": "-x"
    },
    "wine": {
      "position": [
        3,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "shoes": {
    "position": [
      1,
      6
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.650
facing: 1
pos: 0.586
overall: 0.745
Global (Full):
dir: 0.650
facing: 1
pos: 0.586
overall: 0.745
Local:
dir: 0.900
facing: 1
pos: 0.887
overall: 0.929
Local (Newly):
dir: 1
facing: 1
pos: 1
overall: 1
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.585
is_action_fail: False
step: 17
action_counts:
move: 10
rotate: 10
return: 0
observe: 17
term: 0
forced_term: 0
query: 0
information_gain: 0.748
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 17
Current state
State at Turn 17

🔄 Turn 18

💬 Assistant Action
Actions: [Term()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      2,
      0
    ],
    "facing": "west"
  },
  "yellow door": {
    "position": [
      1,
      3
    ]
  },
  "brown door": {
    "position": [
      2,
      0
    ]
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ]
  },
  "plant": {
    "position": [
      0,
      9
    ]
  },
  "chair": {
    "position": [
      5,
      -1
    ],
    "facing": "south"
  },
  "toilet": {
    "position": [
      8,
      1
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -2
    ]
  },
  "bike": {
    "position": [
      6,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      0,
      -2
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -2,
      -1
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -1,
      1
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -1,
      2
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "scooter": {
    "position": [
      0,
      -3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      5
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      6,
      -3
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      -4,
      -1
    ],
    "facing": "south"
  },
  "cap": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "toilet": {
    "position": [
      8,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      -4,
      -3
    ],
    "facing": "south"
  },
  "wine": {
    "position": [
      -3,
      1
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      2,
      7
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      4,
      -3
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      0,
      9
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "brown door": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      3
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "west"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.867
facing: 1
pos: 0.744
overall: 0.870
Global (Full):
dir: 0.867
facing: 1
pos: 0.744
overall: 0.870
Local:
(none)
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.585
is_action_fail: False
step: 18
action_counts:
move: 10
rotate: 10
return: 0
observe: 17
term: 1
forced_term: 0
query: 0
information_gain: 0.748
reward: -0.100
is_done: True
is_valid_action: True
Previous state
State before Turn 18
Current state
State at Turn 18

🧭 False Belief Exploration

🔄 FB Turn 19

💬 Assistant Action
Actions: [Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.409
facing: 0.667
pos: 0.565
overall: 0.547
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 1
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['yellow door']
Current state
State at Turn 1

🔄 FB Turn 20

💬 Assistant Action
Actions: [JumpTo(yellow door), Rotate(180), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: television:
dir: None
pos: 0.430
facing: None
overall: None
Retention: television:
dir: None
pos: 0.509
facing: None
overall: None
Changed: backpack:
dir: None
pos: None
facing: 0
overall: None
Retention: backpack:
dir: None
pos: None
facing: 1
overall: None
Unchanged (all):
dir: 0.455
facing: 0.500
pos: 0.523
overall: 0.493
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): ['backpack', 'television']
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: ['backpack', 'television']
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 2
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['television', 'backpack']
newly_observed_unchanged_objects: ['brown door', 'scooter']
Previous state
State before Turn 2
Current state
State at Turn 2

🔄 FB Turn 21

💬 Assistant Action
Actions: [Rotate(180), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.455
facing: 0.500
pos: 0.476
overall: 0.477
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 3
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['cap', 'basket']
Previous state
State before Turn 3
Current state
State at Turn 3

🔄 FB Turn 22

💬 Assistant Action
Actions: [JumpTo(basket), Rotate(-90), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.364
facing: 0.667
pos: 0.493
overall: 0.508
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 4
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 4
Current state
State at Turn 4

🔄 FB Turn 23

💬 Assistant Action
Actions: [Rotate(180), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.439
facing: 0.667
pos: 0.536
overall: 0.547
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 5
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 5
Current state
State at Turn 5

🔄 FB Turn 24

💬 Assistant Action
Actions: [Rotate(-90), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.439
facing: 0.833
pos: 0.549
overall: 0.607
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 6
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 6
Current state
State at Turn 6

🔄 FB Turn 25

💬 Assistant Action
Actions: [Rotate(90), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.424
facing: 0.333
pos: 0.581
overall: 0.446
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 7
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 7
Current state
State at Turn 7

🔄 FB Turn 26

💬 Assistant Action
Actions: [Query(yellow door)]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.364
facing: 0.667
pos: 0.511
overall: 0.514
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 8
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 8
Current state
State at Turn 8

🔄 FB Turn 27

💬 Assistant Action
Actions: [Rotate(45), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.576
facing: 0.333
pos: 0.609
overall: 0.506
🧾 False Belief Object Sets
all_objects: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
all_changed_objects: ['backpack', 'chair', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'bike', 'brown door', 'cap', 'scooter', 'shoes', 'table', 'toilet', 'wine', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'basket', 'bike', 'brown door', 'cap', 'chair', 'plant', 'scooter', 'shoes', 'table', 'television', 'toilet', 'wine', 'yellow door']
🧭 False Belief Info
step: 9
correctly_identified_changes: None
f1_overall: None
f1_position: None
f1_facing: None
action_cost: None
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 9
Current state
State at Turn 9

