Model: gemini-3-pro-preview

sample_run03

Select Configuration:

📊 Sample Metrics

🔍 Exploration

last_node_coverage: 1
last_edge_coverage: 0.561
n_exploration_steps: 17
action_counts:
move: 5
rotate: 10
return: 0
observe: 16
term: 1
forced_term: 0
query: 0
action_cost: 16
final_information_gain: 0.888
action_fail_ratio: 0.059
valid_action_ratio: 1
false_belief_steps: 10
false_belief_f1: 1
false_belief_f1_position: 1
false_belief_f1_facing: 1
false_belief_action_cost: 9
false_belief_action_cost_after_seen: 0

✅ Evaluation

overall:
n_total: 27
total_score: 22.634
avg_accuracy: 0.838
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 1.500
avg_accuracy: 0.500
PovEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
Action2ViewEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
View2ActionTextEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.634
avg_accuracy: 0.878
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 (prompt_cogmap)

overall:
n_total: 27
total_score: 19.586
avg_accuracy: 0.725
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 1.500
avg_accuracy: 0.500
PovEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
Action2ViewEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
View2ActionTextEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.668
avg_accuracy: 0.889
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: 2.418
avg_accuracy: 0.806

✅ Evaluation (use_gt_cogmap)

overall:
n_total: 27
total_score: 26.639
avg_accuracy: 0.987
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: 2.639
avg_accuracy: 0.880

✅ Evaluation (use_model_cogmap)

overall:
n_total: 27
total_score: 22.962
avg_accuracy: 0.850
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
PovEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
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: 2.544
avg_accuracy: 0.848
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: 2.418
avg_accuracy: 0.806

🧠 Cognitive Map

exploration:
error:
local_vs_gt_local_avg:
dir: 0.851
facing: 1
pos: 0.914
overall: 0.922
global_vs_gt_global_avg:
dir: 0.837
facing: 0.948
pos: 0.856
overall: 0.880
agent_vs_gt_agent_avg:
dir: 1
facing: 1
pos: 0.936
overall: 0.979
newly_observed_vs_gt_local_avg:
dir: 0.856
facing: 1
pos: 0.874
overall: 0.910
correctness:
last_global_vs_gt_full:
dir: 0.825
facing: 1
pos: 0.771
overall: 0.865
consistency:
local_vs_global_avg:
dir: 0.782
facing: 0.974
pos: 0.885
overall: 0.881
position_update_avg: 0.774
facing_update_avg: 0.936
position_stability_avg: 0.774
facing_stability_avg: 0.936
fog_probe:
f1_avg: 1
precision_avg: 1
recall_avg: 1
cogmap_fb:
metrics:
changed:
dir: None
pos: 0.904
facing: 0.500
overall: None
retention:
dir: None
pos: 0.367
facing: 0.500
overall: None
unchanged:
dir: 0.823
facing: 0.870
pos: 0.798
overall: 0.831
inertia: 0
inertia_list: [0.0]
unchanged_retention:
dir: None
pos: 0.788
facing: 1
overall: None
unchanged_retention_minus_retention:
pos: 0.784
facing: 0.750
unchanged_exploration:
dir: 0.873
facing: 1
pos: 0.780
overall: 0.884

🧭 False Belief CogMap

inertia: 0
changed:
dir: None
pos: 0.904
facing: 0.500
overall: None
retention:
dir: None
pos: 0.367
facing: 0.500
overall: None
unchanged:
dir: 0.823
facing: 0.870
pos: 0.798
overall: 0.831
unchanged_retention:
dir: None
pos: 0.788
facing: 1
overall: None
unchanged_retention_minus_retention:
pos: 0.784
facing: 0.750
unchanged_exploration:
dir: 0.873
facing: 1
pos: 0.780
overall: 0.884

📊 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"
  },
  "teddybear": {
    "position": [
      2,
      3
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "teddybear": {
      "position": [
        2,
        3
      ],
      "facing": "+x"
    },
    "bike": {
      "position": [
        2,
        5
      ],
      "facing": "+x"
    },
    "vase": {
      "position": [
        -2,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "teddybear": {
      "position": [
        2,
        3
      ],
      "facing": "+x"
    },
    "bike": {
      "position": [
        2,
        5
      ],
      "facing": "+x"
    },
    "vase": {
      "position": [
        -2,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  }
}
🗺️ Symbolic Fog Map
######################
#......###############
#......#......#......#
#......#..E...+......#
#......#..F...#......#
#......#A.B..C#......#
#......+..*...#......#
########.....D#......#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, C, D
🎯 Ground Truth: D, A, C
🧠 Cognitive Map Metrics
Global:
dir: 1
facing: 1
pos: 0.844
overall: 0.948
Global (Full):
dir: 0.083
facing: 0.333
pos: 0.225
overall: 0.214
Local:
dir: 1
facing: 1
pos: 0.822
overall: 0.941
Local (Newly):
dir: 1
facing: 1
pos: 0.822
overall: 0.941
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.214
edge_coverage: 0.073
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: 0.186
reward: -0.100
is_done: False
is_valid_action: True
Current state
State at Turn 1

🔄 Turn 2

💬 Assistant Action
Actions: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "east"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      2
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        0,
        3
      ],
      "facing": "+x"
    },
    "green door": {
      "position": [
        -3,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "green door": {
    "position": [
      -3,
      4
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      3
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        0,
        3
      ],
      "facing": "+x"
    },
    "green door": {
      "position": [
        -3,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "green door": {
    "position": [
      -3,
      4
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      3
    ],
    "facing": "south"
  }
}
🗺️ Symbolic Fog Map
######################
#......###############
#......#......#......#
#......#......+......#
#......#.E....#......#
#......#BFD...#......#
#......+.C*...#......#
########..A...#......#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, C
🎯 Ground Truth: B, C, A
🧠 Cognitive Map Metrics
Global:
dir: 0.905
facing: 1
pos: 0.940
overall: 0.948
Global (Full):
dir: 0.158
facing: 0.444
pos: 0.376
overall: 0.326
Local:
dir: 0.667
facing: 1
pos: 0.898
overall: 0.855
Local (Newly):
dir: 0.667
facing: 1
pos: 0.898
overall: 0.855
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.122
is_action_fail: False
step: 2
action_counts:
move: 0
rotate: 1
return: 0
observe: 2
term: 0
forced_term: 0
query: 0
information_gain: 0.293
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: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "south"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      3,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "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
######################
#......###############
#......#......#......#
#......#......+......#
#......#.C....#......#
#......#E....D#......#
#......+BA*...#......#
########..F...#......#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, E
🎯 Ground Truth: E, A, B
🧠 Cognitive Map Metrics
Global:
dir: 0.905
facing: 1
pos: 0.940
overall: 0.948
Global (Full):
dir: 0.158
facing: 0.444
pos: 0.376
overall: 0.326
Local:
(none)
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.357
edge_coverage: 0.122
is_action_fail: False
step: 3
action_counts:
move: 0
rotate: 2
return: 0
observe: 3
term: 0
forced_term: 0
query: 0
information_gain: 0.293
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: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "west"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      5
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "vase": {
      "position": [
        2,
        2
      ]
    },
    "yellow door": {
      "position": [
        0,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "vase": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      0,
      3
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "vase": {
      "position": [
        2,
        2
      ]
    },
    "yellow door": {
      "position": [
        0,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      0,
      3
    ],
    "facing": "east"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.821
facing: 1
pos: 0.906
overall: 0.909
Global (Full):
dir: 0.192
facing: 0.444
pos: 0.423
overall: 0.353
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
dir: 1
facing: 1
pos: 1
overall: 1
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 0.429
edge_coverage: 0.146
is_action_fail: False
step: 4
action_counts:
move: 0
rotate: 3
return: 0
observe: 4
term: 0
forced_term: 0
query: 0
information_gain: 0.369
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(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -3,
      0
    ],
    "facing": "west"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      3
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -6,
      3
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -8,
      1
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -3,
      0
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -3,
      0
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "chair": {
      "position": [
        0,
        2
      ],
      "facing": "-x"
    },
    "desklamp": {
      "position": [
        3,
        5
      ],
      "facing": "+y"
    },
    "plant": {
      "position": [
        2,
        7
      ]
    }
  }
}
🎯 Ground Truth
{
  "desklamp": {
    "position": [
      2,
      4
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      0,
      2
    ],
    "facing": "south"
  },
  "plant": {
    "position": [
      2,
      6
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "chair": {
      "position": [
        0,
        2
      ],
      "facing": "-x"
    },
    "desklamp": {
      "position": [
        3,
        5
      ],
      "facing": "+y"
    },
    "plant": {
      "position": [
        2,
        7
      ]
    }
  }
}
🎯 Ground Truth
{
  "desklamp": {
    "position": [
      2,
      4
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      0,
      2
    ],
    "facing": "south"
  },
  "plant": {
    "position": [
      2,
      6
    ],
    "facing": "east"
  }
}
🗺️ Symbolic Fog Map
######################
#EF.C..###############
#......#......#......#
#....B.#......+......#
#.....A#......#......#
#......#......#......#
#....D.*......#......#
########......#......#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, C
🎯 Ground Truth: A, B, C
🧠 Cognitive Map Metrics
Global:
dir: 0.836
facing: 1
pos: 0.881
overall: 0.906
Global (Full):
dir: 0.383
facing: 0.667
pos: 0.587
overall: 0.546
Local:
dir: 0.667
facing: 1
pos: 0.859
overall: 0.842
Local (Newly):
dir: 0.667
facing: 1
pos: 0.859
overall: 0.842
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.643
edge_coverage: 0.220
is_action_fail: False
step: 5
action_counts:
move: 1
rotate: 3
return: 0
observe: 5
term: 0
forced_term: 0
query: 0
information_gain: 0.550
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(chair), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "west"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      3,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -7,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "desklamp": {
      "position": [
        2,
        2
      ],
      "facing": "+y"
    },
    "plant": {
      "position": [
        3,
        4
      ]
    }
  }
}
🎯 Ground Truth
{
  "desklamp": {
    "position": [
      2,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      2,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "desklamp": {
      "position": [
        2,
        2
      ],
      "facing": "+y"
    },
    "plant": {
      "position": [
        3,
        4
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
######################
#.BA.F.###############
#C.....#......#......#
#.....E#......+......#
#......#......#......#
#...D..#......#......#
#....*.+......#......#
########......#......#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, E, F
🎯 Ground Truth: A, F, E
🧠 Cognitive Map Metrics
Global:
dir: 0.800
facing: 1
pos: 0.853
overall: 0.884
Global (Full):
dir: 0.367
facing: 0.667
pos: 0.569
overall: 0.534
Local:
dir: 0.667
facing: 1
pos: 0.898
overall: 0.855
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.643
edge_coverage: 0.268
is_action_fail: False
step: 6
action_counts:
move: 2
rotate: 3
return: 0
observe: 6
term: 0
forced_term: 0
query: 0
information_gain: 0.550
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: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "north"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      3,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      3
    ],
    "facing": "west"
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "plant": {
    "position": [
      -7,
      5
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "desklamp": {
      "position": [
        -2,
        2
      ],
      "facing": "-x"
    },
    "basket": {
      "position": [
        0,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "desklamp": {
    "position": [
      -2,
      2
    ],
    "facing": "west"
  },
  "basket": {
    "position": [
      0,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "desklamp": {
      "position": [
        -2,
        2
      ],
      "facing": "-x"
    },
    "basket": {
      "position": [
        0,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "basket": {
    "position": [
      0,
      4
    ],
    "facing": "east"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.742
facing: 1
pos: 0.819
overall: 0.854
Global (Full):
dir: 0.408
facing: 0.667
pos: 0.601
overall: 0.559
Local:
dir: 1
facing: 1
pos: 0.898
overall: 0.966
Local (Newly):
dir: 1
facing: 1
pos: 0.859
overall: 0.953
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 0.714
edge_coverage: 0.293
is_action_fail: False
step: 7
action_counts:
move: 2
rotate: 4
return: 0
observe: 7
term: 0
forced_term: 0
query: 0
information_gain: 0.615
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(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "green door": {
    "position": [
      3,
      4
    ]
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -8,
      3
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        0,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      0,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        0,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🧠 Cognitive Map Metrics
Global:
dir: 0.848
facing: 1
pos: 0.894
overall: 0.914
Global (Full):
dir: 0.467
facing: 0.667
pos: 0.656
overall: 0.596
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 0.714
edge_coverage: 0.293
is_action_fail: False
step: 8
action_counts:
move: 2
rotate: 5
return: 0
observe: 8
term: 0
forced_term: 0
query: 0
information_gain: 0.615
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: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      3,
      3
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "plant": {
    "position": [
      -7,
      1
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.879
facing: 1
pos: 0.866
overall: 0.915
Global (Full):
dir: 0.483
facing: 0.667
pos: 0.635
overall: 0.595
Local:
(none)
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 0.714
edge_coverage: 0.293
is_action_fail: False
step: 9
action_counts:
move: 2
rotate: 6
return: 0
observe: 9
term: 0
forced_term: 0
query: 0
information_gain: 0.615
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: [JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -8,
      1
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
🧠 Cognitive Map Metrics
Global:
dir: 0.848
facing: 1
pos: 0.886
overall: 0.912
Global (Full):
dir: 0.467
facing: 0.667
pos: 0.650
overall: 0.594
Local:
(none)
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 0.714
edge_coverage: 0.293
is_action_fail: True
step: 10
action_counts:
move: 2
rotate: 6
return: 0
observe: 10
term: 0
forced_term: 0
query: 0
information_gain: 0.615
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: [Rotate(-90), JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "left"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "left"
  },
  "plant": {
    "position": [
      -8,
      3
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "right"
  },
  "teddybear": {
    "position": [
      2,
      3
    ],
    "facing": "right"
  },
  "bike": {
    "position": [
      3,
      3
    ],
    "facing": "right"
  },
  "vase": {
    "position": [
      -2,
      3
    ]
  },
  "green door": {
    "position": [
      4,
      2
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        0,
        6
      ],
      "facing": "+x"
    },
    "teddybear": {
      "position": [
        -2,
        6
      ],
      "facing": "+y"
    },
    "bike": {
      "position": [
        -4,
        6
      ],
      "facing": "+y"
    },
    "green door": {
      "position": [
        -4,
        7
      ]
    }
  }
}
🎯 Ground Truth
{
  "teddybear": {
    "position": [
      -2,
      4
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      -3,
      7
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      -4,
      4
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      0,
      6
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        0,
        6
      ],
      "facing": "+x"
    },
    "teddybear": {
      "position": [
        -2,
        6
      ],
      "facing": "+y"
    },
    "bike": {
      "position": [
        -4,
        6
      ],
      "facing": "+y"
    },
    "green door": {
      "position": [
        -4,
        7
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🧠 Cognitive Map Metrics
Global:
dir: 0.682
facing: 0.667
pos: 0.854
overall: 0.734
Global (Full):
dir: 0.375
facing: 0.444
pos: 0.626
overall: 0.482
Local:
dir: 0.600
facing: 1
pos: 0.797
overall: 0.799
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 0.714
edge_coverage: 0.390
is_action_fail: False
step: 11
action_counts:
move: 3
rotate: 7
return: 0
observe: 11
term: 0
forced_term: 0
query: 0
information_gain: 0.634
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(green door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      3,
      3
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      3,
      -1
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -1,
      2
    ]
  },
  "green door": {
    "position": [
      3,
      3
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -6,
      1
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -6,
      2
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "shoppingcart": {
    "position": [
      6,
      0
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      6,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      6,
      5
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoppingcart": {
      "position": [
        4,
        4
      ],
      "facing": "+x"
    },
    "scooter": {
      "position": [
        1,
        3
      ],
      "facing": "+y"
    },
    "shoes": {
      "position": [
        5,
        5
      ],
      "facing": "+y"
    },
    "shelf": {
      "position": [
        -2,
        6
      ]
    }
  }
}
🎯 Ground Truth
{
  "shoes": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      -1,
      5
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      1,
      3
    ],
    "facing": "east"
  },
  "shoppingcart": {
    "position": [
      3,
      3
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoppingcart": {
      "position": [
        4,
        4
      ],
      "facing": "+x"
    },
    "scooter": {
      "position": [
        1,
        3
      ],
      "facing": "+y"
    },
    "shoes": {
      "position": [
        5,
        5
      ],
      "facing": "+y"
    },
    "shelf": {
      "position": [
        -2,
        6
      ]
    }
  }
}
🎯 Ground Truth
{
  "shoes": {
    "position": [
      3,
      5
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      -1,
      5
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      1,
      3
    ],
    "facing": "east"
  },
  "shoppingcart": {
    "position": [
      3,
      3
    ],
    "facing": "south"
  }
}
🗺️ Symbolic Fog Map
######################
#......###############
#......#......#.C....#
#......#......*......#
#......#......#......#
#......#......#B..E..#
#......+......#D.F...#
########......#.A....#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, D
🎯 Ground Truth: B, D, A
🧠 Cognitive Map Metrics
Global:
dir: 0.817
facing: 1
pos: 0.786
overall: 0.867
Global (Full):
dir: 0.817
facing: 1
pos: 0.786
overall: 0.867
Local:
dir: 0.800
facing: 1
pos: 0.807
overall: 0.869
Local (Newly):
dir: 0.800
facing: 1
pos: 0.807
overall: 0.869
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.488
is_action_fail: False
step: 12
action_counts:
move: 4
rotate: 7
return: 0
observe: 12
term: 0
forced_term: 0
query: 0
information_gain: 0.858
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(scooter), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -7,
      4
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "shoppingcart": {
    "position": [
      8,
      -2
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      6,
      1
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      8,
      0
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      6,
      4
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoes": {
      "position": [
        2,
        2
      ],
      "facing": "+y"
    },
    "shelf": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "shoes": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoes": {
      "position": [
        2,
        2
      ],
      "facing": "+y"
    },
    "shelf": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
######################
#......###############
#......#......#......#
#......#......+...F..#
#......#......#..*.B.#
#......#......#......#
#......+......#AD....#
########......#C....E#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, C, D
🎯 Ground Truth: D, A, C
🧠 Cognitive Map Metrics
Global:
dir: 0.758
facing: 1
pos: 0.804
overall: 0.854
Global (Full):
dir: 0.758
facing: 1
pos: 0.804
overall: 0.854
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.537
is_action_fail: False
step: 13
action_counts:
move: 5
rotate: 7
return: 0
observe: 13
term: 0
forced_term: 0
query: 0
information_gain: 0.874
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": [
      7,
      1
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "green door": {
    "position": [
      4,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -6,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -7,
      1
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "shoppingcart": {
    "position": [
      7,
      -1
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      7,
      1
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      -1
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      8,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoppingcart": {
      "position": [
        0,
        2
      ],
      "facing": "+y"
    },
    "shoes": {
      "position": [
        -2,
        3
      ],
      "facing": "-x"
    }
  }
}
🎯 Ground Truth
{
  "shoes": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoppingcart": {
    "position": [
      0,
      2
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoppingcart": {
      "position": [
        0,
        2
      ],
      "facing": "+y"
    },
    "shoes": {
      "position": [
        -2,
        3
      ],
      "facing": "-x"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
######################
#......###############
#......#......#......#
#......#......+......#
#......#......#..*...#
#......#......#BA....#
#......+......#......#
########......#......#
######################
🔍 Fog Probe JSONs
📍 Candidates: A, B
🤖 Predicted: B
🎯 Ground Truth: B
🧠 Cognitive Map Metrics
Global:
dir: 0.858
facing: 1
pos: 0.851
overall: 0.903
Global (Full):
dir: 0.858
facing: 1
pos: 0.851
overall: 0.903
Local:
dir: 0.667
facing: 1
pos: 0.898
overall: 0.855
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.561
is_action_fail: False
step: 14
action_counts:
move: 5
rotate: 8
return: 0
observe: 14
term: 0
forced_term: 0
query: 0
information_gain: 0.883
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(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      6,
      1
    ],
    "facing": "west"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "right"
  },
  "bike": {
    "position": [
      3,
      3
    ],
    "facing": "right"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "right"
  },
  "green door": {
    "position": [
      3,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "left"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "left"
  },
  "plant": {
    "position": [
      -7,
      1
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "shoppingcart": {
    "position": [
      6,
      -1
    ],
    "facing": "forward"
  },
  "scooter": {
    "position": [
      6,
      1
    ],
    "facing": "forward"
  },
  "shoes": {
    "position": [
      8,
      -1
    ],
    "facing": "left"
  },
  "shelf": {
    "position": [
      8,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "green door": {
      "position": [
        1,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "green door": {
    "position": [
      1,
      3
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "green door": {
      "position": [
        1,
        3
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🧠 Cognitive Map Metrics
Global:
dir: 0.850
facing: 0.444
pos: 0.826
overall: 0.707
Global (Full):
dir: 0.850
facing: 0.444
pos: 0.826
overall: 0.707
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.561
is_action_fail: False
step: 15
action_counts:
move: 5
rotate: 9
return: 0
observe: 15
term: 0
forced_term: 0
query: 0
information_gain: 0.883
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": [
      7,
      1
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      3,
      3
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "green door": {
    "position": [
      4,
      2
    ]
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "chair": {
    "position": [
      -4,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -6,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -6,
      3
    ]
  },
  "basket": {
    "position": [
      -4,
      3
    ]
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "scooter": {
    "position": [
      7,
      1
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      8,
      0
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shelf": {
      "position": [
        2,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "shelf": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shelf": {
      "position": [
        2,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🧠 Cognitive Map Metrics
Global:
dir: 0.850
facing: 1
pos: 0.822
overall: 0.891
Global (Full):
dir: 0.850
facing: 1
pos: 0.822
overall: 0.891
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.561
is_action_fail: False
step: 16
action_counts:
move: 5
rotate: 10
return: 0
observe: 16
term: 0
forced_term: 0
query: 0
information_gain: 0.888
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: [Term()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      8,
      0
    ],
    "facing": "north"
  },
  "vase": {
    "position": [
      -2,
      2
    ]
  },
  "teddybear": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "bike": {
    "position": [
      2,
      5
    ],
    "facing": "east"
  },
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ]
  },
  "green door": {
    "position": [
      5,
      1
    ]
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "plant": {
    "position": [
      -6,
      3
    ]
  },
  "basket": {
    "position": [
      -5,
      3
    ]
  },
  "scooter": {
    "position": [
      8,
      0
    ],
    "facing": "east"
  },
  "shoppingcart": {
    "position": [
      8,
      -2
    ],
    "facing": "south"
  },
  "shoes": {
    "position": [
      10,
      -2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      10,
      2
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "television": {
    "position": [
      3,
      0
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      7,
      0
    ],
    "facing": "south"
  },
  "chair": {
    "position": [
      -5,
      0
    ],
    "facing": "south"
  },
  "teddybear": {
    "position": [
      1,
      2
    ],
    "facing": "east"
  },
  "scooter": {
    "position": [
      7,
      2
    ],
    "facing": "east"
  },
  "desklamp": {
    "position": [
      -7,
      2
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      1,
      4
    ],
    "facing": "east"
  },
  "vase": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoes": {
    "position": [
      9,
      0
    ],
    "facing": "east"
  },
  "plant": {
    "position": [
      -9,
      2
    ],
    "facing": "east"
  },
  "shelf": {
    "position": [
      9,
      4
    ],
    "facing": "east"
  },
  "basket": {
    "position": [
      -5,
      4
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "green door": {
    "position": [
      4,
      3
    ],
    "facing": "east"
  },
  "agent": {
    "position": [
      7,
      2
    ],
    "facing": "north"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.825
facing: 1
pos: 0.771
overall: 0.865
Global (Full):
dir: 0.825
facing: 1
pos: 0.771
overall: 0.865
Local:
(none)
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.561
is_action_fail: False
step: 17
action_counts:
move: 5
rotate: 10
return: 0
observe: 16
term: 1
forced_term: 0
query: 0
information_gain: 0.888
reward: -0.100
is_done: True
is_valid_action: True
Previous state
State before Turn 17
Current state
State at Turn 17

🧭 False Belief Exploration

🔄 FB Turn 18

💬 Assistant Action
Actions: [Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: plant:
dir: None
pos: 1
facing: None
overall: None
Retention: plant:
dir: None
pos: 0.462
facing: None
overall: None
Unchanged (all):
dir: 0.848
facing: 0.833
pos: 0.838
overall: 0.840
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): ['plant']
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: ['plant']
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['plant']
newly_observed_unchanged_objects: ['vase', 'teddybear']
Current state
State at Turn 1

🔄 FB Turn 19

💬 Assistant Action
Actions: [Rotate(90), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: television:
dir: None
pos: None
facing: 0
overall: None
Retention: television:
dir: None
pos: None
facing: 1
overall: None
Unchanged (all):
dir: 0.924
facing: 1
pos: 0.741
overall: 0.888
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): ['television']
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: ['television']
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['television']
newly_observed_unchanged_objects: ['green door']
Previous state
State before Turn 2
Current state
State at Turn 2

🔄 FB Turn 20

💬 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: 0.879
facing: 1
pos: 0.859
overall: 0.913
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 3
Current state
State at Turn 3

🔄 FB Turn 21

💬 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: 0.788
facing: 0.833
pos: 0.792
overall: 0.804
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['basket', 'chair', 'desklamp', 'green door', 'grid', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['yellow door']
Previous state
State before Turn 4
Current state
State at Turn 4

🔄 FB Turn 22

💬 Assistant Action
Actions: [JumpTo(yellow door), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: desklamp:
dir: None
pos: None
facing: 1
overall: None
Retention: desklamp:
dir: None
pos: None
facing: 0
overall: None
Unchanged (all):
dir: 0.727
facing: 0.500
pos: 0.729
overall: 0.652
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): ['desklamp']
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: ['desklamp']
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['desklamp']
newly_observed_unchanged_objects: ['chair']
Previous state
State before Turn 5
Current state
State at Turn 5

🔄 FB Turn 23

💬 Assistant Action
Actions: [JumpTo(chair), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.848
facing: 1
pos: 0.815
overall: 0.888
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['basket', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', '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 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: 0.833
facing: 0.667
pos: 0.769
overall: 0.756
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['basket']
Previous state
State before Turn 7
Current state
State at Turn 7

🔄 FB Turn 25

💬 Assistant Action
Actions: [Rotate(90), JumpTo(yellow door), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.788
facing: 1
pos: 0.833
overall: 0.874
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): []
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', '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 26

💬 Assistant Action
Actions: [JumpTo(green door), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: bike:
dir: None
pos: 0.807
facing: None
overall: None
Retention: bike:
dir: None
pos: 0.272
facing: None
overall: None
Unchanged (all):
dir: 0.773
facing: 1
pos: 0.807
overall: 0.860
🧾 False Belief Object Sets
all_objects: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', 'yellow door']
all_changed_objects: ['bike', 'desklamp', 'plant', 'television']
newly_observed_changed (this turn): ['bike']
unchanged_objects: ['basket', 'chair', 'green door', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'vase', 'yellow door']
pred_changed_keys: ['bike']
pred_unchanged_keys: ['basket', 'bike', 'chair', 'desklamp', 'green door', 'plant', 'scooter', 'shelf', 'shoes', 'shoppingcart', 'teddybear', 'television', 'vase', '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': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['bike']
newly_observed_unchanged_objects: ['shoes', 'shelf', 'scooter', 'shoppingcart']
Previous state
State before Turn 9
Current state
State at Turn 9

🔄 FB Turn 27

💬 Assistant Action
Actions: [Term(changes="television: orientation, bike: position, plant: position, desklamp: orientation")]
📈 Turn Metrics
reward: 1
is_done: True
is_valid_action: True
success: 1
🧭 False Belief Info
step: 10
correctly_identified_changes: 1
f1_overall: 1
f1_position: 1
f1_facing: 1
action_cost: 9
action_cost_after_seen: 0
ground_truth_changes: [{'name': 'television', 'ori': True}, {'name': 'desklamp', 'ori': True}, {'name': 'plant', 'pos': True}, {'name': 'bike', 'pos': True}]
reported_changes: [{'name': 'television', 'ori': True}, {'name': 'bike', 'pos': True}, {'name': 'plant', 'pos': True}, {'name': 'desklamp', 'ori': 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: a5560bd263efdb31)

✅ Evaluation Results
id: a5560bd263efdb31
question: You return to your starting position and face north. From a Top-Down map, describe where basket is relative to vase. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: bb2523a0048c8980)

✅ Evaluation Results
id: bb2523a0048c8980
question: You return to your starting position and face north. From a Top-Down map, describe where plant is relative to basket. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south west, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: daa53364e07a0ab1)

✅ Evaluation Results
id: daa53364e07a0ab1
question: You return to your starting position and face north. From a Top-Down map, describe where desklamp is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3f86078c87f16910)

✅ Evaluation Results
id: 3f86078c87f16910
question: Now you jump to scooter's direction, facing its direction. Describe where shelf is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-left, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: 18c74f89f0b249a8)

✅ Evaluation Results
id: 18c74f89f0b249a8
question: Now you jump to desklamp'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, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 581f2fdf25b85ca0)

✅ Evaluation Results
id: 581f2fdf25b85ca0
question: Now you jump to scooter's direction, facing its direction. Describe where shoes 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
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 98f3ab2f400036ba)

✅ Evaluation Results
id: 98f3ab2f400036ba
question: Now you jump to an object's position, facing its direction. You observe that shoes is front-right, mid distance, facing forward; shelf is front-left, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [17, 4]
final_ori: [1, 0]
final_observation: [{'name': 'shoes', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'shelf', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 2
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: 06116bb98f50440a)

✅ Evaluation Results
id: 06116bb98f50440a
question: Now you jump to an object's position, facing its direction. You observe that television is front-right, mid distance, facing right; green door is front-slight-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: teddybear
final_pos: [11, 4]
final_ori: [1, 0]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'green door', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 1
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: False
view_match: False
score: 0
evaluation_mode: default
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: a0575673764e4662)

✅ Evaluation Results
id: a0575673764e4662
question: Now you jump to an object's position, facing its direction. You observe that plant is front, near. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 4]
final_ori: [-1, 0]
final_observation: [{'name': 'plant', 'direction': 'front', 'distance': 'near', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 3
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: e3a718b9ba658f8a)

✅ Evaluation Results
id: e3a718b9ba658f8a
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, mid distance. 3. Jump to the object at front-slight-right, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of yellow door 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: 4ddf26d26bf2de51)

✅ Evaluation Results
id: 4ddf26d26bf2de51
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-right, mid distance. 2. Rotate(90) 3. Jump to the object at front-right, mid distance. 4. Rotate(-90) After executing the actions, what is the ego relation of bike relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 73bdb5bede08b131)

✅ Evaluation Results
id: 73bdb5bede08b131
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, slightly far. 2. Rotate(-180) 3. Jump to the object at front-right, slightly far. 4. Rotate(-90) After executing the actions, what is the ego relation of television relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 9f3daf6b05eca7d1)

✅ Evaluation Results
id: 9f3daf6b05eca7d1
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: yellow door is at front-slight-right, slightly far, on front wall; chair is at front-right, slightly far, facing right; desklamp is at front, near, facing backward 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: [1, 4]
final_ori: [1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 180]]
final_observation: [{'name': 'yellow door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}, {'name': 'chair', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front', 'distance': 'near', 'orientation': 'facing backward'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [1.0, 4.0]
final_ori: [1, 0]
visible_match: True
score: 1
evaluation_mode: default
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 5b0522617e98fcb6)

✅ Evaluation Results
id: 5b0522617e98fcb6
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: desklamp is at front-left, mid distance, facing forward; plant is at front-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: [5, 6]
final_ori: [-1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['rotate', 90], ['jumpto', 'basket'], ['rotate', -90]]
final_observation: [{'name': 'desklamp', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'plant', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: False
ori_match: False
final_pos: [5.0, 2.0]
final_ori: [0, 1]
visible_match: False
score: 0
evaluation_mode: default
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: c9fb26112af06791)

✅ Evaluation Results
id: c9fb26112af06791
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: green door is at front-right, slightly far, on front wall 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: [17, 2]
final_ori: [-1, 0]
room_id: 2
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'green door'], ['jumpto', 'shoppingcart'], ['rotate', 180]]
final_observation: [{'name': 'green door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [17.0, 2.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: default
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2cc0be1d05b6551a)

✅ Evaluation Results
id: 2cc0be1d05b6551a
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: basket, vase, chair. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 4], [-2, 2], [-5, 0]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.862
threshold: 0.900
score: 0.862
evaluation_mode: default
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 9523d4db4cc7f611)

✅ Evaluation Results
id: 9523d4db4cc7f611
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: shelf, shoppingcart, basket, scooter. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[9, 4], [7, 0], [-5, 4], [7, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.939
threshold: 0.900
score: 0.939
evaluation_mode: default
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 934a5d170d934897)

✅ Evaluation Results
id: 934a5d170d934897
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: chair, bike, vase, shoppingcart, teddybear. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 0], [1, 4], [-2, 2], [7, 0], [1, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.833
threshold: 0.900
score: 0.833
evaluation_mode: default
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: fa250972cf6336ae)

✅ Evaluation Results
id: fa250972cf6336ae
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: plant, shoes, vase. 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: ['vase', 'plant', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: bb289996eb948eb5)

✅ Evaluation Results
id: bb289996eb948eb5
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: bike, desklamp, scooter. 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: ['bike', 'scooter', 'desklamp']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: 849efca6f71b0548)

✅ Evaluation Results
id: 849efca6f71b0548
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: chair, shelf, vase. 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: ['vase', 'chair', 'shelf']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: RotEvaluationTask

📊 Task: RotDualEvaluationTask

Question 1 (ID: 9c32cc1590bebf7a)

✅ Evaluation Results
id: 9c32cc1590bebf7a
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: vase, plant, shoes 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
Q1: RotDualEvaluationTask

Question 2 (ID: b329ee5b46d5266a)

✅ Evaluation Results
id: b329ee5b46d5266a
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: bike, scooter, desklamp 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
Q2: RotDualEvaluationTask

Question 3 (ID: 70141be403b87c4e)

✅ Evaluation Results
id: 70141be403b87c4e
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: vase, chair, shelf 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: 7a18b9e1a601f3c8)

✅ Evaluation Results
id: 7a18b9e1a601f3c8
question: Still treat your initial position as origin (0, 0) You move to (-2, 1) and face east. What is the egocentric relation of bike? 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: 8497629827c2666b)

✅ Evaluation Results
id: 8497629827c2666b
question: Still treat your initial position as origin (0, 0) You move to (-1, 2) and face west. What is the egocentric relation of vase? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 2be81510a6e4a0ff)

✅ Evaluation Results
id: 2be81510a6e4a0ff
question: Still treat your initial position as origin (0, 0) You move to (0, 4) and face east. What is the egocentric relation of bike? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 71d44ca0438f07d8)

✅ Evaluation Results
id: 71d44ca0438f07d8
question: You move to a new location and face east. You observe: bike is at front-left, slightly far, facing forward; teddybear is at front-slight-left, mid distance, facing forward; television is at front-slight-right, slightly far, facing right 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: [-2, 1]
final_pos: [8, 3]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'teddybear', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'television', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing right'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: default
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: abe453e8057600a8)

✅ Evaluation Results
id: abe453e8057600a8
question: You move to a new location and face west. You observe: vase is at front, near; yellow door is at front-left, mid distance, 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, 2]
final_pos: [9, 4]
final_ori: [-1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'vase', 'direction': 'front', 'distance': 'near', 'orientation': None}, {'name': 'yellow door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: dafbe7465cd09199)

✅ Evaluation Results
id: dafbe7465cd09199
question: You move to a new location and face east. You observe: bike is at front, near, facing forward; green door is at front-slight-right, 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: [0, 4]
final_pos: [10, 6]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front', 'distance': 'near', 'orientation': 'facing forward'}, {'name': 'green door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: default
Evaluation state
Q3: View2LocationTextEvaluationTask

📊 Evaluation (prompt_cogmap)

📊 Task: DirectionEvaluationTask

Question 1 (ID: a5560bd263efdb31)

✅ Evaluation Results
id: a5560bd263efdb31
question: You return to your starting position and face north. From a Top-Down map, describe where basket is relative to vase. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: bb2523a0048c8980)

✅ Evaluation Results
id: bb2523a0048c8980
question: You return to your starting position and face north. From a Top-Down map, describe where plant is relative to basket. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south west, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: daa53364e07a0ab1)

✅ Evaluation Results
id: daa53364e07a0ab1
question: You return to your starting position and face north. From a Top-Down map, describe where desklamp is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3f86078c87f16910)

✅ Evaluation Results
id: 3f86078c87f16910
question: Now you jump to scooter's direction, facing its direction. Describe where shelf is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-left, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: 18c74f89f0b249a8)

✅ Evaluation Results
id: 18c74f89f0b249a8
question: Now you jump to desklamp'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, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 581f2fdf25b85ca0)

✅ Evaluation Results
id: 581f2fdf25b85ca0
question: Now you jump to scooter's direction, facing its direction. Describe where shoes 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: prompt_cogmap
Evaluation state
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 98f3ab2f400036ba)

✅ Evaluation Results
id: 98f3ab2f400036ba
question: Now you jump to an object's position, facing its direction. You observe that shoes is front-right, mid distance, facing forward; shelf is front-left, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [17, 4]
final_ori: [1, 0]
final_observation: [{'name': 'shoes', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'shelf', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 2
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: 06116bb98f50440a)

✅ Evaluation Results
id: 06116bb98f50440a
question: Now you jump to an object's position, facing its direction. You observe that television is front-right, mid distance, facing right; green door is front-slight-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: teddybear
final_pos: [11, 4]
final_ori: [1, 0]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'green door', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 1
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: False
view_match: False
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: a0575673764e4662)

✅ Evaluation Results
id: a0575673764e4662
question: Now you jump to an object's position, facing its direction. You observe that plant is front, near. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 4]
final_ori: [-1, 0]
final_observation: [{'name': 'plant', 'direction': 'front', 'distance': 'near', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 3
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: e3a718b9ba658f8a)

✅ Evaluation Results
id: e3a718b9ba658f8a
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, mid distance. 3. Jump to the object at front-slight-right, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of yellow door 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: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q1: Action2ViewEvaluationTask

Question 2 (ID: 4ddf26d26bf2de51)

✅ Evaluation Results
id: 4ddf26d26bf2de51
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-right, mid distance. 2. Rotate(90) 3. Jump to the object at front-right, mid distance. 4. Rotate(-90) After executing the actions, what is the ego relation of bike relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 73bdb5bede08b131)

✅ Evaluation Results
id: 73bdb5bede08b131
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, slightly far. 2. Rotate(-180) 3. Jump to the object at front-right, slightly far. 4. Rotate(-90) After executing the actions, what is the ego relation of television relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 9f3daf6b05eca7d1)

✅ Evaluation Results
id: 9f3daf6b05eca7d1
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: yellow door is at front-slight-right, slightly far, on front wall; chair is at front-right, slightly far, facing right; desklamp is at front, near, facing backward 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: [1, 4]
final_ori: [1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 180]]
final_observation: [{'name': 'yellow door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}, {'name': 'chair', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front', 'distance': 'near', 'orientation': 'facing backward'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
error: invalid_format
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 5b0522617e98fcb6)

✅ Evaluation Results
id: 5b0522617e98fcb6
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: desklamp is at front-left, mid distance, facing forward; plant is at front-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: [5, 6]
final_ori: [-1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['rotate', 90], ['jumpto', 'basket'], ['rotate', -90]]
final_observation: [{'name': 'desklamp', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'plant', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 6.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: c9fb26112af06791)

✅ Evaluation Results
id: c9fb26112af06791
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: green door is at front-right, slightly far, on front wall 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: [17, 2]
final_ori: [-1, 0]
room_id: 2
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'green door'], ['jumpto', 'shoppingcart'], ['rotate', 180]]
final_observation: [{'name': 'green door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: False
ori_match: False
final_pos: [7.0, 2.0]
final_ori: [0, 1]
visible_match: False
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2cc0be1d05b6551a)

✅ Evaluation Results
id: 2cc0be1d05b6551a
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: basket, vase, chair. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 4], [-2, 2], [-5, 0]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.862
threshold: 0.900
score: 0.862
evaluation_mode: prompt_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 9523d4db4cc7f611)

✅ Evaluation Results
id: 9523d4db4cc7f611
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: shelf, shoppingcart, basket, scooter. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[9, 4], [7, 0], [-5, 4], [7, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.939
threshold: 0.900
score: 0.939
evaluation_mode: prompt_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 934a5d170d934897)

✅ Evaluation Results
id: 934a5d170d934897
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: chair, bike, vase, shoppingcart, teddybear. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 0], [1, 4], [-2, 2], [7, 0], [1, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.867
threshold: 0.900
score: 0.867
evaluation_mode: prompt_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: fa250972cf6336ae)

✅ Evaluation Results
id: fa250972cf6336ae
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: plant, shoes, vase. 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: ['vase', 'plant', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: bb289996eb948eb5)

✅ Evaluation Results
id: bb289996eb948eb5
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: bike, desklamp, scooter. 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: ['bike', 'scooter', 'desklamp']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: 849efca6f71b0548)

✅ Evaluation Results
id: 849efca6f71b0548
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: chair, shelf, vase. 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: ['vase', 'chair', 'shelf']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: 7a18b9e1a601f3c8)

✅ Evaluation Results
id: 7a18b9e1a601f3c8
question: Still treat your initial position as origin (0, 0) You move to (-2, 1) and face east. What is the egocentric relation of bike? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 8497629827c2666b)

✅ Evaluation Results
id: 8497629827c2666b
question: Still treat your initial position as origin (0, 0) You move to (-1, 2) and face west. What is the egocentric relation of vase? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 2be81510a6e4a0ff)

✅ Evaluation Results
id: 2be81510a6e4a0ff
question: Still treat your initial position as origin (0, 0) You move to (0, 4) and face east. What is the egocentric relation of bike? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 71d44ca0438f07d8)

✅ Evaluation Results
id: 71d44ca0438f07d8
question: You move to a new location and face east. You observe: bike is at front-left, slightly far, facing forward; teddybear is at front-slight-left, mid distance, facing forward; television is at front-slight-right, slightly far, facing right 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: [-2, 1]
final_pos: [8, 3]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'teddybear', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'television', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing right'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: abe453e8057600a8)

✅ Evaluation Results
id: abe453e8057600a8
question: You move to a new location and face west. You observe: vase is at front, near; yellow door is at front-left, mid distance, 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, 2]
final_pos: [9, 4]
final_ori: [-1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'vase', 'direction': 'front', 'distance': 'near', 'orientation': None}, {'name': 'yellow door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.639
raw_score: 0.639
score: 0.639
evaluation_mode: prompt_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: dafbe7465cd09199)

✅ Evaluation Results
id: dafbe7465cd09199
question: You move to a new location and face east. You observe: bike is at front, near, facing forward; green door is at front-slight-right, 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: [0, 4]
final_pos: [10, 6]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front', 'distance': 'near', 'orientation': 'facing forward'}, {'name': 'green door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.779
raw_score: 0.779
score: 0.779
evaluation_mode: prompt_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask

📊 Evaluation (use_gt_cogmap)

📊 Task: DirectionEvaluationTask

Question 1 (ID: a5560bd263efdb31)

✅ Evaluation Results
id: a5560bd263efdb31
question: You return to your starting position and face north. From a Top-Down map, describe where basket is relative to vase. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: bb2523a0048c8980)

✅ Evaluation Results
id: bb2523a0048c8980
question: You return to your starting position and face north. From a Top-Down map, describe where plant is relative to basket. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south west, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: daa53364e07a0ab1)

✅ Evaluation Results
id: daa53364e07a0ab1
question: You return to your starting position and face north. From a Top-Down map, describe where desklamp is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3f86078c87f16910)

✅ Evaluation Results
id: 3f86078c87f16910
question: Now you jump to scooter's direction, facing its direction. Describe where shelf is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-left, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: 18c74f89f0b249a8)

✅ Evaluation Results
id: 18c74f89f0b249a8
question: Now you jump to desklamp'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, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 581f2fdf25b85ca0)

✅ Evaluation Results
id: 581f2fdf25b85ca0
question: Now you jump to scooter's direction, facing its direction. Describe where shoes 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
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 98f3ab2f400036ba)

✅ Evaluation Results
id: 98f3ab2f400036ba
question: Now you jump to an object's position, facing its direction. You observe that shoes is front-right, mid distance, facing forward; shelf is front-left, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [17, 4]
final_ori: [1, 0]
final_observation: [{'name': 'shoes', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'shelf', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 2
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: 06116bb98f50440a)

✅ Evaluation Results
id: 06116bb98f50440a
question: Now you jump to an object's position, facing its direction. You observe that television is front-right, mid distance, facing right; green door is front-slight-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: teddybear
final_pos: [11, 4]
final_ori: [1, 0]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'green door', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 1
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: a0575673764e4662)

✅ Evaluation Results
id: a0575673764e4662
question: Now you jump to an object's position, facing its direction. You observe that plant is front, near. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 4]
final_ori: [-1, 0]
final_observation: [{'name': 'plant', 'direction': 'front', 'distance': 'near', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 3
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: e3a718b9ba658f8a)

✅ Evaluation Results
id: e3a718b9ba658f8a
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, mid distance. 3. Jump to the object at front-slight-right, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of yellow door 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: 4ddf26d26bf2de51)

✅ Evaluation Results
id: 4ddf26d26bf2de51
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-right, mid distance. 2. Rotate(90) 3. Jump to the object at front-right, mid distance. 4. Rotate(-90) After executing the actions, what is the ego relation of bike relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 73bdb5bede08b131)

✅ Evaluation Results
id: 73bdb5bede08b131
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, slightly far. 2. Rotate(-180) 3. Jump to the object at front-right, slightly far. 4. Rotate(-90) After executing the actions, what is the ego relation of television relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 9f3daf6b05eca7d1)

✅ Evaluation Results
id: 9f3daf6b05eca7d1
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: yellow door is at front-slight-right, slightly far, on front wall; chair is at front-right, slightly far, facing right; desklamp is at front, near, facing backward 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: [1, 4]
final_ori: [1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 180]]
final_observation: [{'name': 'yellow door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}, {'name': 'chair', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front', 'distance': 'near', 'orientation': 'facing backward'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [1.0, 4.0]
final_ori: [1, 0]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 5b0522617e98fcb6)

✅ Evaluation Results
id: 5b0522617e98fcb6
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: desklamp is at front-left, mid distance, facing forward; plant is at front-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: [5, 6]
final_ori: [-1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['rotate', 90], ['jumpto', 'basket'], ['rotate', -90]]
final_observation: [{'name': 'desklamp', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'plant', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 6.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: c9fb26112af06791)

✅ Evaluation Results
id: c9fb26112af06791
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: green door is at front-right, slightly far, on front wall 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: [17, 2]
final_ori: [-1, 0]
room_id: 2
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'green door'], ['jumpto', 'shoppingcart'], ['rotate', 180]]
final_observation: [{'name': 'green door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [17.0, 2.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2cc0be1d05b6551a)

✅ Evaluation Results
id: 2cc0be1d05b6551a
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: basket, vase, chair. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 4], [-2, 2], [-5, 0]]
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: 9523d4db4cc7f611)

✅ Evaluation Results
id: 9523d4db4cc7f611
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: shelf, shoppingcart, basket, scooter. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[9, 4], [7, 0], [-5, 4], [7, 2]]
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: 934a5d170d934897)

✅ Evaluation Results
id: 934a5d170d934897
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: chair, bike, vase, shoppingcart, teddybear. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 0], [1, 4], [-2, 2], [7, 0], [1, 2]]
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: fa250972cf6336ae)

✅ Evaluation Results
id: fa250972cf6336ae
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: plant, shoes, vase. 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: ['vase', 'plant', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: bb289996eb948eb5)

✅ Evaluation Results
id: bb289996eb948eb5
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: bike, desklamp, scooter. 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: ['bike', 'scooter', 'desklamp']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: 849efca6f71b0548)

✅ Evaluation Results
id: 849efca6f71b0548
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: chair, shelf, vase. 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: ['vase', 'chair', 'shelf']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: 7a18b9e1a601f3c8)

✅ Evaluation Results
id: 7a18b9e1a601f3c8
question: Still treat your initial position as origin (0, 0) You move to (-2, 1) and face east. What is the egocentric relation of bike? 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: 8497629827c2666b)

✅ Evaluation Results
id: 8497629827c2666b
question: Still treat your initial position as origin (0, 0) You move to (-1, 2) and face west. What is the egocentric relation of vase? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 2be81510a6e4a0ff)

✅ Evaluation Results
id: 2be81510a6e4a0ff
question: Still treat your initial position as origin (0, 0) You move to (0, 4) and face east. What is the egocentric relation of bike? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 71d44ca0438f07d8)

✅ Evaluation Results
id: 71d44ca0438f07d8
question: You move to a new location and face east. You observe: bike is at front-left, slightly far, facing forward; teddybear is at front-slight-left, mid distance, facing forward; television is at front-slight-right, slightly far, facing right 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: [-2, 1]
final_pos: [8, 3]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'teddybear', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'television', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing right'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: abe453e8057600a8)

✅ Evaluation Results
id: abe453e8057600a8
question: You move to a new location and face west. You observe: vase is at front, near; yellow door is at front-left, mid distance, 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, 2]
final_pos: [9, 4]
final_ori: [-1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'vase', 'direction': 'front', 'distance': 'near', 'orientation': None}, {'name': 'yellow door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.639
raw_score: 0.639
score: 0.639
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: dafbe7465cd09199)

✅ Evaluation Results
id: dafbe7465cd09199
question: You move to a new location and face east. You observe: bike is at front, near, facing forward; green door is at front-slight-right, 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: [0, 4]
final_pos: [10, 6]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front', 'distance': 'near', 'orientation': 'facing forward'}, {'name': 'green door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: a5560bd263efdb31)

✅ Evaluation Results
id: a5560bd263efdb31
question: You return to your starting position and face north. From a Top-Down map, describe where basket is relative to vase. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: bb2523a0048c8980)

✅ Evaluation Results
id: bb2523a0048c8980
question: You return to your starting position and face north. From a Top-Down map, describe where plant is relative to basket. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: south west, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: daa53364e07a0ab1)

✅ Evaluation Results
id: daa53364e07a0ab1
question: You return to your starting position and face north. From a Top-Down map, describe where desklamp is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: 3f86078c87f16910)

✅ Evaluation Results
id: 3f86078c87f16910
question: Now you jump to scooter's direction, facing its direction. Describe where shelf is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-left, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: 18c74f89f0b249a8)

✅ Evaluation Results
id: 18c74f89f0b249a8
question: Now you jump to desklamp'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, near
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: 581f2fdf25b85ca0)

✅ Evaluation Results
id: 581f2fdf25b85ca0
question: Now you jump to scooter's direction, facing its direction. Describe where shoes 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
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 98f3ab2f400036ba)

✅ Evaluation Results
id: 98f3ab2f400036ba
question: Now you jump to an object's position, facing its direction. You observe that shoes is front-right, mid distance, facing forward; shelf is front-left, mid distance. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: scooter
final_pos: [17, 4]
final_ori: [1, 0]
final_observation: [{'name': 'shoes', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'shelf', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 2
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: 06116bb98f50440a)

✅ Evaluation Results
id: 06116bb98f50440a
question: Now you jump to an object's position, facing its direction. You observe that television is front-right, mid distance, facing right; green door is front-slight-left, mid distance, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: teddybear
final_pos: [11, 4]
final_ori: [1, 0]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'green door', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 1
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: a0575673764e4662)

✅ Evaluation Results
id: a0575673764e4662
question: Now you jump to an object's position, facing its direction. You observe that plant is front, near. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 4]
final_ori: [-1, 0]
final_observation: [{'name': 'plant', 'direction': 'front', 'distance': 'near', 'orientation': None}]
object_positions:
television: [13.0, 2.0]
shoppingcart: [17.0, 2.0]
chair: [5.0, 2.0]
teddybear: [11.0, 4.0]
scooter: [17.0, 4.0]
desklamp: [3.0, 4.0]
bike: [11.0, 6.0]
vase: [8.0, 4.0]
shoes: [19.0, 2.0]
plant: [1.0, 4.0]
shelf: [19.0, 6.0]
basket: [5.0, 6.0]
yellow door: [7.0, 2.0]
green door: [14.0, 5.0]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
room_id: 3
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green 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: e3a718b9ba658f8a)

✅ Evaluation Results
id: e3a718b9ba658f8a
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, mid distance. 3. Jump to the object at front-slight-right, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of yellow door 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: 4ddf26d26bf2de51)

✅ Evaluation Results
id: 4ddf26d26bf2de51
question: You return to your starting position and face north. You will execute the following action sequence: 1. Jump to the object at front-right, mid distance. 2. Rotate(90) 3. Jump to the object at front-right, mid distance. 4. Rotate(-90) After executing the actions, what is the ego relation of bike relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 73bdb5bede08b131)

✅ Evaluation Results
id: 73bdb5bede08b131
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, slightly far. 2. Rotate(-180) 3. Jump to the object at front-right, slightly far. 4. Rotate(-90) After executing the actions, what is the ego relation of television relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front, slightly far
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 9f3daf6b05eca7d1)

✅ Evaluation Results
id: 9f3daf6b05eca7d1
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: yellow door is at front-slight-right, slightly far, on front wall; chair is at front-right, slightly far, facing right; desklamp is at front, near, facing backward 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: [1, 4]
final_ori: [1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['jumpto', 'plant'], ['rotate', 180]]
final_observation: [{'name': 'yellow door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}, {'name': 'chair', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front', 'distance': 'near', 'orientation': 'facing backward'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [1.0, 4.0]
final_ori: [1, 0]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 5b0522617e98fcb6)

✅ Evaluation Results
id: 5b0522617e98fcb6
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: desklamp is at front-left, mid distance, facing forward; plant is at front-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: [5, 6]
final_ori: [-1, 0]
room_id: 3
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', -90], ['jumpto', 'yellow door'], ['rotate', 90], ['jumpto', 'basket'], ['rotate', -90]]
final_observation: [{'name': 'desklamp', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'plant', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 6.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: c9fb26112af06791)

✅ Evaluation Results
id: c9fb26112af06791
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: green door is at front-right, slightly far, on front wall 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: [17, 2]
final_ori: [-1, 0]
room_id: 2
init_pos: [10, 2]
init_ori: [0, 1]
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
minimal_plan: [['rotate', 90], ['jumpto', 'green door'], ['jumpto', 'shoppingcart'], ['rotate', 180]]
final_observation: [{'name': 'green door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [17.0, 2.0]
final_ori: [-1, 0]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2cc0be1d05b6551a)

✅ Evaluation Results
id: 2cc0be1d05b6551a
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: basket, vase, chair. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 4], [-2, 2], [-5, 0]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.862
threshold: 0.900
score: 0.862
evaluation_mode: use_model_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 9523d4db4cc7f611)

✅ Evaluation Results
id: 9523d4db4cc7f611
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: shelf, shoppingcart, basket, scooter. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[9, 4], [7, 0], [-5, 4], [7, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.836
threshold: 0.900
score: 0.836
evaluation_mode: use_model_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 934a5d170d934897)

✅ Evaluation Results
id: 934a5d170d934897
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: chair, bike, vase, shoppingcart, teddybear. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 0], [1, 4], [-2, 2], [7, 0], [1, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.846
threshold: 0.900
score: 0.846
evaluation_mode: use_model_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: fa250972cf6336ae)

✅ Evaluation Results
id: fa250972cf6336ae
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: plant, shoes, vase. 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: ['vase', 'plant', 'shoes']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: bb289996eb948eb5)

✅ Evaluation Results
id: bb289996eb948eb5
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: bike, desklamp, scooter. 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: ['bike', 'scooter', 'desklamp']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: 849efca6f71b0548)

✅ Evaluation Results
id: 849efca6f71b0548
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: chair, shelf, vase. 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: ['vase', 'chair', 'shelf']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: 7a18b9e1a601f3c8)

✅ Evaluation Results
id: 7a18b9e1a601f3c8
question: Still treat your initial position as origin (0, 0) You move to (-2, 1) and face east. What is the egocentric relation of bike? 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_model_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 8497629827c2666b)

✅ Evaluation Results
id: 8497629827c2666b
question: Still treat your initial position as origin (0, 0) You move to (-1, 2) and face west. What is the egocentric relation of vase? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 2be81510a6e4a0ff)

✅ Evaluation Results
id: 2be81510a6e4a0ff
question: Still treat your initial position as origin (0, 0) You move to (0, 4) and face east. What is the egocentric relation of bike? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, near
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 71d44ca0438f07d8)

✅ Evaluation Results
id: 71d44ca0438f07d8
question: You move to a new location and face east. You observe: bike is at front-left, slightly far, facing forward; teddybear is at front-slight-left, mid distance, facing forward; television is at front-slight-right, slightly far, facing right 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: [-2, 1]
final_pos: [8, 3]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'teddybear', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'television', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing right'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: abe453e8057600a8)

✅ Evaluation Results
id: abe453e8057600a8
question: You move to a new location and face west. You observe: vase is at front, near; yellow door is at front-left, mid distance, 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, 2]
final_pos: [9, 4]
final_ori: [-1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'vase', 'direction': 'front', 'distance': 'near', 'orientation': None}, {'name': 'yellow door', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.639
raw_score: 0.639
score: 0.639
evaluation_mode: use_model_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: dafbe7465cd09199)

✅ Evaluation Results
id: dafbe7465cd09199
question: You move to a new location and face east. You observe: bike is at front, near, facing forward; green door is at front-slight-right, 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: [0, 4]
final_pos: [10, 6]
final_ori: [1, 0]
room_id: 1
object_positions:
television: [13, 2]
shoppingcart: [17, 2]
chair: [5, 2]
teddybear: [11, 4]
scooter: [17, 4]
desklamp: [3, 4]
bike: [11, 6]
vase: [8, 4]
shoes: [19, 2]
plant: [1, 4]
shelf: [19, 6]
basket: [5, 6]
yellow door: [7, 2]
green door: [14, 5]
object_orientations:
television: [0, -1]
shoppingcart: [0, -1]
chair: [0, -1]
teddybear: [1, 0]
scooter: [1, 0]
desklamp: [-1, 0]
bike: [1, 0]
shoes: [1, 0]
yellow door: [1, 0]
green door: [1, 0]
final_observation: [{'name': 'bike', 'direction': 'front', 'distance': 'near', 'orientation': 'facing forward'}, {'name': 'green door', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
gate_info:
yellow door:
room_ids: [3, 1]
ori_by_room:
3: [-1, 0]
1: [1, 0]
green door:
room_ids: [1, 2]
ori_by_room:
1: [-1, 0]
2: [1, 0]
object_rooms:
television: 1
shoppingcart: 2
chair: 3
teddybear: 1
scooter: 2
desklamp: 3
bike: 1
vase: 1
shoes: 2
plant: 3
shelf: 2
basket: 3
yellow door: [3, 1]
green door: [1, 2]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.779
raw_score: 0.779
score: 0.779
evaluation_mode: use_model_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask