Model: gemini-3-pro-preview

sample_run08

Select Configuration:

📊 Sample Metrics

🔍 Exploration

last_node_coverage: 1
last_edge_coverage: 0.488
n_exploration_steps: 15
action_counts:
move: 4
rotate: 12
return: 0
observe: 14
term: 1
forced_term: 0
query: 0
action_cost: 14
final_information_gain: 0.914
action_fail_ratio: 0.067
valid_action_ratio: 1
false_belief_steps: 9
false_belief_f1: 1
false_belief_f1_position: 1
false_belief_f1_facing: 1
false_belief_action_cost: 8
false_belief_action_cost_after_seen: 0

✅ Evaluation

overall:
n_total: 27
total_score: 19.430
avg_accuracy: 0.720
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
PovEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
View2ActionTextEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.062
avg_accuracy: 0.687
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: 2.368
avg_accuracy: 0.789

✅ Evaluation (prompt_cogmap)

overall:
n_total: 27
total_score: 18.670
avg_accuracy: 0.691
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 1
avg_accuracy: 0.333
PovEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
View2ActionTextEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
AlloMappingEvaluationTask:
n_total: 3
task_score: 1.811
avg_accuracy: 0.604
RotEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Location2ViewEvaluationTask:
n_total: 3
task_score: 2
avg_accuracy: 0.667
View2LocationTextEvaluationTask:
n_total: 3
task_score: 1.859
avg_accuracy: 0.620

✅ Evaluation (use_gt_cogmap)

overall:
n_total: 27
total_score: 26.500
avg_accuracy: 0.981
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 2.500
avg_accuracy: 0.833
PovEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
BackwardPovTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Action2ViewEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
View2ActionTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
AlloMappingEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
RotEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Location2ViewEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
View2LocationTextEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1

✅ Evaluation (use_model_cogmap)

overall:
n_total: 27
total_score: 17.840
avg_accuracy: 0.661
per_task:
DirectionEvaluationTask:
n_total: 3
task_score: 1.500
avg_accuracy: 0.500
PovEvaluationTask:
n_total: 3
task_score: 1.500
avg_accuracy: 0.500
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: 1
avg_accuracy: 0.333
AlloMappingEvaluationTask:
n_total: 3
task_score: 2.157
avg_accuracy: 0.719
RotEvaluationTask:
n_total: 3
task_score: 3
avg_accuracy: 1
Location2ViewEvaluationTask:
n_total: 3
task_score: 1.500
avg_accuracy: 0.500
View2LocationTextEvaluationTask:
n_total: 3
task_score: 1.682
avg_accuracy: 0.561

🧠 Cognitive Map

exploration:
error:
local_vs_gt_local_avg:
dir: 0.910
facing: 1
pos: 0.884
overall: 0.931
global_vs_gt_global_avg:
dir: 0.801
facing: 0.958
pos: 0.758
overall: 0.839
agent_vs_gt_agent_avg:
dir: 1
facing: 1
pos: 0.876
overall: 0.959
newly_observed_vs_gt_local_avg:
dir: 0.862
facing: 1
pos: 0.832
overall: 0.898
correctness:
last_global_vs_gt_full:
dir: 0.800
facing: 1
pos: 0.722
overall: 0.841
consistency:
local_vs_global_avg:
dir: 0.833
facing: 1
pos: 0.801
overall: 0.878
position_update_avg: 0.593
facing_update_avg: 0.949
position_stability_avg: 0.593
facing_stability_avg: 0.949
fog_probe:
f1_avg: 0.508
precision_avg: 0.649
recall_avg: 0.468
cogmap_fb:
metrics:
changed:
dir: None
pos: 0.626
facing: 1
overall: None
retention:
dir: None
pos: 0.309
facing: 0
overall: None
unchanged:
dir: 0.748
facing: 0.896
pos: 0.697
overall: 0.780
inertia: 0.023
inertia_list: [8.867500991375526e-05, 0.04670215852138788]
unchanged_retention:
dir: None
pos: 0.652
facing: 1
overall: None
unchanged_retention_minus_retention:
pos: 0.774
facing: 1
unchanged_exploration:
dir: 0.818
facing: 1
pos: 0.740
overall: 0.853

🧭 False Belief CogMap

inertia: 0.023
changed:
dir: None
pos: 0.626
facing: 1
overall: None
retention:
dir: None
pos: 0.309
facing: 0
overall: None
unchanged:
dir: 0.748
facing: 0.896
pos: 0.697
overall: 0.780
unchanged_retention:
dir: None
pos: 0.652
facing: 1
overall: None
unchanged_retention_minus_retention:
pos: 0.774
facing: 1
unchanged_exploration:
dir: 0.818
facing: 1
pos: 0.740
overall: 0.853

📊 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"
  },
  "laptop": {
    "position": [
      -2,
      3
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "laptop": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "laptop": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  }
}
🗺️ Symbolic Fog Map
###############
#...AE.#......#
#..B.C.#......#
#.....*#......#
#......#......#
#......+......#
#.F.D..#......#
#####+#########
##......#######
##......#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: B, D, F
🎯 Ground Truth: F, D, B
🧠 Cognitive Map Metrics
Global:
dir: 1
facing: 1
pos: 0.838
overall: 0.946
Global (Full):
dir: 0.025
facing: 0.200
pos: 0.112
overall: 0.112
Local:
dir: 1
facing: 1
pos: 0.779
overall: 0.926
Local (Newly):
dir: 1
facing: 1
pos: 0.779
overall: 0.926
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.071
edge_coverage: 0.024
is_action_fail: False
step: 1
action_counts:
move: 0
rotate: 0
return: 0
observe: 1
term: 0
forced_term: 0
query: 0
information_gain: 0.057
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"
  },
  "laptop": {
    "position": [
      -1,
      3
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {}
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#...E.F#......#
#..B.C.#......#
#..D..*#......#
#......#......#
#...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: 0.333
facing: 1
pos: 0.882
overall: 0.739
Global (Full):
dir: 0.008
facing: 0.200
pos: 0.118
overall: 0.109
Local:
(none)
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 1
overall: 1
📈 Turn Metrics
node_coverage: 0.071
edge_coverage: 0.024
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: 0.057
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"
  },
  "laptop": {
    "position": [
      -2,
      3
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      2,
      -3
    ],
    "facing": "west"
  },
  "yellow door": {
    "position": [
      -1,
      -5
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      0,
      0
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "red door": {
      "position": [
        -2,
        2
      ]
    },
    "yellow door": {
      "position": [
        1,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "red door": {
    "position": [
      -1,
      2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      4
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "red door": {
      "position": [
        -2,
        2
      ]
    },
    "yellow door": {
      "position": [
        1,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "red door": {
    "position": [
      -1,
      2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      1,
      4
    ],
    "facing": "north"
  }
}
🗺️ Symbolic Fog Map
###############
#......#......#
#...C..#......#
#.....*#......#
#...BE.#......#
#..A.F.+......#
#....D.#......#
#####+#########
##......#######
##......#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, B, C, E, F
🎯 Ground Truth: B, A, C
🧠 Cognitive Map Metrics
Global:
dir: 1
facing: 1
pos: 0.821
overall: 0.940
Global (Full):
dir: 0.083
facing: 0.200
pos: 0.219
overall: 0.167
Local:
dir: 1
facing: 1
pos: 0.838
overall: 0.946
Local (Newly):
dir: 1
facing: 1
pos: 0.838
overall: 0.946
Fog Probe:
precision: 0.600
recall: 1
overall: 0.750
📈 Turn Metrics
node_coverage: 0.214
edge_coverage: 0.073
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: 0.160
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 3
Current state
State at Turn 3

🔄 Turn 4

💬 Assistant Action
Actions: [JumpTo(red door), Rotate(-90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "east"
  },
  "laptop": {
    "position": [
      -2,
      3
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      2,
      -2
    ]
  },
  "yellow door": {
    "position": [
      -2,
      -5
    ]
  },
  "backpack": {
    "position": [
      4,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      6,
      1
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      4,
      1
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "backpack": {
      "position": [
        0,
        2
      ],
      "facing": "-x"
    },
    "bike": {
      "position": [
        -3,
        5
      ],
      "facing": "-x"
    },
    "books": {
      "position": [
        -5,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "backpack": {
    "position": [
      0,
      2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      -2,
      4
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      -4,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "backpack": {
      "position": [
        0,
        2
      ],
      "facing": "-x"
    },
    "bike": {
      "position": [
        -3,
        5
      ],
      "facing": "-x"
    },
    "books": {
      "position": [
        -5,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "backpack": {
    "position": [
      0,
      2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      -2,
      4
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      -4,
      4
    ],
    "facing": "east"
  }
}
🗺️ Symbolic Fog Map
###############
#..H...#.EJ...#
#..F.D.#..B...#
#.C....#L.....#
#....G.#......#
#......*A.....#
#.....I#....K.#
#####+#########
##......#######
##......#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: C
🎯 Ground Truth: F, C, H, E, L, J
🧠 Cognitive Map Metrics
Global:
dir: 0.929
facing: 1
pos: 0.801
overall: 0.910
Global (Full):
dir: 0.217
facing: 0.400
pos: 0.374
overall: 0.330
Local:
dir: 1
facing: 1
pos: 0.815
overall: 0.938
Local (Newly):
dir: 1
facing: 1
pos: 0.815
overall: 0.938
Fog Probe:
precision: 1
recall: 0.167
overall: 0.286
📈 Turn Metrics
node_coverage: 0.429
edge_coverage: 0.146
is_action_fail: False
step: 4
action_counts:
move: 1
rotate: 3
return: 0
observe: 4
term: 0
forced_term: 0
query: 0
information_gain: 0.285
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: [Rotate(90), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      1,
      -1
    ],
    "facing": "south"
  },
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      1,
      -1
    ]
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ]
  },
  "backpack": {
    "position": [
      3,
      -1
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      4,
      2
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      4,
      3
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      -2
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      -2
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        2,
        2
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      2,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        2,
        2
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#I...H.#..A...#
#......#G.....#
#..L...#D.....#
#....C.#.KJ...#
#B.....*.....F#
#...E..#......#
#####+#########
##......#######
##......#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: B, F, I
🎯 Ground Truth: B, I, L, A, G, D
🧠 Cognitive Map Metrics
Global:
dir: 0.821
facing: 1
pos: 0.810
overall: 0.877
Global (Full):
dir: 0.192
facing: 0.400
pos: 0.378
overall: 0.323
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 0.667
recall: 0.333
overall: 0.444
📈 Turn Metrics
node_coverage: 0.429
edge_coverage: 0.171
is_action_fail: False
step: 5
action_counts:
move: 1
rotate: 4
return: 0
observe: 5
term: 0
forced_term: 0
query: 0
information_gain: 0.349
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: [Rotate(180), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      2,
      -2
    ],
    "facing": "north"
  },
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      2,
      -2
    ]
  },
  "yellow door": {
    "position": [
      -2,
      -5
    ]
  },
  "backpack": {
    "position": [
      4,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      5,
      1
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      5,
      0
    ]
  },
  "pillow": {
    "position": [
      6,
      1
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      -2
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      1,
      -2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "laptop": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "pillow": {
      "position": [
        3,
        5
      ]
    },
    "books": {
      "position": [
        5,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "laptop": {
    "position": [
      -2,
      4
    ],
    "facing": "south"
  },
  "pillow": {
    "position": [
      2,
      4
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      4,
      4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "laptop": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "pillow": {
      "position": [
        3,
        5
      ]
    },
    "books": {
      "position": [
        5,
        5
      ]
    }
  }
}
🎯 Ground Truth
{
  "pillow": {
    "position": [
      2,
      4
    ],
    "facing": "east"
  }
}
🗺️ Symbolic Fog Map
###############
#F.....#......#
#.D....#......#
#....C.#......#
#......#......#
#E....A*......#
#.....B#......#
#####+#########
##......#######
##......#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: F, B
🎯 Ground Truth: D, E, F
🧠 Cognitive Map Metrics
Global:
dir: 0.833
facing: 1
pos: 0.756
overall: 0.863
Global (Full):
dir: 0.250
facing: 0.400
pos: 0.403
overall: 0.351
Local:
dir: 1
facing: 1
pos: 0.779
overall: 0.926
Local (Newly):
dir: 1
facing: 1
pos: 0.779
overall: 0.926
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.500
edge_coverage: 0.220
is_action_fail: False
step: 6
action_counts:
move: 1
rotate: 5
return: 0
observe: 6
term: 0
forced_term: 0
query: 0
information_gain: 0.422
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(180), JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      -4
    ],
    "facing": "south"
  },
  "laptop": {
    "position": [
      -2,
      3
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      2,
      -1
    ]
  },
  "yellow door": {
    "position": [
      0,
      -4
    ]
  },
  "backpack": {
    "position": [
      4,
      -1
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      5,
      2
    ]
  },
  "books": {
    "position": [
      6,
      2
    ]
  },
  "bike": {
    "position": [
      7,
      2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      0,
      -6
    ],
    "facing": "west"
  },
  "table": {
    "position": [
      -2,
      -6
    ]
  },
  "chair": {
    "position": [
      2,
      -7
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      2,
      -9
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -2,
        6
      ],
      "facing": "-y"
    },
    "suitcase": {
      "position": [
        0,
        2
      ],
      "facing": "+x"
    },
    "chair": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "table": {
      "position": [
        2,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "suitcase": {
    "position": [
      0,
      2
    ],
    "facing": "west"
  },
  "table": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "chair": {
    "position": [
      -2,
      4
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -2,
      6
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -2,
        6
      ],
      "facing": "-y"
    },
    "suitcase": {
      "position": [
        0,
        2
      ],
      "facing": "+x"
    },
    "chair": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "table": {
      "position": [
        2,
        3
      ]
    }
  }
}
🎯 Ground Truth
{
  "suitcase": {
    "position": [
      0,
      2
    ],
    "facing": "west"
  },
  "table": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "chair": {
    "position": [
      -2,
      4
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -2,
      6
    ],
    "facing": "north"
  }
}
🗺️ Symbolic Fog Map
###############
#.J...E#......#
#...B..#......#
#......#......#
#...L.I#......#
#.C....+......#
#......#......#
#####*#########
##DG...A#######
##......#######
##..K..H#######
##......#######
##..F...#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H, I, J, K, L
🤖 Predicted: A, C, D, G
🎯 Ground Truth: J, C, L, A, G, D
🧠 Cognitive Map Metrics
Global:
dir: 0.885
facing: 1
pos: 0.767
overall: 0.884
Global (Full):
dir: 0.575
facing: 0.700
pos: 0.614
overall: 0.630
Local:
dir: 0.700
facing: 1
pos: 0.858
overall: 0.853
Local (Newly):
dir: 0.700
facing: 1
pos: 0.858
overall: 0.853
Fog Probe:
precision: 1
recall: 0.667
overall: 0.800
📈 Turn Metrics
node_coverage: 0.786
edge_coverage: 0.317
is_action_fail: False
step: 7
action_counts:
move: 2
rotate: 6
return: 0
observe: 7
term: 0
forced_term: 0
query: 0
information_gain: 0.656
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": [
      0,
      -5
    ],
    "facing": "west"
  },
  "laptop": {
    "position": [
      -2,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      3,
      -2
    ]
  },
  "yellow door": {
    "position": [
      0,
      -5
    ]
  },
  "backpack": {
    "position": [
      5,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      6,
      0
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      6,
      1
    ]
  },
  "pillow": {
    "position": [
      5,
      1
    ]
  },
  "television": {
    "position": [
      2,
      -9
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      0,
      -7
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      3,
      -8
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      -2,
      -7
    ]
  },
  "shoppingcart": {
    "position": [
      -2,
      -3
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoppingcart": {
      "position": [
        2,
        2
      ],
      "facing": "+x"
    },
    "table": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "table": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  },
  "shoppingcart": {
    "position": [
      2,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "shoppingcart": {
      "position": [
        2,
        2
      ],
      "facing": "+x"
    },
    "table": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "shoppingcart": {
    "position": [
      2,
      2
    ],
    "facing": "north"
  }
}
🗺️ Symbolic Fog Map
###############
#.DC...#......#
#..A.F.#......#
#..G...#......#
#.....B#......#
#......+......#
#......#......#
#####*#########
##.....H#######
##......#######
##......#######
##......#######
##...E..#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F, G, H
🤖 Predicted: C, F, H
🎯 Ground Truth: G, A, D, H
🧠 Cognitive Map Metrics
Global:
dir: 0.846
facing: 1
pos: 0.755
overall: 0.867
Global (Full):
dir: 0.642
facing: 0.800
pos: 0.654
overall: 0.699
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
dir: 1
facing: 1
pos: 1
overall: 1
Fog Probe:
precision: 0.333
recall: 0.250
overall: 0.286
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.341
is_action_fail: False
step: 8
action_counts:
move: 2
rotate: 7
return: 0
observe: 8
term: 0
forced_term: 0
query: 0
information_gain: 0.716
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(180), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "east"
  },
  "laptop": {
    "position": [
      -2,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      3,
      -1
    ]
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ]
  },
  "backpack": {
    "position": [
      5,
      -1
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      7,
      1
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      6,
      1
    ]
  },
  "pillow": {
    "position": [
      5,
      1
    ]
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      2,
      -6
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      2,
      -7
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      -3,
      -6
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "east"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "red door": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "red door": {
    "position": [
      -2,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "red door": {
      "position": [
        -2,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#......#......#
#B.....#......#
#.C....#......#
#D..F..#......#
#......+......#
#E..A..#......#
#####*#########
##......#######
##......#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: C
🎯 Ground Truth: B, F, C
🧠 Cognitive Map Metrics
Global:
dir: 0.747
facing: 1
pos: 0.728
overall: 0.825
Global (Full):
dir: 0.567
facing: 0.800
pos: 0.631
overall: 0.666
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 1
recall: 0.333
overall: 0.500
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.341
is_action_fail: False
step: 9
action_counts:
move: 2
rotate: 8
return: 0
observe: 9
term: 0
forced_term: 0
query: 0
information_gain: 0.764
reward: -0.100
is_done: False
is_valid_action: True
Previous state
State before Turn 9
Current state
State at Turn 9

🔄 Turn 10

💬 Assistant Action
Actions: [Rotate(90), JumpTo(suitcase), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      -7
    ],
    "facing": "south"
  },
  "laptop": {
    "position": [
      -2,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      3,
      0
    ]
  },
  "yellow door": {
    "position": [
      0,
      -5
    ]
  },
  "shoppingcart": {
    "position": [
      -2,
      -3
    ],
    "facing": "west"
  },
  "backpack": {
    "position": [
      5,
      0
    ]
  },
  "bike": {
    "position": [
      6,
      3
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      5,
      3
    ]
  },
  "pillow": {
    "position": [
      4,
      3
    ]
  },
  "suitcase": {
    "position": [
      0,
      -7
    ],
    "facing": "west"
  },
  "television": {
    "position": [
      2,
      -9
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      3,
      -9
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      -3,
      -8
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "chair": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "chair": {
    "position": [
      -2,
      2
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -2,
      4
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "chair": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#.CE...#......#
#.....F#......#
#..D...#......#
#...B..#......#
#..A...+......#
#......#......#
#####+#########
##......#######
##...*..#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: A, C
🎯 Ground Truth: D, B, C
🧠 Cognitive Map Metrics
Global:
dir: 0.736
facing: 0.750
pos: 0.709
overall: 0.732
Global (Full):
dir: 0.558
facing: 0.600
pos: 0.615
overall: 0.591
Local:
dir: 0.667
facing: 1
pos: 0.805
overall: 0.824
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.390
is_action_fail: False
step: 10
action_counts:
move: 3
rotate: 9
return: 0
observe: 10
term: 0
forced_term: 0
query: 0
information_gain: 0.773
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), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -1,
      -7
    ],
    "facing": "west"
  },
  "laptop": {
    "position": [
      -2,
      2
    ],
    "facing": "south"
  },
  "shoppingcart": {
    "position": [
      -3,
      -3
    ],
    "facing": "north"
  },
  "red door": {
    "position": [
      3,
      -1
    ]
  },
  "yellow door": {
    "position": [
      -1,
      -5
    ]
  },
  "backpack": {
    "position": [
      5,
      -1
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      7,
      3
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      6,
      3
    ]
  },
  "pillow": {
    "position": [
      7,
      2
    ]
  },
  "suitcase": {
    "position": [
      -1,
      -7
    ],
    "facing": "west"
  },
  "television": {
    "position": [
      1,
      -9
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      0,
      -9
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      -3,
      -7
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "table": {
      "position": [
        0,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "table": {
    "position": [
      0,
      2
    ],
    "facing": "east"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "table": {
      "position": [
        0,
        2
      ]
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#......#......#
#.E...B#......#
#.CF.D.#......#
#.A....#......#
#......+......#
#......#......#
#####+#########
##......#######
##...*..#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: (none)
🎯 Ground Truth: E, F, C
🧠 Cognitive Map Metrics
Global:
dir: 0.758
facing: 1
pos: 0.707
overall: 0.822
Global (Full):
dir: 0.575
facing: 0.800
pos: 0.613
overall: 0.663
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 0
recall: 0
overall: 0
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.415
is_action_fail: False
step: 11
action_counts:
move: 3
rotate: 10
return: 0
observe: 11
term: 0
forced_term: 0
query: 0
information_gain: 0.773
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: [Rotate(-90), JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -1,
      -7
    ],
    "facing": "south"
  },
  "laptop": {
    "position": [
      -2,
      3
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      4,
      -3
    ],
    "facing": "west"
  },
  "yellow door": {
    "position": [
      -1,
      -5
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -4,
      -2
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      6,
      -3
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      6,
      -1
    ],
    "facing": "west"
  },
  "books": {
    "position": [
      6,
      0
    ]
  },
  "pillow": {
    "position": [
      7,
      0
    ]
  },
  "suitcase": {
    "position": [
      -1,
      -7
    ],
    "facing": "west"
  },
  "table": {
    "position": [
      -3,
      -7
    ]
  },
  "television": {
    "position": [
      2,
      -8
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      2,
      -9
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "south"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "south"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "chair": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "chair": {
    "position": [
      -2,
      2
    ],
    "facing": "north"
  },
  "television": {
    "position": [
      -2,
      4
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "television": {
      "position": [
        -3,
        5
      ],
      "facing": "-y"
    },
    "chair": {
      "position": [
        -2,
        3
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#....E.#......#
#.FBD..#......#
#C.....#......#
#..A...#......#
#......+......#
#......#......#
#####+#########
##......#######
##...*..#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: F, D
🎯 Ground Truth: A, F, B
🧠 Cognitive Map Metrics
Global:
dir: 0.736
facing: 0.625
pos: 0.682
overall: 0.681
Global (Full):
dir: 0.558
facing: 0.500
pos: 0.591
overall: 0.550
Local:
dir: 0.667
facing: 1
pos: 0.805
overall: 0.824
Local (Newly):
(none)
Fog Probe:
precision: 0.500
recall: 0.333
overall: 0.400
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.415
is_action_fail: True
step: 12
action_counts:
move: 3
rotate: 11
return: 0
observe: 12
term: 0
forced_term: 0
query: 0
information_gain: 0.773
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: [Rotate(180), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "north"
  },
  "laptop": {
    "position": [
      -2,
      2
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      2,
      -2
    ]
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ]
  },
  "backpack": {
    "position": [
      4,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      5,
      -1
    ]
  },
  "pillow": {
    "position": [
      6,
      -1
    ]
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "television": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -7
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      -3,
      -6
    ]
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -6
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        0,
        2
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
{
  "yellow door": {
    "position": [
      0,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "yellow door": {
      "position": [
        0,
        2
      ],
      "facing": "-y"
    }
  }
}
🎯 Ground Truth
(no data)
🗺️ Symbolic Fog Map
###############
#....F.#......#
#..E...#......#
#......#......#
#..BC.A#......#
#.D....+......#
#......#......#
#####+#########
##......#######
##...*..#######
##......#######
##......#######
##......#######
##......#######
###############
🔍 Fog Probe JSONs
📍 Candidates: A, B, C, D, E, F
🤖 Predicted: D, E, F
🎯 Ground Truth: B, E, C
🧠 Cognitive Map Metrics
Global:
dir: 0.769
facing: 1
pos: 0.748
overall: 0.839
Global (Full):
dir: 0.583
facing: 0.800
pos: 0.648
overall: 0.677
Local:
dir: 1
facing: 1
pos: 1
overall: 1
Local (Newly):
(none)
Fog Probe:
precision: 0.333
recall: 0.333
overall: 0.333
📈 Turn Metrics
node_coverage: 0.857
edge_coverage: 0.415
is_action_fail: False
step: 13
action_counts:
move: 3
rotate: 12
return: 0
observe: 13
term: 0
forced_term: 0
query: 0
information_gain: 0.773
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: [JumpTo(yellow door), Observe()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      0,
      -5
    ],
    "facing": "north"
  },
  "laptop": {
    "position": [
      -1,
      3
    ],
    "facing": "south"
  },
  "yellow door": {
    "position": [
      0,
      -5
    ]
  },
  "red door": {
    "position": [
      4,
      -1
    ]
  },
  "shoppingcart": {
    "position": [
      -3,
      -3
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      -1
    ],
    "facing": "east"
  },
  "truck": {
    "position": [
      -5,
      -2
    ],
    "facing": "west"
  },
  "backpack": {
    "position": [
      6,
      -1
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      8,
      2
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      7,
      2
    ]
  },
  "pillow": {
    "position": [
      6,
      2
    ]
  },
  "suitcase": {
    "position": [
      0,
      -7
    ],
    "facing": "west"
  },
  "table": {
    "position": [
      -3,
      -7
    ]
  },
  "television": {
    "position": [
      3,
      -10
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      3,
      -11
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "laptop": {
      "position": [
        0,
        6
      ],
      "facing": "-y"
    },
    "desklamp": {
      "position": [
        -2,
        6
      ],
      "facing": "+x"
    },
    "shoppingcart": {
      "position": [
        -2,
        3
      ],
      "facing": "+y"
    },
    "truck": {
      "position": [
        -5,
        6
      ],
      "facing": "-x"
    },
    "red door": {
      "position": [
        3,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "desklamp": {
    "position": [
      -2,
      4
    ],
    "facing": "east"
  },
  "laptop": {
    "position": [
      0,
      6
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      2,
      2
    ],
    "facing": "east"
  },
  "truck": {
    "position": [
      -4,
      6
    ],
    "facing": "west"
  },
  "shoppingcart": {
    "position": [
      -2,
      2
    ],
    "facing": "north"
  }
}
📊 Cognitive Map JSONs
🤖 Predicted
{
  "origin": "agent",
  "objects": {
    "laptop": {
      "position": [
        0,
        6
      ],
      "facing": "-y"
    },
    "desklamp": {
      "position": [
        -2,
        6
      ],
      "facing": "+x"
    },
    "shoppingcart": {
      "position": [
        -2,
        3
      ],
      "facing": "+y"
    },
    "truck": {
      "position": [
        -5,
        6
      ],
      "facing": "-x"
    },
    "red door": {
      "position": [
        3,
        2
      ]
    }
  }
}
🎯 Ground Truth
{
  "desklamp": {
    "position": [
      -2,
      4
    ],
    "facing": "east"
  },
  "truck": {
    "position": [
      -4,
      6
    ],
    "facing": "west"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.825
facing: 1
pos: 0.650
overall: 0.825
Global (Full):
dir: 0.825
facing: 1
pos: 0.650
overall: 0.825
Local:
dir: 0.800
facing: 1
pos: 0.811
overall: 0.870
Local (Newly):
dir: 0.333
facing: 1
pos: 0.756
overall: 0.696
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.488
is_action_fail: False
step: 14
action_counts:
move: 4
rotate: 12
return: 0
observe: 14
term: 0
forced_term: 0
query: 0
information_gain: 0.914
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: [Term()]
📊 Cognitive Map JSONs
🤖 Predicted
{
  "agent": {
    "position": [
      -2,
      -5
    ],
    "facing": "north"
  },
  "laptop": {
    "position": [
      -2,
      3
    ],
    "facing": "south"
  },
  "red door": {
    "position": [
      3,
      -2
    ]
  },
  "yellow door": {
    "position": [
      -2,
      -5
    ]
  },
  "shoppingcart": {
    "position": [
      -5,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -6,
      0
    ],
    "facing": "west"
  },
  "desklamp": {
    "position": [
      -5,
      -1
    ],
    "facing": "east"
  },
  "backpack": {
    "position": [
      5,
      -2
    ],
    "facing": "north"
  },
  "bike": {
    "position": [
      7,
      2
    ],
    "facing": "north"
  },
  "books": {
    "position": [
      6,
      2
    ]
  },
  "pillow": {
    "position": [
      5,
      2
    ]
  },
  "suitcase": {
    "position": [
      -2,
      -7
    ],
    "facing": "west"
  },
  "television": {
    "position": [
      0,
      -9
    ],
    "facing": "north"
  },
  "chair": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "table": {
    "position": [
      -4,
      -7
    ]
  }
}
🎯 Ground Truth (Observed)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  }
}
🎯 Ground Truth (Full)
{
  "laptop": {
    "position": [
      -1,
      2
    ],
    "facing": "south"
  },
  "television": {
    "position": [
      1,
      -10
    ],
    "facing": "north"
  },
  "backpack": {
    "position": [
      3,
      -2
    ],
    "facing": "north"
  },
  "desklamp": {
    "position": [
      -3,
      0
    ],
    "facing": "east"
  },
  "suitcase": {
    "position": [
      -1,
      -6
    ],
    "facing": "west"
  },
  "bike": {
    "position": [
      5,
      0
    ],
    "facing": "north"
  },
  "shoppingcart": {
    "position": [
      -3,
      -2
    ],
    "facing": "north"
  },
  "truck": {
    "position": [
      -5,
      2
    ],
    "facing": "west"
  },
  "chair": {
    "position": [
      1,
      -8
    ],
    "facing": "north"
  },
  "pillow": {
    "position": [
      3,
      2
    ],
    "facing": "east"
  },
  "table": {
    "position": [
      -3,
      -6
    ],
    "facing": "east"
  },
  "books": {
    "position": [
      5,
      2
    ],
    "facing": "east"
  },
  "red door": {
    "position": [
      1,
      -2
    ],
    "facing": "east"
  },
  "yellow door": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  },
  "agent": {
    "position": [
      -1,
      -4
    ],
    "facing": "north"
  }
}
🧠 Cognitive Map Metrics
Global:
dir: 0.800
facing: 1
pos: 0.722
overall: 0.841
Global (Full):
dir: 0.800
facing: 1
pos: 0.722
overall: 0.841
Local:
(none)
Local (Newly):
(none)
Fog Probe:
(none)
📈 Turn Metrics
node_coverage: 1
edge_coverage: 0.488
is_action_fail: False
step: 15
action_counts:
move: 4
rotate: 12
return: 0
observe: 14
term: 1
forced_term: 0
query: 0
information_gain: 0.914
reward: -0.100
is_done: True
is_valid_action: True
Previous state
State before Turn 15
Current state
State at Turn 15

🧭 False Belief Exploration

🔄 FB Turn 16

💬 Assistant Action
Actions: [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: 0.699
overall: 0.829
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): []
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['laptop']
Current state
State at Turn 1

🔄 FB Turn 17

💬 Assistant Action
Actions: [Rotate(-90), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: chair:
dir: None
pos: 0.838
facing: None
overall: None
Retention: chair:
dir: None
pos: 0.206
facing: None
overall: None
Unchanged (all):
dir: 0.773
facing: 0.833
pos: 0.711
overall: 0.772
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): ['chair']
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: ['chair']
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['chair']
newly_observed_unchanged_objects: ['desklamp', 'truck']
Previous state
State before Turn 2
Current state
State at Turn 2

🔄 FB Turn 18

💬 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: 0.742
facing: 1
pos: 0.705
overall: 0.816
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): []
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['red door', 'yellow door']
Previous state
State before Turn 3
Current state
State at Turn 3

🔄 FB Turn 19

💬 Assistant Action
Actions: [JumpTo(red door), Rotate(-90), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: backpack:
dir: None
pos: None
facing: 1
overall: None
Retention: backpack:
dir: None
pos: None
facing: 0
overall: None
Changed: bike:
dir: None
pos: None
facing: 1
overall: None
Retention: bike:
dir: None
pos: None
facing: 0
overall: None
Unchanged (all):
dir: 0.788
facing: 0.833
pos: 0.783
overall: 0.802
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): ['backpack', 'bike']
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: ['backpack', 'bike']
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['backpack', 'bike']
newly_observed_unchanged_objects: ['books']
Previous state
State before Turn 4
Current state
State at Turn 4

🔄 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: 0.682
facing: 0.667
pos: 0.655
overall: 0.668
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): []
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: ['pillow']
Previous state
State before Turn 5
Current state
State at Turn 5

🔄 FB Turn 21

💬 Assistant Action
Actions: [Rotate(180), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.742
facing: 1
pos: 0.689
overall: 0.810
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): []
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', '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 22

💬 Assistant Action
Actions: [JumpTo(yellow door), Rotate(180), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Unchanged (all):
dir: 0.712
facing: 0.833
pos: 0.655
overall: 0.733
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): []
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: []
pred_unchanged_keys: ['grid', 'objects']
🧭 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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 7
Current state
State at Turn 7

🔄 FB Turn 23

💬 Assistant Action
Actions: [Rotate(180), Observe()]
📈 Turn Metrics
reward: -0.100
is_done: False
is_valid_action: True
🧭 False Belief Cogmap Metrics
Changed: shoppingcart:
dir: None
pos: 0.413
facing: None
overall: None
Retention: shoppingcart:
dir: None
pos: 0.413
facing: None
overall: None
Unchanged (all):
dir: 0.758
facing: 1
pos: 0.678
overall: 0.812
🧾 False Belief Object Sets
all_objects: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', 'yellow door']
all_changed_objects: ['backpack', 'bike', 'chair', 'shoppingcart']
newly_observed_changed (this turn): ['shoppingcart']
unchanged_objects: ['books', 'desklamp', 'laptop', 'pillow', 'red door', 'suitcase', 'table', 'television', 'truck', 'yellow door']
pred_changed_keys: ['shoppingcart']
pred_unchanged_keys: ['backpack', 'bike', 'books', 'chair', 'desklamp', 'laptop', 'pillow', 'red door', 'shoppingcart', 'suitcase', 'table', 'television', 'truck', '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': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: []
newly_observed_changed_objects: ['shoppingcart']
newly_observed_unchanged_objects: ['television', 'table', 'suitcase']
Previous state
State before Turn 8
Current state
State at Turn 8

🔄 FB Turn 24

💬 Assistant Action
Actions: [Term(changes="chair: position, shoppingcart: position, backpack: orientation, bike: orientation")]
📈 Turn Metrics
reward: 1
is_done: True
is_valid_action: True
success: 1
🧭 False Belief Info
step: 9
correctly_identified_changes: 1
f1_overall: 1
f1_position: 1
f1_facing: 1
action_cost: 8
action_cost_after_seen: 0
ground_truth_changes: [{'name': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'chair', 'pos': True}]
reported_changes: [{'name': 'chair', 'pos': True}, {'name': 'shoppingcart', 'pos': True}, {'name': 'backpack', 'ori': True}, {'name': 'bike', 'ori': True}]
newly_observed_changed_objects: []
newly_observed_unchanged_objects: []
Previous state
State before Turn 9
Current state
State at Turn 9

📊 Evaluation (default)

📊 Task: DirectionEvaluationTask

Question 1 (ID: c9de6790a897c673)

✅ Evaluation Results
id: c9de6790a897c673
question: You return to your starting position and face north. From a Top-Down map, describe where truck is relative to desklamp. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: 7360e44dad33a0d5)

✅ Evaluation Results
id: 7360e44dad33a0d5
question: You return to your starting position and face north. From a Top-Down map, describe where books is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 50faba75f48ab8cb)

✅ Evaluation Results
id: 50faba75f48ab8cb
question: You return to your starting position and face north. From a Top-Down map, describe where backpack is relative to table. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north east, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: fffaede931ebf4f3)

✅ Evaluation Results
id: fffaede931ebf4f3
question: Now you jump to laptop's direction, facing its direction. Describe where desklamp 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
Q1: PovEvaluationTask

Question 2 (ID: b8cd5a53479d1c3e)

✅ Evaluation Results
id: b8cd5a53479d1c3e
question: Now you jump to backpack's direction, facing its direction. Describe where books is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, slightly far
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: a67a1cef66054f66)

✅ Evaluation Results
id: a67a1cef66054f66
question: Now you jump to desklamp's direction, facing its direction. Describe where laptop 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
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 5902e70da1b23e88)

✅ Evaluation Results
id: 5902e70da1b23e88
question: Now you jump to an object's position, facing its direction. You observe that laptop is front-left, mid distance, facing right; red door is front-right, slightly far, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 11]
final_ori: [1, 0]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: default
Evaluation state
Q1: BackwardPovTextEvaluationTask

Question 2 (ID: 7f5c758512898b6b)

✅ Evaluation Results
id: 7f5c758512898b6b
question: Now you jump to an object's position, facing its direction. You observe that red door is front-left, slightly far, on left wall; shoppingcart is front-right, slightly far, facing backward; desklamp is front-right, mid distance, facing left. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: laptop
final_pos: [5, 13]
final_ori: [0, -1]
final_observation: [{'name': 'red door', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'on left wall'}, {'name': 'shoppingcart', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing left'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: default
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: 7f4f9f9c8d6112b9)

✅ Evaluation Results
id: 7f4f9f9c8d6112b9
question: Now you jump to an object's position, facing its direction. You observe that bike is front-right, mid distance, facing forward; pillow is front, mid distance; books is front-right, slightly far. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: backpack
final_pos: [9, 9]
final_ori: [0, 1]
final_observation: [{'name': 'bike', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 286b5d2b65475d4f)

✅ Evaluation Results
id: 286b5d2b65475d4f
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. Rotate(-90) 4. Jump to the object at front-left, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of laptop 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: e413d4447d27b08e)

✅ Evaluation Results
id: e413d4447d27b08e
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-180) 2. Jump to the object at front-slight-right, slightly far. 3. Jump to the object at front-left, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of suitcase relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 45597bafd7e0cdbc)

✅ Evaluation Results
id: 45597bafd7e0cdbc
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-left, mid distance. 3. Rotate(90) 4. Jump to the object at front-right, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of desklamp relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: default
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 5ed57112b3bfdc2e)

✅ Evaluation Results
id: 5ed57112b3bfdc2e
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: laptop is at front-left, slightly far, facing backward; pillow is at front-right, slightly far; books is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 9]
final_ori: [0, 1]
room_id: [1, 3]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'pillow', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 9.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: default
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 1f898b79fbf64cc4)

✅ Evaluation Results
id: 1f898b79fbf64cc4
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: shoppingcart is at front-left, mid distance, facing forward; laptop is at front, slightly far, facing backward; desklamp is at front-left, slightly far, facing right 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, 7]
final_ori: [0, 1]
room_id: [2, 1]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'laptop', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 7.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: default
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 8a8f0522e5b332f6)

✅ Evaluation Results
id: 8a8f0522e5b332f6
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: backpack is at front, mid distance, facing backward; bike is at front-left, mid distance, facing backward; red door is at front-right, slightly far, on right 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: [9, 13]
final_ori: [0, -1]
room_id: 3
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'red door'], ['rotate', 180], ['jumpto', 'pillow'], ['rotate', 180]]
final_observation: [{'name': 'backpack', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'bike', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on right wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: False
ori_match: True
final_pos: [11.0, 13.0]
final_ori: [0, -1]
visible_match: False
score: 0
evaluation_mode: default
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2fec3ac651cf4a7c)

✅ Evaluation Results
id: 2fec3ac651cf4a7c
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: truck, desklamp, chair, laptop. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 2], [-3, 0], [1, -8], [-1, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.653
threshold: 0.900
score: 0.653
evaluation_mode: default
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 237ae2871d72362b)

✅ Evaluation Results
id: 237ae2871d72362b
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: backpack, chair, bike. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[3, -2], [1, -8], [5, 0]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.712
threshold: 0.900
score: 0.712
evaluation_mode: default
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 0ca18bd6fca57b5f)

✅ Evaluation Results
id: 0ca18bd6fca57b5f
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, backpack, bike, books. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, -6], [3, -2], [5, 0], [5, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.697
threshold: 0.900
score: 0.697
evaluation_mode: default
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: 4831d162b78edf8c)

✅ Evaluation Results
id: 4831d162b78edf8c
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, desklamp, laptop, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['laptop', 'desklamp', 'table', 'chair']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: b3bb94ba48268066)

✅ Evaluation Results
id: b3bb94ba48268066
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: backpack, bike, chair, pillow, shoppingcart. 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: ['pillow', 'bike', 'backpack', 'chair', 'shoppingcart']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: a73f3abfbc74d987)

✅ Evaluation Results
id: a73f3abfbc74d987
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: laptop, table, television, truck. 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: ['laptop', 'truck', 'table', 'television']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: RotEvaluationTask

📊 Task: RotDualEvaluationTask

Question 1 (ID: ac2a6bf257762996)

✅ Evaluation Results
id: ac2a6bf257762996
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: laptop, desklamp, table, chair 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: fabe192c1f42a07a)

✅ Evaluation Results
id: fabe192c1f42a07a
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: pillow, bike, backpack, chair, shoppingcart 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: 1fe9e0ec40250bfb)

✅ Evaluation Results
id: 1fe9e0ec40250bfb
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: laptop, truck, table, television 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: c98da85995bf0909)

✅ Evaluation Results
id: c98da85995bf0909
question: Still treat your initial position as origin (0, 0) You move to (0, 1) and face west. What is the egocentric relation of truck? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 233021678b15a057)

✅ Evaluation Results
id: 233021678b15a057
question: Treat the red door as the new 'origin' (0, 0). You move to (2, 1) and face north. What is the egocentric relation of pillow? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, mid distance
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: default
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 5807e77e81650360)

✅ Evaluation Results
id: 5807e77e81650360
question: Treat the yellow door as the new 'origin' (0, 0). You move to (-2, -4) and face east. What is the egocentric relation of television? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, slightly far
task_type: Action2LocationEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: default
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3ba4cbab06925eb6)

✅ Evaluation Results
id: 3ba4cbab06925eb6
question: You move to a new location and face west. You observe: truck is at front-slight-right, slightly far, facing forward; shoppingcart is at front-left, slightly far, facing right; desklamp is at front-slight-left, mid distance, facing backward 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, 1]
final_pos: [6, 12]
final_ori: [-1, 0]
room_id: 1
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'truck', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing backward'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.368
raw_score: 0.368
score: 0.368
evaluation_mode: default
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: 079f24d0e9023ee5)

✅ Evaluation Results
id: 079f24d0e9023ee5
question: You move to a new location and face north. You observe: pillow is at front, mid distance; books is at front-right, mid distance Treat the red door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [2, 1]
final_pos: [9, 10]
final_ori: [0, 1]
room_id: 3
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: Location2ActionTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: default
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: db6d367fcaa0e174)

✅ Evaluation Results
id: db6d367fcaa0e174
question: You move to a new location and face east. You observe: television is at front-right, slightly far, facing left; suitcase is at front-left, mid distance, facing backward; chair is at front, mid distance, facing left Treat the yellow door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-2, -4]
final_pos: [3, 3]
final_ori: [1, 0]
room_id: 2
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'suitcase', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'chair', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing left'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: c9de6790a897c673)

✅ Evaluation Results
id: c9de6790a897c673
question: You return to your starting position and face north. From a Top-Down map, describe where truck is relative to desklamp. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north west, mid distance
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: 7360e44dad33a0d5)

✅ Evaluation Results
id: 7360e44dad33a0d5
question: You return to your starting position and face north. From a Top-Down map, describe where books is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 50faba75f48ab8cb)

✅ Evaluation Results
id: 50faba75f48ab8cb
question: You return to your starting position and face north. From a Top-Down map, describe where backpack is relative to table. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north east, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: fffaede931ebf4f3)

✅ Evaluation Results
id: fffaede931ebf4f3
question: Now you jump to laptop's direction, facing its direction. Describe where desklamp 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
Q1: PovEvaluationTask

Question 2 (ID: b8cd5a53479d1c3e)

✅ Evaluation Results
id: b8cd5a53479d1c3e
question: Now you jump to backpack's direction, facing its direction. Describe where books is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, slightly far
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: a67a1cef66054f66)

✅ Evaluation Results
id: a67a1cef66054f66
question: Now you jump to desklamp's direction, facing its direction. Describe where laptop 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
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 5902e70da1b23e88)

✅ Evaluation Results
id: 5902e70da1b23e88
question: Now you jump to an object's position, facing its direction. You observe that laptop is front-left, mid distance, facing right; red door is front-right, slightly far, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 11]
final_ori: [1, 0]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 7f5c758512898b6b)

✅ Evaluation Results
id: 7f5c758512898b6b
question: Now you jump to an object's position, facing its direction. You observe that red door is front-left, slightly far, on left wall; shoppingcart is front-right, slightly far, facing backward; desklamp is front-right, mid distance, facing left. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: laptop
final_pos: [5, 13]
final_ori: [0, -1]
final_observation: [{'name': 'red door', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'on left wall'}, {'name': 'shoppingcart', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing left'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: BackwardPovTextEvaluationTask
choices: []
kwargs:
(none)
name_match: True
view_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: BackwardPovTextEvaluationTask

Question 3 (ID: 7f4f9f9c8d6112b9)

✅ Evaluation Results
id: 7f4f9f9c8d6112b9
question: Now you jump to an object's position, facing its direction. You observe that bike is front-right, mid distance, facing forward; pillow is front, mid distance; books is front-right, slightly far. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: backpack
final_pos: [9, 9]
final_ori: [0, 1]
final_observation: [{'name': 'bike', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 286b5d2b65475d4f)

✅ Evaluation Results
id: 286b5d2b65475d4f
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. Rotate(-90) 4. Jump to the object at front-left, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of laptop 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: e413d4447d27b08e)

✅ Evaluation Results
id: e413d4447d27b08e
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-180) 2. Jump to the object at front-slight-right, slightly far. 3. Jump to the object at front-left, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of suitcase relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 45597bafd7e0cdbc)

✅ Evaluation Results
id: 45597bafd7e0cdbc
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-left, mid distance. 3. Rotate(90) 4. Jump to the object at front-right, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of desklamp relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 5ed57112b3bfdc2e)

✅ Evaluation Results
id: 5ed57112b3bfdc2e
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: laptop is at front-left, slightly far, facing backward; pillow is at front-right, slightly far; books is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 9]
final_ori: [0, 1]
room_id: [1, 3]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'pillow', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 9.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 1f898b79fbf64cc4)

✅ Evaluation Results
id: 1f898b79fbf64cc4
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: shoppingcart is at front-left, mid distance, facing forward; laptop is at front, slightly far, facing backward; desklamp is at front-left, slightly far, facing right 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, 7]
final_ori: [0, 1]
room_id: [2, 1]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'laptop', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 7.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 8a8f0522e5b332f6)

✅ Evaluation Results
id: 8a8f0522e5b332f6
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: backpack is at front, mid distance, facing backward; bike is at front-left, mid distance, facing backward; red door is at front-right, slightly far, on right 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: [9, 13]
final_ori: [0, -1]
room_id: 3
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'red door'], ['rotate', 180], ['jumpto', 'pillow'], ['rotate', 180]]
final_observation: [{'name': 'backpack', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'bike', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on right wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: False
ori_match: True
final_pos: [11.0, 13.0]
final_ori: [0, -1]
visible_match: False
score: 0
evaluation_mode: prompt_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2fec3ac651cf4a7c)

✅ Evaluation Results
id: 2fec3ac651cf4a7c
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: truck, desklamp, chair, laptop. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 2], [-3, 0], [1, -8], [-1, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.700
threshold: 0.900
score: 0.700
evaluation_mode: prompt_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 237ae2871d72362b)

✅ Evaluation Results
id: 237ae2871d72362b
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: backpack, chair, bike. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[3, -2], [1, -8], [5, 0]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.636
threshold: 0.900
score: 0.636
evaluation_mode: prompt_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 0ca18bd6fca57b5f)

✅ Evaluation Results
id: 0ca18bd6fca57b5f
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, backpack, bike, books. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, -6], [3, -2], [5, 0], [5, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.475
threshold: 0.900
score: 0.475
evaluation_mode: prompt_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: 4831d162b78edf8c)

✅ Evaluation Results
id: 4831d162b78edf8c
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, desklamp, laptop, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['laptop', 'desklamp', 'table', 'chair']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: b3bb94ba48268066)

✅ Evaluation Results
id: b3bb94ba48268066
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: backpack, bike, chair, pillow, shoppingcart. 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: ['pillow', 'bike', 'backpack', 'chair', 'shoppingcart']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: a73f3abfbc74d987)

✅ Evaluation Results
id: a73f3abfbc74d987
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: laptop, table, television, truck. 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: ['laptop', 'truck', 'table', 'television']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: c98da85995bf0909)

✅ Evaluation Results
id: c98da85995bf0909
question: Still treat your initial position as origin (0, 0) You move to (0, 1) and face west. What is the egocentric relation of truck? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 233021678b15a057)

✅ Evaluation Results
id: 233021678b15a057
question: Treat the red door as the new 'origin' (0, 0). You move to (2, 1) and face north. What is the egocentric relation of pillow? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, mid distance
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: prompt_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 5807e77e81650360)

✅ Evaluation Results
id: 5807e77e81650360
question: Treat the yellow door as the new 'origin' (0, 0). You move to (-2, -4) and face east. What is the egocentric relation of television? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3ba4cbab06925eb6)

✅ Evaluation Results
id: 3ba4cbab06925eb6
question: You move to a new location and face west. You observe: truck is at front-slight-right, slightly far, facing forward; shoppingcart is at front-left, slightly far, facing right; desklamp is at front-slight-left, mid distance, facing backward 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, 1]
final_pos: [6, 12]
final_ori: [-1, 0]
room_id: 1
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'truck', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing backward'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.059
raw_score: 0.059
score: 0.059
evaluation_mode: prompt_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: 079f24d0e9023ee5)

✅ Evaluation Results
id: 079f24d0e9023ee5
question: You move to a new location and face north. You observe: pillow is at front, mid distance; books is at front-right, mid distance Treat the red door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [2, 1]
final_pos: [9, 10]
final_ori: [0, 1]
room_id: 3
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: prompt_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: db6d367fcaa0e174)

✅ Evaluation Results
id: db6d367fcaa0e174
question: You move to a new location and face east. You observe: television is at front-right, slightly far, facing left; suitcase is at front-left, mid distance, facing backward; chair is at front, mid distance, facing left Treat the yellow door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-2, -4]
final_pos: [3, 3]
final_ori: [1, 0]
room_id: 2
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'suitcase', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'chair', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing left'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.800
raw_score: 0.800
score: 0.800
evaluation_mode: prompt_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask

📊 Evaluation (use_gt_cogmap)

📊 Task: DirectionEvaluationTask

Question 1 (ID: c9de6790a897c673)

✅ Evaluation Results
id: c9de6790a897c673
question: You return to your starting position and face north. From a Top-Down map, describe where truck is relative to desklamp. 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: 7360e44dad33a0d5)

✅ Evaluation Results
id: 7360e44dad33a0d5
question: You return to your starting position and face north. From a Top-Down map, describe where books is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 50faba75f48ab8cb)

✅ Evaluation Results
id: 50faba75f48ab8cb
question: You return to your starting position and face north. From a Top-Down map, describe where backpack is relative to table. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north east, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: fffaede931ebf4f3)

✅ Evaluation Results
id: fffaede931ebf4f3
question: Now you jump to laptop's direction, facing its direction. Describe where desklamp 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
Q1: PovEvaluationTask

Question 2 (ID: b8cd5a53479d1c3e)

✅ Evaluation Results
id: b8cd5a53479d1c3e
question: Now you jump to backpack's direction, facing its direction. Describe where books is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, slightly far
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: a67a1cef66054f66)

✅ Evaluation Results
id: a67a1cef66054f66
question: Now you jump to desklamp's direction, facing its direction. Describe where laptop 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
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 5902e70da1b23e88)

✅ Evaluation Results
id: 5902e70da1b23e88
question: Now you jump to an object's position, facing its direction. You observe that laptop is front-left, mid distance, facing right; red door is front-right, slightly far, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 11]
final_ori: [1, 0]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 7f5c758512898b6b)

✅ Evaluation Results
id: 7f5c758512898b6b
question: Now you jump to an object's position, facing its direction. You observe that red door is front-left, slightly far, on left wall; shoppingcart is front-right, slightly far, facing backward; desklamp is front-right, mid distance, facing left. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: laptop
final_pos: [5, 13]
final_ori: [0, -1]
final_observation: [{'name': 'red door', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'on left wall'}, {'name': 'shoppingcart', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing left'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 7f4f9f9c8d6112b9)

✅ Evaluation Results
id: 7f4f9f9c8d6112b9
question: Now you jump to an object's position, facing its direction. You observe that bike is front-right, mid distance, facing forward; pillow is front, mid distance; books is front-right, slightly far. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: backpack
final_pos: [9, 9]
final_ori: [0, 1]
final_observation: [{'name': 'bike', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 286b5d2b65475d4f)

✅ Evaluation Results
id: 286b5d2b65475d4f
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. Rotate(-90) 4. Jump to the object at front-left, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of laptop 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: e413d4447d27b08e)

✅ Evaluation Results
id: e413d4447d27b08e
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-180) 2. Jump to the object at front-slight-right, slightly far. 3. Jump to the object at front-left, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of suitcase relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 45597bafd7e0cdbc)

✅ Evaluation Results
id: 45597bafd7e0cdbc
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-left, mid distance. 3. Rotate(90) 4. Jump to the object at front-right, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of desklamp relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 5ed57112b3bfdc2e)

✅ Evaluation Results
id: 5ed57112b3bfdc2e
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: laptop is at front-left, slightly far, facing backward; pillow is at front-right, slightly far; books is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 9]
final_ori: [0, 1]
room_id: [1, 3]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'pillow', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [7.0, 9.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 1f898b79fbf64cc4)

✅ Evaluation Results
id: 1f898b79fbf64cc4
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: shoppingcart is at front-left, mid distance, facing forward; laptop is at front, slightly far, facing backward; desklamp is at front-left, slightly far, facing right 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, 7]
final_ori: [0, 1]
room_id: [2, 1]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'laptop', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 7.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 8a8f0522e5b332f6)

✅ Evaluation Results
id: 8a8f0522e5b332f6
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: backpack is at front, mid distance, facing backward; bike is at front-left, mid distance, facing backward; red door is at front-right, slightly far, on right 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: [9, 13]
final_ori: [0, -1]
room_id: 3
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'red door'], ['rotate', 180], ['jumpto', 'pillow'], ['rotate', 180]]
final_observation: [{'name': 'backpack', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'bike', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on right wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [9.0, 13.0]
final_ori: [0, -1]
visible_match: True
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2fec3ac651cf4a7c)

✅ Evaluation Results
id: 2fec3ac651cf4a7c
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: truck, desklamp, chair, laptop. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 2], [-3, 0], [1, -8], [-1, 2]]
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: 237ae2871d72362b)

✅ Evaluation Results
id: 237ae2871d72362b
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: backpack, chair, bike. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[3, -2], [1, -8], [5, 0]]
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: 0ca18bd6fca57b5f)

✅ Evaluation Results
id: 0ca18bd6fca57b5f
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, backpack, bike, books. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, -6], [3, -2], [5, 0], [5, 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: 4831d162b78edf8c)

✅ Evaluation Results
id: 4831d162b78edf8c
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, desklamp, laptop, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['laptop', 'desklamp', 'table', 'chair']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: b3bb94ba48268066)

✅ Evaluation Results
id: b3bb94ba48268066
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: backpack, bike, chair, pillow, shoppingcart. 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: ['pillow', 'bike', 'backpack', 'chair', 'shoppingcart']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: a73f3abfbc74d987)

✅ Evaluation Results
id: a73f3abfbc74d987
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: laptop, table, television, truck. 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: ['laptop', 'truck', 'table', 'television']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: c98da85995bf0909)

✅ Evaluation Results
id: c98da85995bf0909
question: Still treat your initial position as origin (0, 0) You move to (0, 1) and face west. What is the egocentric relation of truck? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 233021678b15a057)

✅ Evaluation Results
id: 233021678b15a057
question: Treat the red door as the new 'origin' (0, 0). You move to (2, 1) and face north. What is the egocentric relation of pillow? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, mid distance
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 5807e77e81650360)

✅ Evaluation Results
id: 5807e77e81650360
question: Treat the yellow door as the new 'origin' (0, 0). You move to (-2, -4) and face east. What is the egocentric relation of television? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3ba4cbab06925eb6)

✅ Evaluation Results
id: 3ba4cbab06925eb6
question: You move to a new location and face west. You observe: truck is at front-slight-right, slightly far, facing forward; shoppingcart is at front-left, slightly far, facing right; desklamp is at front-slight-left, mid distance, facing backward 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, 1]
final_pos: [6, 12]
final_ori: [-1, 0]
room_id: 1
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'truck', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing backward'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 079f24d0e9023ee5)

✅ Evaluation Results
id: 079f24d0e9023ee5
question: You move to a new location and face north. You observe: pillow is at front, mid distance; books is at front-right, mid distance Treat the red door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [2, 1]
final_pos: [9, 10]
final_ori: [0, 1]
room_id: 3
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 1
raw_score: 1
score: 1
evaluation_mode: use_gt_cogmap
Evaluation state
Q2: View2LocationTextEvaluationTask

Question 3 (ID: db6d367fcaa0e174)

✅ Evaluation Results
id: db6d367fcaa0e174
question: You move to a new location and face east. You observe: television is at front-right, slightly far, facing left; suitcase is at front-left, mid distance, facing backward; chair is at front, mid distance, facing left Treat the yellow door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-2, -4]
final_pos: [3, 3]
final_ori: [1, 0]
room_id: 2
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'suitcase', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'chair', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing left'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: c9de6790a897c673)

✅ Evaluation Results
id: c9de6790a897c673
question: You return to your starting position and face north. From a Top-Down map, describe where truck is relative to desklamp. 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: use_model_cogmap
Evaluation state
Q1: DirectionEvaluationTask

Question 2 (ID: 7360e44dad33a0d5)

✅ Evaluation Results
id: 7360e44dad33a0d5
question: You return to your starting position and face north. From a Top-Down map, describe where books is relative to chair. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north, far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q2: DirectionEvaluationTask

Question 3 (ID: 50faba75f48ab8cb)

✅ Evaluation Results
id: 50faba75f48ab8cb
question: You return to your starting position and face north. From a Top-Down map, describe where backpack is relative to table. Answer format: <cardinal direction>, <distance> Example: north-west, near
action: None
answer: north east, slightly far
task_type: DirectionEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q3: DirectionEvaluationTask

📊 Task: PovEvaluationTask

Question 1 (ID: fffaede931ebf4f3)

✅ Evaluation Results
id: fffaede931ebf4f3
question: Now you jump to laptop's direction, facing its direction. Describe where desklamp is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, mid distance
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q1: PovEvaluationTask

Question 2 (ID: b8cd5a53479d1c3e)

✅ Evaluation Results
id: b8cd5a53479d1c3e
question: Now you jump to backpack's direction, facing its direction. Describe where books is relative to you. Answer format: <ego direction>, <distance> Example: front-left, near
action: None
answer: front-right, slightly far
task_type: PovEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q2: PovEvaluationTask

Question 3 (ID: a67a1cef66054f66)

✅ Evaluation Results
id: a67a1cef66054f66
question: Now you jump to desklamp's direction, facing its direction. Describe where laptop 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: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q3: PovEvaluationTask

📊 Task: BackwardPovTextEvaluationTask

Question 1 (ID: 5902e70da1b23e88)

✅ Evaluation Results
id: 5902e70da1b23e88
question: Now you jump to an object's position, facing its direction. You observe that laptop is front-left, mid distance, facing right; red door is front-right, slightly far, on front wall. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: desklamp
final_pos: [3, 11]
final_ori: [1, 0]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing right'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on front wall'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 7f5c758512898b6b)

✅ Evaluation Results
id: 7f5c758512898b6b
question: Now you jump to an object's position, facing its direction. You observe that red door is front-left, slightly far, on left wall; shoppingcart is front-right, slightly far, facing backward; desklamp is front-right, mid distance, facing left. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: laptop
final_pos: [5, 13]
final_ori: [0, -1]
final_observation: [{'name': 'red door', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'on left wall'}, {'name': 'shoppingcart', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing left'}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 1
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 7f4f9f9c8d6112b9)

✅ Evaluation Results
id: 7f4f9f9c8d6112b9
question: Now you jump to an object's position, facing its direction. You observe that bike is front-right, mid distance, facing forward; pillow is front, mid distance; books is front-right, slightly far. Which object are you standing at? Answer format: <object_name> Example: lamp
action: None
answer:
answer: backpack
final_pos: [9, 9]
final_ori: [0, 1]
final_observation: [{'name': 'bike', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
object_positions:
laptop: [5.0, 13.0]
television: [7.0, 1.0]
backpack: [9.0, 9.0]
desklamp: [3.0, 11.0]
suitcase: [5.0, 5.0]
bike: [11.0, 11.0]
shoppingcart: [3.0, 9.0]
truck: [1.0, 13.0]
chair: [7.0, 3.0]
pillow: [9.0, 13.0]
table: [3.0, 5.0]
books: [11.0, 13.0]
red door: [7.0, 9.0]
yellow door: [5.0, 7.0]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
room_id: 3
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: 286b5d2b65475d4f)

✅ Evaluation Results
id: 286b5d2b65475d4f
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. Rotate(-90) 4. Jump to the object at front-left, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of laptop 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
Q1: Action2ViewEvaluationTask

Question 2 (ID: e413d4447d27b08e)

✅ Evaluation Results
id: e413d4447d27b08e
question: You return to your starting position and face north. You will execute the following action sequence: 1. Rotate(-180) 2. Jump to the object at front-slight-right, slightly far. 3. Jump to the object at front-left, slightly far. 4. Rotate(-180) After executing the actions, what is the ego relation of suitcase relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-left, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: Action2ViewEvaluationTask

Question 3 (ID: 45597bafd7e0cdbc)

✅ Evaluation Results
id: 45597bafd7e0cdbc
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-left, mid distance. 3. Rotate(90) 4. Jump to the object at front-right, slightly far. 5. Rotate(-180) After executing the actions, what is the ego relation of desklamp relative to you? Answer format: <ego direction>, <distance> Example: front, near
action: None
answer: front-right, mid distance
task_type: Action2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q3: Action2ViewEvaluationTask

📊 Task: View2ActionTextEvaluationTask

Question 1 (ID: 5ed57112b3bfdc2e)

✅ Evaluation Results
id: 5ed57112b3bfdc2e
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: laptop is at front-left, slightly far, facing backward; pillow is at front-right, slightly far; books is at front-right, slightly far What action sequence led to this final view? The action sequence must be valid and only contain move actions. Answer format: <sequence of move actions> Example: JumpTo(lamp), Rotate(90)
action: None
answer:
final_pos: [7, 9]
final_ori: [0, 1]
room_id: [1, 3]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'laptop', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'pillow', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': None}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
error: target_not_visible
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q1: View2ActionTextEvaluationTask

Question 2 (ID: 1f898b79fbf64cc4)

✅ Evaluation Results
id: 1f898b79fbf64cc4
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: shoppingcart is at front-left, mid distance, facing forward; laptop is at front, slightly far, facing backward; desklamp is at front-left, slightly far, facing right 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, 7]
final_ori: [0, 1]
room_id: [2, 1]
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'initial_pos'], ['rotate', 180]]
final_observation: [{'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing forward'}, {'name': 'laptop', 'direction': 'front', 'distance': 'slightly far', 'orientation': 'facing backward'}, {'name': 'desklamp', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
pos_match: True
ori_match: True
final_pos: [5.0, 7.0]
final_ori: [0, 1]
visible_match: True
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: View2ActionTextEvaluationTask

Question 3 (ID: 8a8f0522e5b332f6)

✅ Evaluation Results
id: 8a8f0522e5b332f6
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: backpack is at front, mid distance, facing backward; bike is at front-left, mid distance, facing backward; red door is at front-right, slightly far, on right 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: [9, 13]
final_ori: [0, -1]
room_id: 3
init_pos: [6, 11]
init_ori: [0, 1]
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
minimal_plan: [['rotate', 180], ['jumpto', 'red door'], ['rotate', 180], ['jumpto', 'pillow'], ['rotate', 180]]
final_observation: [{'name': 'backpack', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'bike', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'red door', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'on right wall'}]
task_type: View2ActionTextEvaluationTask
choices: []
kwargs:
(none)
error: target_not_visible
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q3: View2ActionTextEvaluationTask

📊 Task: AlloMappingEvaluationTask

Question 1 (ID: 2fec3ac651cf4a7c)

✅ Evaluation Results
id: 2fec3ac651cf4a7c
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: truck, desklamp, chair, laptop. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-5, 2], [-3, 0], [1, -8], [-1, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.790
threshold: 0.900
score: 0.790
evaluation_mode: use_model_cogmap
Evaluation state
Q1: AlloMappingEvaluationTask

Question 2 (ID: 237ae2871d72362b)

✅ Evaluation Results
id: 237ae2871d72362b
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: backpack, chair, bike. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[3, -2], [1, -8], [5, 0]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.670
threshold: 0.900
score: 0.670
evaluation_mode: use_model_cogmap
Evaluation state
Q2: AlloMappingEvaluationTask

Question 3 (ID: 0ca18bd6fca57b5f)

✅ Evaluation Results
id: 0ca18bd6fca57b5f
question: Treat your starting position as the origin (0, 0) while facing north. Report allocentric coordinates using (x right/east, y up/north). Objects: table, backpack, bike, books. Answer format: (x0, y0); (x1, y1); ... in the same order. Example: (1, 0); (-2, 3); (0, -1)
action: None
answer: [[-3, -6], [3, -2], [5, 0], [5, 2]]
task_type: AlloMappingEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.697
threshold: 0.900
score: 0.697
evaluation_mode: use_model_cogmap
Evaluation state
Q3: AlloMappingEvaluationTask

📊 Task: RotEvaluationTask

Question 1 (ID: 4831d162b78edf8c)

✅ Evaluation Results
id: 4831d162b78edf8c
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, desklamp, laptop, table. List them in the exact order they appear directly ahead while you rotate. If two objects share a bearing, place the nearer one first. Answer format: <object_name1>, <object_name2>, ... Example: mug, sofa, plant
action: None
answer: ['laptop', 'desklamp', 'table', 'chair']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q1: RotEvaluationTask

Question 2 (ID: b3bb94ba48268066)

✅ Evaluation Results
id: b3bb94ba48268066
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: backpack, bike, chair, pillow, shoppingcart. 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: ['pillow', 'bike', 'backpack', 'chair', 'shoppingcart']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: RotEvaluationTask

Question 3 (ID: a73f3abfbc74d987)

✅ Evaluation Results
id: a73f3abfbc74d987
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: laptop, table, television, truck. 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: ['laptop', 'truck', 'table', 'television']
task_type: RotEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q3: RotEvaluationTask

📊 Task: Location2ViewEvaluationTask

Question 1 (ID: c98da85995bf0909)

✅ Evaluation Results
id: c98da85995bf0909
question: Still treat your initial position as origin (0, 0) You move to (0, 1) and face west. What is the egocentric relation of truck? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-slight-right, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0.500
evaluation_mode: use_model_cogmap
Evaluation state
Q1: Location2ViewEvaluationTask

Question 2 (ID: 233021678b15a057)

✅ Evaluation Results
id: 233021678b15a057
question: Treat the red door as the new 'origin' (0, 0). You move to (2, 1) and face north. What is the egocentric relation of pillow? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front, mid distance
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 1
evaluation_mode: use_model_cogmap
Evaluation state
Q2: Location2ViewEvaluationTask

Question 3 (ID: 5807e77e81650360)

✅ Evaluation Results
id: 5807e77e81650360
question: Treat the yellow door as the new 'origin' (0, 0). You move to (-2, -4) and face east. What is the egocentric relation of television? Answer format: <direction>, <distance> Example: front, near
action: None
answer: front-right, slightly far
task_type: Location2ViewEvaluationTask
choices: []
kwargs:
(none)
score: 0
evaluation_mode: use_model_cogmap
Evaluation state
Q3: Location2ViewEvaluationTask

📊 Task: View2LocationTextEvaluationTask

Question 1 (ID: 3ba4cbab06925eb6)

✅ Evaluation Results
id: 3ba4cbab06925eb6
question: You move to a new location and face west. You observe: truck is at front-slight-right, slightly far, facing forward; shoppingcart is at front-left, slightly far, facing right; desklamp is at front-slight-left, mid distance, facing backward 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, 1]
final_pos: [6, 12]
final_ori: [-1, 0]
room_id: 1
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'truck', 'direction': 'front-slight-right', 'distance': 'slightly far', 'orientation': 'facing forward'}, {'name': 'shoppingcart', 'direction': 'front-left', 'distance': 'slightly far', 'orientation': 'facing right'}, {'name': 'desklamp', 'direction': 'front-slight-left', 'distance': 'mid distance', 'orientation': 'facing backward'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.243
raw_score: 0.243
score: 0.243
evaluation_mode: use_model_cogmap
Evaluation state
Q1: View2LocationTextEvaluationTask

Question 2 (ID: 079f24d0e9023ee5)

✅ Evaluation Results
id: 079f24d0e9023ee5
question: You move to a new location and face north. You observe: pillow is at front, mid distance; books is at front-right, mid distance Treat the red door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [2, 1]
final_pos: [9, 10]
final_ori: [0, 1]
room_id: 3
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'pillow', 'direction': 'front', 'distance': 'mid distance', 'orientation': None}, {'name': 'books', 'direction': 'front-right', 'distance': 'mid distance', 'orientation': None}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
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: db6d367fcaa0e174)

✅ Evaluation Results
id: db6d367fcaa0e174
question: You move to a new location and face east. You observe: television is at front-right, slightly far, facing left; suitcase is at front-left, mid distance, facing backward; chair is at front, mid distance, facing left Treat the yellow door as the new 'origin' (0, 0). What is your new 2D coordinate (x, y)? Answer format: (x, y) Example: (2, -1)
action: None
answer:
coord: [-2, -4]
final_pos: [3, 3]
final_ori: [1, 0]
room_id: 2
object_positions:
laptop: [5, 13]
television: [7, 1]
backpack: [9, 9]
desklamp: [3, 11]
suitcase: [5, 5]
bike: [11, 11]
shoppingcart: [3, 9]
truck: [1, 13]
chair: [7, 3]
pillow: [9, 13]
table: [3, 5]
books: [11, 13]
red door: [7, 9]
yellow door: [5, 7]
object_orientations:
laptop: [0, -1]
television: [0, 1]
backpack: [0, 1]
desklamp: [1, 0]
suitcase: [-1, 0]
bike: [0, 1]
shoppingcart: [0, 1]
truck: [-1, 0]
chair: [0, 1]
red door: [1, 0]
yellow door: [0, 1]
final_observation: [{'name': 'television', 'direction': 'front-right', 'distance': 'slightly far', 'orientation': 'facing left'}, {'name': 'suitcase', 'direction': 'front-left', 'distance': 'mid distance', 'orientation': 'facing backward'}, {'name': 'chair', 'direction': 'front', 'distance': 'mid distance', 'orientation': 'facing left'}]
gate_info:
red door:
room_ids: [1, 3]
ori_by_room:
1: [-1, 0]
3: [1, 0]
yellow door:
room_ids: [2, 1]
ori_by_room:
2: [0, -1]
1: [0, 1]
object_rooms:
laptop: 1
television: 2
backpack: 3
desklamp: 1
suitcase: 2
bike: 3
shoppingcart: 1
truck: 1
chair: 2
pillow: 3
table: 2
books: 3
red door: [1, 3]
yellow door: [2, 1]
task_type: View2LocationTextEvaluationTask
choices: []
kwargs:
(none)
similarity: 0.800
raw_score: 0.800
score: 0.800
evaluation_mode: use_model_cogmap
Evaluation state
Q3: View2LocationTextEvaluationTask