🔄 FB Turn 28

💬 Assistant Action
Actions: [Term(changes="backpack: orientation, television: position, plant: position, basket: position")]
📈 Turn Metrics
reward: 0.750
is_done: True
is_valid_action: True
success: 0.750
🧭 False Belief Info
step: 10
correctly_identified_changes: 0.750
f1_overall: 0.750
f1_position: 0.800
f1_facing: 0.667
action_cost: 8
action_cost_after_seen: None
ground_truth_changes: [{'name': 'chair', 'ori': True}, {'name': 'backpack', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'television', 'pos': True}]
reported_changes: [{'name': 'backpack', 'ori': True}, {'name': 'television', 'pos': True}, {'name': 'plant', 'pos': True}, {'name': 'basket', 'pos': True}]
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 10
Current state
State at Turn 10

📊 Evaluation (default)

📊 Task: DirectionEvaluationTask

Question 1 (ID: 2a3ea1ab8ec1bd26)

✅ Evaluation Results
id: 2a3ea1ab8ec1bd26
question: You return to your starting position and face north. From a Top-Down map, describe where wine is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: f7b63fa7e2d19d32)

✅ Evaluation Results
id: f7b63fa7e2d19d32
question: You return to your starting position and face north. From a Top-Down map, describe where table is relative to television. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 093963cbd99a1c04)

✅ Evaluation Results
id: 093963cbd99a1c04
question: You return to your starting position and face north. From a Top-Down map, describe where toilet is relative to scooter. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3976e12c4008e19b)

✅ Evaluation Results
id: 3976e12c4008e19b
question: Now you jump to shoes's direction, facing its direction. Describe where backpack is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: c74b1f5f919fdbbc)

✅ Evaluation Results
id: c74b1f5f919fdbbc
question: Now you jump to television's direction, facing its direction. Describe where basket is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 20fcddf7da613597)

✅ Evaluation Results
id: 20fcddf7da613597
question: Now you jump to television's direction, facing its direction. Describe where plant is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 221e1938c962c6af)

✅ Evaluation Results
id: 221e1938c962c6af
question: Now you jump to an object's position, facing its direction. You observe that basket is front-right, mid distance; plant is front, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: television
final_pos: [5, 10]
final_ori: [0, 1]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'plant', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 2
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: default
Evaluation state
Q1: BackwardPovTextEvaluationTask

Question 2 (ID: b042fd780599b324)

✅ Evaluation Results
id: b042fd780599b324
question: Now you jump to an object's position, facing its direction. You observe that toilet is front-right, mid distance, facing forward. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: bike
final_pos: [11, 6]
final_ori: [1, 0]
final_observation: [{'name': 'toilet', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: default
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: b331cdf635e89588)

✅ Evaluation Results
id: b331cdf635e89588
question: Now you jump to an object's position, facing its direction. You observe that brown door is front-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [5, 2]
final_ori: [1, 0]
final_observation: [{'name': 'brown door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: default
Evaluation state
Q3: BackwardPovTextEvaluationTask

📊 Task: Action2ViewEvaluationTask

Question 1 (ID: 79708c6ef79fe3f2)

✅ Evaluation Results
id: 79708c6ef79fe3f2
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-slight-right, mid distance. 2. Jump to the object at front-slight-left, slightly far. 3. Rotate(90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: Action2ViewEvaluationTask

Question 2 (ID: 52fe3e3f1a964c59)

✅ Evaluation Results
id: 52fe3e3f1a964c59
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-90) 2. Jump to the object at front-slight-right, mid distance. 3. Rotate(-180) 4. Jump to the object at front-left, slightly far. 5. Rotate(-90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 26bdb606439e4c23)

✅ Evaluation Results
id: 26bdb606439e4c23
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(90) 2. Jump to the object at front-right, mid distance. 3. Jump to the object at front-right, mid distance. After executing the actions, what is the ego relation of chair relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: e845c6e72911adc5)

✅ Evaluation Results
id: e845c6e72911adc5
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: scooter is at front-left, mid distance, facing backward; shoes is at front-slight-right, slightly far, facing left; wine is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 3]
final_ori: [-1, 0]
room_id: [1, 3]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'scooter', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'shoes', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 3.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: default
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 9e96f120288b1fd3)

✅ Evaluation Results
id: 9e96f120288b1fd3
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: basket is at front-right, mid distance What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [5, 14]
final_ori: [1, 0]
room_id: 2
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 90]]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
error: invalid_format
score: 0
evaluation_mode: default
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 58129cad65341385)

✅ Evaluation Results
id: 58129cad65341385
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: cap is at front-right, mid distance, facing right; basket is at front-slight-right, slightly far; plant is at front-slight-left, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [6, 8]
final_ori: [0, 1]
room_id: [1, 2]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'initial_pos']]
final_observation: [{'name': 'cap', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'basket', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'plant', 'direction': 'front-slight-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [6.0, 8.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: default
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 77fee2388e671ed1)

✅ Evaluation Results
id: 77fee2388e671ed1
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: wine, chair, backpack, plant, table. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, 1], [6, -3], [-4, -3], [0, 9], [4, -3]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.668
threshold: 0.900
score: 0.668
evaluation_mode: default
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 86e022f45899546e)

✅ Evaluation Results
id: 86e022f45899546e
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, television, backpack, toilet. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[4, -3], [0, 5], [-4, -3], [8, -1]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.844
threshold: 0.900
score: 0.844
evaluation_mode: default
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 5f8f2517c700a2b9)

✅ Evaluation Results
id: 5f8f2517c700a2b9
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: toilet, scooter, chair, television, plant. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[8, -1], [0, -3], [6, -3], [0, 5], [0, 9]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.872
threshold: 0.900
score: 0.872
evaluation_mode: default
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: c9f33275797c1371)

✅ Evaluation Results
id: c9f33275797c1371
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning clockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: basket, bike, scooter, shoes, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['basket', 'bike', 'table', 'scooter', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: 88f524a1ea9bb292)

✅ Evaluation Results
id: 88f524a1ea9bb292
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: fa85ac27ecb06dfa)

✅ Evaluation Results
id: fa85ac27ecb06dfa
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, table, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter', 'table']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q3: RotEvaluationTask

📊 Task: RotDualEvaluationTask

Question 1 (ID: b72c000118d6dabd)

✅ Evaluation Results
id: b72c000118d6dabd
question: You return to your starting position and face north. You performed a complete 360° rotation in place. Assume all walls are removed (you can see through walls), so every object is visible. During the rotation, these objects appeared directly in front of you in this order: basket, bike, table, scooter, shoes Based on this sequence, in which direction did you rotate? Answer format: clockwise or counterclockwise Example: clockwise
action: None
answer: clockwise
task_type: RotDualEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: RotDualEvaluationTask

Question 2 (ID: 08504c64e20ddfdb)

✅ Evaluation Results
id: 08504c64e20ddfdb
question: You return to your starting position and face north. You performed a complete 360° rotation in place. Assume all walls are removed (you can see through walls), so every object is visible. During the rotation, these objects appeared directly in front of you in this order: wine, backpack, scooter Based on this sequence, in which direction did you rotate? Answer format: clockwise or counterclockwise Example: clockwise
action: None
answer: counterclockwise
task_type: RotDualEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q2: RotDualEvaluationTask

Question 3 (ID: 36155bdbf69a1da7)

✅ Evaluation Results
id: 36155bdbf69a1da7
question: You return to your starting position and face north. You performed a complete 360° rotation in place. Assume all walls are removed (you can see through walls), so every object is visible. During the rotation, these objects appeared directly in front of you in this order: wine, backpack, scooter, table Based on this sequence, in which direction did you rotate? Answer format: clockwise or counterclockwise Example: clockwise
action: None
answer: counterclockwise
task_type: RotDualEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: RotDualEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: efa7a1eae6c023bd)

✅ Evaluation Results
id: efa7a1eae6c023bd
question: Still treat your initial position as origin (0, 0) You move to (1, -3) and face north. What is the egocentric relation of wine? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 29dc2089738c91f3)

✅ Evaluation Results
id: 29dc2089738c91f3
question: Treat the brown door as the new 'origin' (0, 0). You move to (5, -2) and face west. What is the egocentric relation of chair? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, near
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 0f994784bf1c8d5b)

✅ Evaluation Results
id: 0f994784bf1c8d5b
question: Still treat your initial position as origin (0, 0) You move to (-1, 0) and face west. What is the egocentric relation of shoes? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-left, mid distance
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3943df1f7c7f8b07)

✅ Evaluation Results
id: 3943df1f7c7f8b07
question: You move to a new location and face north. You observe: wine is at front-left, slightly far; brown door is at front-right, near, on right wall; yellow door is at front, slightly far, on front wall Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [1, -3]
final_pos: [6, 2]
final_ori: [0, 1]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'wine', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}, {'name': 'brown door', 'direction': 'front-right', 'distance': 'near', 'orientation': 'on right wall'}, {'name': 'yellow door', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.493
raw_score: 0.493
score: 0.493
evaluation_mode: default
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: f08df2fab1aea39f)

✅ Evaluation Results
id: f08df2fab1aea39f
question: You move to a new location and face west. You observe: chair is at front-right, near, facing left; table is at front-slight-right, mid distance; brown door is at front-slight-right, slightly far, on front wall Treat the brown door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [5, -2]
final_pos: [12, 1]
final_ori: [-1, 0]
room_id: 3
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'chair', 'direction': 'front-right', 'distance': 'near', 'orientation': 'facing left'}, {'name': 'table', 'direction': 'front-slight-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'brown door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: default
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: ce196c535efde5f3)

✅ Evaluation Results
id: ce196c535efde5f3
question: You move to a new location and face west. You observe: shoes is at front-slight-left, mid distance, facing left; backpack is at front-left, slightly far, facing left; wine is at front-right, mid distance Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-1, 0]
final_pos: [4, 5]
final_ori: [-1, 0]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'shoes', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing left'}, {'name': 'backpack', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.059
raw_score: 0.059
score: 0.059
evaluation_mode: default
Evaluation state
Q3: View2LocationTextEvaluationTask

📊 Evaluation (prompt_cogmap)

📊 Task: DirectionEvaluationTask

Question 1 (ID: 2a3ea1ab8ec1bd26)

✅ Evaluation Results
id: 2a3ea1ab8ec1bd26
question: You return to your starting position and face north. From a Top-Down map, describe where wine is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: f7b63fa7e2d19d32)

✅ Evaluation Results
id: f7b63fa7e2d19d32
question: You return to your starting position and face north. From a Top-Down map, describe where table is relative to television. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 093963cbd99a1c04)

✅ Evaluation Results
id: 093963cbd99a1c04
question: You return to your starting position and face north. From a Top-Down map, describe where toilet is relative to scooter. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3976e12c4008e19b)

✅ Evaluation Results
id: 3976e12c4008e19b
question: Now you jump to shoes's direction, facing its direction. Describe where backpack is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: c74b1f5f919fdbbc)

✅ Evaluation Results
id: c74b1f5f919fdbbc
question: Now you jump to television's direction, facing its direction. Describe where basket is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 20fcddf7da613597)

✅ Evaluation Results
id: 20fcddf7da613597
question: Now you jump to television's direction, facing its direction. Describe where plant is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 221e1938c962c6af)

✅ Evaluation Results
id: 221e1938c962c6af
question: Now you jump to an object's position, facing its direction. You observe that basket is front-right, mid distance; plant is front, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: television
final_pos: [5, 10]
final_ori: [0, 1]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'plant', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 2
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: BackwardPovTextEvaluationTask

Question 2 (ID: b042fd780599b324)

✅ Evaluation Results
id: b042fd780599b324
question: Now you jump to an object's position, facing its direction. You observe that toilet is front-right, mid distance, facing forward. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: bike
final_pos: [11, 6]
final_ori: [1, 0]
final_observation: [{'name': 'toilet', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: b331cdf635e89588)

✅ Evaluation Results
id: b331cdf635e89588
question: Now you jump to an object's position, facing its direction. You observe that brown door is front-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [5, 2]
final_ori: [1, 0]
final_observation: [{'name': 'brown door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: BackwardPovTextEvaluationTask

📊 Task: Action2ViewEvaluationTask

Question 1 (ID: 79708c6ef79fe3f2)

✅ Evaluation Results
id: 79708c6ef79fe3f2
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-slight-right, mid distance. 2. Jump to the object at front-slight-left, slightly far. 3. Rotate(90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: Action2ViewEvaluationTask

Question 2 (ID: 52fe3e3f1a964c59)

✅ Evaluation Results
id: 52fe3e3f1a964c59
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-90) 2. Jump to the object at front-slight-right, mid distance. 3. Rotate(-180) 4. Jump to the object at front-left, slightly far. 5. Rotate(-90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 26bdb606439e4c23)

✅ Evaluation Results
id: 26bdb606439e4c23
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(90) 2. Jump to the object at front-right, mid distance. 3. Jump to the object at front-right, mid distance. After executing the actions, what is the ego relation of chair relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: e845c6e72911adc5)

✅ Evaluation Results
id: e845c6e72911adc5
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: scooter is at front-left, mid distance, facing backward; shoes is at front-slight-right, slightly far, facing left; wine is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 3]
final_ori: [-1, 0]
room_id: [1, 3]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'scooter', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'shoes', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 3.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 9e96f120288b1fd3)

✅ Evaluation Results
id: 9e96f120288b1fd3
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: basket is at front-right, mid distance What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [5, 14]
final_ori: [1, 0]
room_id: 2
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 90]]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 14.0]
final_ori: [1, 0]
visible_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 58129cad65341385)

✅ Evaluation Results
id: 58129cad65341385
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: cap is at front-right, mid distance, facing right; basket is at front-slight-right, slightly far; plant is at front-slight-left, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [6, 8]
final_ori: [0, 1]
room_id: [1, 2]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'initial_pos']]
final_observation: [{'name': 'cap', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'basket', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'plant', 'direction': 'front-slight-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [6.0, 8.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 77fee2388e671ed1)

✅ Evaluation Results
id: 77fee2388e671ed1
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: wine, chair, backpack, plant, table. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, 1], [6, -3], [-4, -3], [0, 9], [4, -3]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.724
threshold: 0.900
score: 0.724
evaluation_mode: prompt_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 86e022f45899546e)

✅ Evaluation Results
id: 86e022f45899546e
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, television, backpack, toilet. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[4, -3], [0, 5], [-4, -3], [8, -1]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.672
threshold: 0.900
score: 0.672
evaluation_mode: prompt_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 5f8f2517c700a2b9)

✅ Evaluation Results
id: 5f8f2517c700a2b9
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: toilet, scooter, chair, television, plant. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[8, -1], [0, -3], [6, -3], [0, 5], [0, 9]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.743
threshold: 0.900
score: 0.743
evaluation_mode: prompt_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: c9f33275797c1371)

✅ Evaluation Results
id: c9f33275797c1371
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning clockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: basket, bike, scooter, shoes, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['basket', 'bike', 'table', 'scooter', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: 88f524a1ea9bb292)

✅ Evaluation Results
id: 88f524a1ea9bb292
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: fa85ac27ecb06dfa)

✅ Evaluation Results
id: fa85ac27ecb06dfa
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, table, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter', 'table']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: efa7a1eae6c023bd)

✅ Evaluation Results
id: efa7a1eae6c023bd
question: Still treat your initial position as origin (0, 0) You move to (1, -3) and face north. What is the egocentric relation of wine? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 29dc2089738c91f3)

✅ Evaluation Results
id: 29dc2089738c91f3
question: Treat the brown door as the new 'origin' (0, 0). You move to (5, -2) and face west. What is the egocentric relation of chair? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 0f994784bf1c8d5b)

✅ Evaluation Results
id: 0f994784bf1c8d5b
question: Still treat your initial position as origin (0, 0) You move to (-1, 0) and face west. What is the egocentric relation of shoes? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-left, mid distance
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3943df1f7c7f8b07)

✅ Evaluation Results
id: 3943df1f7c7f8b07
question: You move to a new location and face north. You observe: wine is at front-left, slightly far; brown door is at front-right, near, on right wall; yellow door is at front, slightly far, on front wall Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [1, -3]
final_pos: [6, 2]
final_ori: [0, 1]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'wine', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}, {'name': 'brown door', 'direction': 'front-right', 'distance': 'near', 'orientation': 'on right wall'}, {'name': 'yellow door', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.368
raw_score: 0.368
score: 0.368
evaluation_mode: prompt_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: f08df2fab1aea39f)

✅ Evaluation Results
id: f08df2fab1aea39f
question: You move to a new location and face west. You observe: chair is at front-right, near, facing left; table is at front-slight-right, mid distance; brown door is at front-slight-right, slightly far, on front wall Treat the brown door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [5, -2]
final_pos: [12, 1]
final_ori: [-1, 0]
room_id: 3
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'chair', 'direction': 'front-right', 'distance': 'near', 'orientation': 'facing left'}, {'name': 'table', 'direction': 'front-slight-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'brown door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.831
raw_score: 0.831
score: 0.831
evaluation_mode: prompt_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: ce196c535efde5f3)

✅ Evaluation Results
id: ce196c535efde5f3
question: You move to a new location and face west. You observe: shoes is at front-slight-left, mid distance, facing left; backpack is at front-left, slightly far, facing left; wine is at front-right, mid distance Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-1, 0]
final_pos: [4, 5]
final_ori: [-1, 0]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'shoes', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing left'}, {'name': 'backpack', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.018
raw_score: 0.018
score: 0.018
evaluation_mode: prompt_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask

📊 Evaluation (use_gt_cogmap)

📊 Task: DirectionEvaluationTask

Question 1 (ID: 2a3ea1ab8ec1bd26)

✅ Evaluation Results
id: 2a3ea1ab8ec1bd26
question: You return to your starting position and face north. From a Top-Down map, describe where wine is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: f7b63fa7e2d19d32)

✅ Evaluation Results
id: f7b63fa7e2d19d32
question: You return to your starting position and face north. From a Top-Down map, describe where table is relative to television. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 093963cbd99a1c04)

✅ Evaluation Results
id: 093963cbd99a1c04
question: You return to your starting position and face north. From a Top-Down map, describe where toilet is relative to scooter. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3976e12c4008e19b)

✅ Evaluation Results
id: 3976e12c4008e19b
question: Now you jump to shoes's direction, facing its direction. Describe where backpack is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: c74b1f5f919fdbbc)

✅ Evaluation Results
id: c74b1f5f919fdbbc
question: Now you jump to television's direction, facing its direction. Describe where basket is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 20fcddf7da613597)

✅ Evaluation Results
id: 20fcddf7da613597
question: Now you jump to television's direction, facing its direction. Describe where plant is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 221e1938c962c6af)

✅ Evaluation Results
id: 221e1938c962c6af
question: Now you jump to an object's position, facing its direction. You observe that basket is front-right, mid distance; plant is front, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: television
final_pos: [5, 10]
final_ori: [0, 1]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'plant', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 2
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: BackwardPovTextEvaluationTask

Question 2 (ID: b042fd780599b324)

✅ Evaluation Results
id: b042fd780599b324
question: Now you jump to an object's position, facing its direction. You observe that toilet is front-right, mid distance, facing forward. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: bike
final_pos: [11, 6]
final_ori: [1, 0]
final_observation: [{'name': 'toilet', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: b331cdf635e89588)

✅ Evaluation Results
id: b331cdf635e89588
question: Now you jump to an object's position, facing its direction. You observe that brown door is front-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [5, 2]
final_ori: [1, 0]
final_observation: [{'name': 'brown door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: BackwardPovTextEvaluationTask

📊 Task: Action2ViewEvaluationTask

Question 1 (ID: 79708c6ef79fe3f2)

✅ Evaluation Results
id: 79708c6ef79fe3f2
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-slight-right, mid distance. 2. Jump to the object at front-slight-left, slightly far. 3. Rotate(90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: Action2ViewEvaluationTask

Question 2 (ID: 52fe3e3f1a964c59)

✅ Evaluation Results
id: 52fe3e3f1a964c59
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-90) 2. Jump to the object at front-slight-right, mid distance. 3. Rotate(-180) 4. Jump to the object at front-left, slightly far. 5. Rotate(-90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 26bdb606439e4c23)

✅ Evaluation Results
id: 26bdb606439e4c23
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(90) 2. Jump to the object at front-right, mid distance. 3. Jump to the object at front-right, mid distance. After executing the actions, what is the ego relation of chair relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: e845c6e72911adc5)

✅ Evaluation Results
id: e845c6e72911adc5
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: scooter is at front-left, mid distance, facing backward; shoes is at front-slight-right, slightly far, facing left; wine is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 3]
final_ori: [-1, 0]
room_id: [1, 3]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'scooter', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'shoes', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 3.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 9e96f120288b1fd3)

✅ Evaluation Results
id: 9e96f120288b1fd3
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: basket is at front-right, mid distance What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [5, 14]
final_ori: [1, 0]
room_id: 2
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 90]]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 14.0]
final_ori: [1, 0]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 58129cad65341385)

✅ Evaluation Results
id: 58129cad65341385
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: cap is at front-right, mid distance, facing right; basket is at front-slight-right, slightly far; plant is at front-slight-left, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [6, 8]
final_ori: [0, 1]
room_id: [1, 2]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'initial_pos']]
final_observation: [{'name': 'cap', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'basket', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'plant', 'direction': 'front-slight-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [6.0, 8.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 77fee2388e671ed1)

✅ Evaluation Results
id: 77fee2388e671ed1
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: wine, chair, backpack, plant, table. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, 1], [6, -3], [-4, -3], [0, 9], [4, -3]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
threshold: 0.900
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 86e022f45899546e)

✅ Evaluation Results
id: 86e022f45899546e
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, television, backpack, toilet. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[4, -3], [0, 5], [-4, -3], [8, -1]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
threshold: 0.900
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 5f8f2517c700a2b9)

✅ Evaluation Results
id: 5f8f2517c700a2b9
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: toilet, scooter, chair, television, plant. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[8, -1], [0, -3], [6, -3], [0, 5], [0, 9]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
threshold: 0.900
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: c9f33275797c1371)

✅ Evaluation Results
id: c9f33275797c1371
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning clockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: basket, bike, scooter, shoes, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['basket', 'bike', 'table', 'scooter', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: 88f524a1ea9bb292)

✅ Evaluation Results
id: 88f524a1ea9bb292
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: fa85ac27ecb06dfa)

✅ Evaluation Results
id: fa85ac27ecb06dfa
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, table, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter', 'table']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: efa7a1eae6c023bd)

✅ Evaluation Results
id: efa7a1eae6c023bd
question: Still treat your initial position as origin (0, 0) You move to (1, -3) and face north. What is the egocentric relation of wine? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 29dc2089738c91f3)

✅ Evaluation Results
id: 29dc2089738c91f3
question: Treat the brown door as the new 'origin' (0, 0). You move to (5, -2) and face west. What is the egocentric relation of chair? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 0f994784bf1c8d5b)

✅ Evaluation Results
id: 0f994784bf1c8d5b
question: Still treat your initial position as origin (0, 0) You move to (-1, 0) and face west. What is the egocentric relation of shoes? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-left, mid distance
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3943df1f7c7f8b07)

✅ Evaluation Results
id: 3943df1f7c7f8b07
question: You move to a new location and face north. You observe: wine is at front-left, slightly far; brown door is at front-right, near, on right wall; yellow door is at front, slightly far, on front wall Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [1, -3]
final_pos: [6, 2]
final_ori: [0, 1]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'wine', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}, {'name': 'brown door', 'direction': 'front-right', 'distance': 'near', 'orientation': 'on right wall'}, {'name': 'yellow door', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: f08df2fab1aea39f)

✅ Evaluation Results
id: f08df2fab1aea39f
question: You move to a new location and face west. You observe: chair is at front-right, near, facing left; table is at front-slight-right, mid distance; brown door is at front-slight-right, slightly far, on front wall Treat the brown door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [5, -2]
final_pos: [12, 1]
final_ori: [-1, 0]
room_id: 3
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'chair', 'direction': 'front-right', 'distance': 'near', 'orientation': 'facing left'}, {'name': 'table', 'direction': 'front-slight-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'brown door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: ce196c535efde5f3)

✅ Evaluation Results
id: ce196c535efde5f3
question: You move to a new location and face west. You observe: shoes is at front-slight-left, mid distance, facing left; backpack is at front-left, slightly far, facing left; wine is at front-right, mid distance Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-1, 0]
final_pos: [4, 5]
final_ori: [-1, 0]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'shoes', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing left'}, {'name': 'backpack', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask

📊 Evaluation (use_model_cogmap)

📊 Task: DirectionEvaluationTask

Question 1 (ID: 2a3ea1ab8ec1bd26)

✅ Evaluation Results
id: 2a3ea1ab8ec1bd26
question: You return to your starting position and face north. From a Top-Down map, describe where wine is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: f7b63fa7e2d19d32)

✅ Evaluation Results
id: f7b63fa7e2d19d32
question: You return to your starting position and face north. From a Top-Down map, describe where table is relative to television. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 093963cbd99a1c04)

✅ Evaluation Results
id: 093963cbd99a1c04
question: You return to your starting position and face north. From a Top-Down map, describe where toilet is relative to scooter. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: east, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3976e12c4008e19b)

✅ Evaluation Results
id: 3976e12c4008e19b
question: Now you jump to shoes's direction, facing its direction. Describe where backpack is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: c74b1f5f919fdbbc)

✅ Evaluation Results
id: c74b1f5f919fdbbc
question: Now you jump to television's direction, facing its direction. Describe where basket is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 20fcddf7da613597)

✅ Evaluation Results
id: 20fcddf7da613597
question: Now you jump to television's direction, facing its direction. Describe where plant is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 221e1938c962c6af)

✅ Evaluation Results
id: 221e1938c962c6af
question: Now you jump to an object's position, facing its direction. You observe that basket is front-right, mid distance; plant is front, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: television
final_pos: [5, 10]
final_ori: [0, 1]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'plant', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 2
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: BackwardPovTextEvaluationTask

Question 2 (ID: b042fd780599b324)

✅ Evaluation Results
id: b042fd780599b324
question: Now you jump to an object's position, facing its direction. You observe that toilet is front-right, mid distance, facing forward. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: bike
final_pos: [11, 6]
final_ori: [1, 0]
final_observation: [{'name': 'toilet', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: b331cdf635e89588)

✅ Evaluation Results
id: b331cdf635e89588
question: Now you jump to an object's position, facing its direction. You observe that brown door is front-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [5, 2]
final_ori: [1, 0]
final_observation: [{'name': 'brown door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
scooter: [5.0, 2.0]
television: [5.0, 10.0]
chair: [11.0, 2.0]
shoes: [1.0, 4.0]
cap: [7.0, 10.0]
toilet: [13.0, 4.0]
backpack: [1.0, 2.0]
wine: [2.0, 6.0]
basket: [7.0, 12.0]
table: [9.0, 2.0]
plant: [5.0, 14.0]
bike: [11.0, 6.0]
brown door: [7.0, 3.0]
yellow door: [6.0, 8.0]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: BackwardPovTextEvaluationTask

📊 Task: Action2ViewEvaluationTask

Question 1 (ID: 79708c6ef79fe3f2)

✅ Evaluation Results
id: 79708c6ef79fe3f2
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-slight-right, mid distance. 2. Jump to the object at front-slight-left, slightly far. 3. Rotate(90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: Action2ViewEvaluationTask

Question 2 (ID: 52fe3e3f1a964c59)

✅ Evaluation Results
id: 52fe3e3f1a964c59
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-90) 2. Jump to the object at front-slight-right, mid distance. 3. Rotate(-180) 4. Jump to the object at front-left, slightly far. 5. Rotate(-90) After executing the actions, what is the ego relation of basket relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 26bdb606439e4c23)

✅ Evaluation Results
id: 26bdb606439e4c23
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(90) 2. Jump to the object at front-right, mid distance. 3. Jump to the object at front-right, mid distance. After executing the actions, what is the ego relation of chair relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: e845c6e72911adc5)

✅ Evaluation Results
id: e845c6e72911adc5
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: scooter is at front-left, mid distance, facing backward; shoes is at front-slight-right, slightly far, facing left; wine is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 3]
final_ori: [-1, 0]
room_id: [1, 3]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'scooter', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'shoes', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 3.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 9e96f120288b1fd3)

✅ Evaluation Results
id: 9e96f120288b1fd3
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: basket is at front-right, mid distance What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [5, 14]
final_ori: [1, 0]
room_id: 2
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 90]]
final_observation: [{'name': 'basket', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 14.0]
final_ori: [1, 0]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 58129cad65341385)

✅ Evaluation Results
id: 58129cad65341385
question: You return to your starting position and face north. Then you have executed an action sequence and changed to a new location and facing direction. You observe the following: cap is at front-right, mid distance, facing right; basket is at front-slight-right, slightly far; plant is at front-slight-left, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [6, 8]
final_ori: [0, 1]
room_id: [1, 2]
init_pos: [5, 5]
init_ori: [0, 1]
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
minimal_plan: [['jumpto', 'initial_pos']]
final_observation: [{'name': 'cap', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'basket', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'plant', 'direction': 'front-slight-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [6.0, 8.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 77fee2388e671ed1)

✅ Evaluation Results
id: 77fee2388e671ed1
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: wine, chair, backpack, plant, table. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, 1], [6, -3], [-4, -3], [0, 9], [4, -3]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.763
threshold: 0.900
score: 0.763
evaluation_mode: use_model_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 86e022f45899546e)

✅ Evaluation Results
id: 86e022f45899546e
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, television, backpack, toilet. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[4, -3], [0, 5], [-4, -3], [8, -1]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.819
threshold: 0.900
score: 0.819
evaluation_mode: use_model_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 5f8f2517c700a2b9)

✅ Evaluation Results
id: 5f8f2517c700a2b9
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: toilet, scooter, chair, television, plant. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[8, -1], [0, -3], [6, -3], [0, 5], [0, 9]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.872
threshold: 0.900
score: 0.872
evaluation_mode: use_model_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: c9f33275797c1371)

✅ Evaluation Results
id: c9f33275797c1371
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning clockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: basket, bike, scooter, shoes, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['basket', 'bike', 'table', 'scooter', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: 88f524a1ea9bb292)

✅ Evaluation Results
id: 88f524a1ea9bb292
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: fa85ac27ecb06dfa)

✅ Evaluation Results
id: fa85ac27ecb06dfa
question: You return to your starting position and face north. You will perform a full 360-degree rotation by continuously turning counterclockwise in place. Assume all walls are removed (you can see through walls), so every object is visible. Focus on this set of objects: backpack, scooter, table, wine. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['wine', 'backpack', 'scooter', 'table']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: efa7a1eae6c023bd)

✅ Evaluation Results
id: efa7a1eae6c023bd
question: Still treat your initial position as origin (0, 0) You move to (1, -3) and face north. What is the egocentric relation of wine? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 29dc2089738c91f3)

✅ Evaluation Results
id: 29dc2089738c91f3
question: Treat the brown door as the new 'origin' (0, 0). You move to (5, -2) and face west. What is the egocentric relation of chair? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 0f994784bf1c8d5b)

✅ Evaluation Results
id: 0f994784bf1c8d5b
question: Still treat your initial position as origin (0, 0) You move to (-1, 0) and face west. What is the egocentric relation of shoes? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-left, mid distance
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3943df1f7c7f8b07)

✅ Evaluation Results
id: 3943df1f7c7f8b07
question: You move to a new location and face north. You observe: wine is at front-left, slightly far; brown door is at front-right, near, on right wall; yellow door is at front, slightly far, on front wall Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [1, -3]
final_pos: [6, 2]
final_ori: [0, 1]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'wine', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}, {'name': 'brown door', 'direction': 'front-right', 'distance': 'near', 'orientation': 'on right wall'}, {'name': 'yellow door', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.531
raw_score: 0.531
score: 0.531
evaluation_mode: use_model_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: f08df2fab1aea39f)

✅ Evaluation Results
id: f08df2fab1aea39f
question: You move to a new location and face west. You observe: chair is at front-right, near, facing left; table is at front-slight-right, mid distance; brown door is at front-slight-right, slightly far, on front wall Treat the brown door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [5, -2]
final_pos: [12, 1]
final_ori: [-1, 0]
room_id: 3
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'chair', 'direction': 'front-right', 'distance': 'near', 'orientation': 'facing left'}, {'name': 'table', 'direction': 'front-slight-right', 'distance': 'mid distance', 'orientation': None}, {'name': 'brown door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: ce196c535efde5f3)

✅ Evaluation Results
id: ce196c535efde5f3
question: You move to a new location and face west. You observe: shoes is at front-slight-left, mid distance, facing left; backpack is at front-left, slightly far, facing left; wine is at front-right, mid distance Still treat your initial position as origin (0, 0) What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-1, 0]
final_pos: [4, 5]
final_ori: [-1, 0]
room_id: 1
object_positions:
scooter: [5, 2]
television: [5, 10]
chair: [11, 2]
shoes: [1, 4]
cap: [7, 10]
toilet: [13, 4]
backpack: [1, 2]
wine: [2, 6]
basket: [7, 12]
table: [9, 2]
plant: [5, 14]
bike: [11, 6]
brown door: [7, 3]
yellow door: [6, 8]
object_orientations:
scooter: [1, 0]
television: [0, 1]
chair: [0, -1]
shoes: [0, -1]
cap: [1, 0]
toilet: [1, 0]
backpack: [0, -1]
bike: [1, 0]
brown door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'shoes', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing left'}, {'name': 'backpack', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'wine', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
brown door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [1, 2]
ori_by_room:
1: [0, -1]
2: [0, 1]
object_rooms:
scooter: 1
television: 2
chair: 3
shoes: 1
cap: 2
toilet: 3
backpack: 1
wine: 1
basket: 2
table: 3
plant: 2
bike: 3
brown door: [1, 3]
yellow door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.042
raw_score: 0.042
score: 0.042
evaluation_mode: use_model_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask