📋 Dashboard Overview
📋 Configuration Summaries
⚙️ text_active_think
📊 Samples: 10
🔍 Exploration
avg_node_coverage: 1
avg_edge_coverage: 0.512
avg_exploration_steps: 14.300
avg_action_cost: 13.300
avg_action_fail_ratio: 0.027
avg_valid_action_ratio: 1
avg_final_information_gain: 0.821
avg_false_belief_steps: 8.300
avg_false_belief_f1: 0.975
avg_false_belief_f1_position: 0.980
avg_false_belief_f1_facing: 0.967
avg_false_belief_action_cost: 7.100
avg_false_belief_action_cost_after_seen: 0.111
avg_action_counts:
move: 5.300
rotate: 9.600
return: 0
observe: 13.300
term: 1
forced_term: 0
query: 0
✅ Evaluation
avg_accuracy: 0.801
task_metrics:
DirectionEvaluationTask:
accuracy: 0.750
total_count: 30
task_score: 22.500
PovEvaluationTask:
accuracy: 0.750
total_count: 30
task_score: 22.500
BackwardPovTextEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
View2ActionTextEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
AlloMappingEvaluationTask:
accuracy: 0.847
total_count: 30
task_score: 25.402
RotEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
Location2ViewEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
View2LocationTextEvaluationTask:
accuracy: 0.792
total_count: 30
task_score: 23.765
Action2ViewEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
✅ Evaluation (prompt_cogmap)
avg_accuracy: 0.752
task_metrics:
DirectionEvaluationTask:
accuracy: 0.633
total_count: 30
task_score: 19
PovEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
BackwardPovTextEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
Action2ViewEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
View2ActionTextEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
AlloMappingEvaluationTask:
accuracy: 0.800
total_count: 30
task_score: 24.006
RotEvaluationTask:
accuracy: 0.867
total_count: 30
task_score: 26
Location2ViewEvaluationTask:
accuracy: 0.633
total_count: 30
task_score: 19
View2LocationTextEvaluationTask:
accuracy: 0.736
total_count: 30
task_score: 22.071
✅ Evaluation (use_gt_cogmap)
avg_accuracy: 0.957
task_metrics:
RotEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
Location2ViewEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
View2LocationTextEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29.016
DirectionEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
PovEvaluationTask:
accuracy: 0.950
total_count: 30
task_score: 28.500
BackwardPovTextEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
Action2ViewEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
View2ActionTextEvaluationTask:
accuracy: 0.833
total_count: 30
task_score: 25
AlloMappingEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
✅ Evaluation (use_model_cogmap)
avg_accuracy: 0.755
task_metrics:
DirectionEvaluationTask:
accuracy: 0.683
total_count: 30
task_score: 20.500
PovEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
BackwardPovTextEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
Action2ViewEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
View2ActionTextEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
AlloMappingEvaluationTask:
accuracy: 0.788
total_count: 30
task_score: 23.630
RotEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
Location2ViewEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
View2LocationTextEvaluationTask:
accuracy: 0.723
total_count: 30
task_score: 21.681
🧠 Cognitive Map
exploration:
consistency:
facing_stability_avg: 0.926
local_vs_global_avg:
dir: 0.806
pos: 0.860
facing: 0.947
overall: 0.871
facing_update_avg: 0.926
position_update_avg: 0.661
position_stability_avg: 0.661
correctness:
last_global_vs_gt_full:
dir: 0.777
pos: 0.742
facing: 1
overall: 0.840
error:
local_vs_gt_local_avg:
dir: 0.892
pos: 0.890
facing: 1
overall: 0.927
newly_observed_vs_gt_local_avg:
dir: 0.897
pos: 0.883
facing: 1
overall: 0.926
agent_vs_gt_agent_avg:
dir: 0.833
pos: 0.870
facing: 1
overall: 0.901
global_vs_gt_global_avg:
dir: 0.798
pos: 0.799
facing: 0.937
overall: 0.845
n_samples: Global: 10, Local: 10, Newly: 10
evaluation:
correctness:
(none)
🌫️ Fog Probe
precision_avg: 0.777
f1_avg: 0.749
recall_avg: 0.755
n_samples: 10
🧭 False Belief CogMap
inertia: 0.037
changed:
dir: None
pos: 0.748
facing: 0.850
overall: None
retention:
dir: None
pos: 0.351
facing: 0.150
overall: None
unchanged:
dir: 0.695
pos: 0.714
facing: 0.824
overall: 0.744
unchanged_retention:
dir: None
pos: 0.758
facing: 0.943
overall: None
unchanged_retention_minus_retention:
pos: 0.764
facing: 0.819
unchanged_exploration:
dir: 0.796
pos: 0.762
facing: 1
overall: 0.853
📈 Correlation
cogmap_acc_correlations:
avg_accuracy:
pearson_r: 0.426
p_value: 0.220
significant: False
n_samples: 10
Location2ViewEvaluationTask:
pearson_r: 0.049
p_value: 0.894
significant: False
n_samples: 10
View2LocationTextEvaluationTask:
pearson_r: -0.146
p_value: 0.688
significant: False
n_samples: 10
Action2ViewEvaluationTask:
pearson_r: 0.802
p_value: 0.005
significant: True
n_samples: 10
RotDualEvaluationTask:
pearson_r: -0.174
p_value: 0.631
significant: False
n_samples: 10
AlloMappingEvaluationTask:
pearson_r: 0.232
p_value: 0.519
significant: False
n_samples: 10
PovEvaluationTask:
pearson_r: 0.534
p_value: 0.112
significant: False
n_samples: 10
DirectionEvaluationTask:
pearson_r: -0.265
p_value: 0.460
significant: False
n_samples: 10
RotEvaluationTask:
pearson_r: -0.174
p_value: 0.631
significant: False
n_samples: 10
BackwardPovTextEvaluationTask:
pearson_r: -0.380
p_value: 0.279
significant: False
n_samples: 10
View2ActionTextEvaluationTask:
pearson_r: 0.120
p_value: 0.741
significant: False
n_samples: 10
cogmap_infogain_correlation:
pearson_r: 0.591
p_value: 0.072
significant: False
n_samples: 10
n_samples: 10
Performance Charts
Information Gain per Turn
Cognitive Map (Update)
Cognitive Map (Full)
Cognitive Map (Self-Tracking)
Fog Probe F1
Fog Probe Precision
Fog Probe Recall
FB CogMap (Unchanged)
Position Update
Facing Update
Position Stability
Facing Stability
CogMap vs Accuracy
CogMap vs InfoGain
⚙️ text_passive_think_strategist
📊 Samples: 10
🔍 Exploration
avg_node_coverage: None
avg_edge_coverage: None
avg_exploration_steps: None
avg_action_cost: None
avg_action_fail_ratio: None
avg_valid_action_ratio: None
avg_final_information_gain: None
avg_false_belief_steps: None
avg_false_belief_f1: None
avg_false_belief_f1_position: None
avg_false_belief_f1_facing: None
avg_false_belief_action_cost: None
avg_false_belief_action_cost_after_seen: None
✅ Evaluation
avg_accuracy: 0.849
task_metrics:
DirectionEvaluationTask:
accuracy: 0.817
total_count: 30
task_score: 24.500
PovEvaluationTask:
accuracy: 0.950
total_count: 30
task_score: 28.500
BackwardPovTextEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
View2ActionTextEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
AlloMappingEvaluationTask:
accuracy: 0.873
total_count: 30
task_score: 26.187
RotEvaluationTask:
accuracy: 0.867
total_count: 30
task_score: 26
Location2ViewEvaluationTask:
accuracy: 0.817
total_count: 30
task_score: 24.500
View2LocationTextEvaluationTask:
accuracy: 0.865
total_count: 30
task_score: 25.940
Action2ViewEvaluationTask:
accuracy: 0.850
total_count: 30
task_score: 25.500
🧠 Cognitive Map
exploration:
correctness:
global_full:
(none)
n_samples: 0
⚙️ vision_active_think
📊 Samples: 10
🔍 Exploration
avg_node_coverage: 1
avg_edge_coverage: 0.534
avg_exploration_steps: 15
avg_action_cost: 14
avg_action_fail_ratio: 0.046
avg_valid_action_ratio: 1
avg_final_information_gain: 0.851
avg_false_belief_steps: 11.500
avg_false_belief_f1: 0.600
avg_false_belief_f1_position: 0.813
avg_false_belief_f1_facing: 0.217
avg_false_belief_action_cost: 10.200
avg_false_belief_action_cost_after_seen: 3.200
avg_action_counts:
move: 5.300
rotate: 9.800
return: 0
observe: 14
term: 1
forced_term: 0
query: 0
✅ Evaluation
avg_accuracy: 0.608
task_metrics:
DirectionEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
PovEvaluationTask:
accuracy: 0.400
total_count: 30
task_score: 12
BackwardPovTextEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
BackwardPovVisionEvaluationTask:
accuracy: 0.633
total_count: 30
task_score: 19
View2ActionTextEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
View2ActionVisionEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
AlloMappingEvaluationTask:
accuracy: 0.650
total_count: 30
task_score: 19.489
RotEvaluationTask:
accuracy: 0.833
total_count: 30
task_score: 25
Location2ViewEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
View2LocationTextEvaluationTask:
accuracy: 0.654
total_count: 30
task_score: 19.629
View2LocationVisionEvaluationTask:
accuracy: 0.553
total_count: 30
task_score: 16.584
Action2ViewEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
✅ Evaluation (prompt_cogmap)
avg_accuracy: 0.556
task_metrics:
DirectionEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
PovEvaluationTask:
accuracy: 0.300
total_count: 30
task_score: 9
BackwardPovTextEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
BackwardPovVisionEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
Action2ViewEvaluationTask:
accuracy: 0.483
total_count: 30
task_score: 14.500
View2ActionTextEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
View2ActionVisionEvaluationTask:
accuracy: 0.733
total_count: 30
task_score: 22
AlloMappingEvaluationTask:
accuracy: 0.568
total_count: 30
task_score: 17.054
RotEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
Location2ViewEvaluationTask:
accuracy: 0.450
total_count: 30
task_score: 13.500
View2LocationTextEvaluationTask:
accuracy: 0.666
total_count: 30
task_score: 19.986
View2LocationVisionEvaluationTask:
accuracy: 0.545
total_count: 30
task_score: 16.359
✅ Evaluation (use_gt_cogmap)
avg_accuracy: 0.963
task_metrics:
DirectionEvaluationTask:
accuracy: 0.917
total_count: 30
task_score: 27.500
PovEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
BackwardPovTextEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
BackwardPovVisionEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
Action2ViewEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
View2ActionTextEvaluationTask:
accuracy: 0.900
total_count: 30
task_score: 27
View2ActionVisionEvaluationTask:
accuracy: 0.800
total_count: 30
task_score: 24
AlloMappingEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
RotEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
Location2ViewEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
View2LocationTextEvaluationTask:
accuracy: 0.988
total_count: 30
task_score: 29.639
View2LocationVisionEvaluationTask:
accuracy: 0.761
total_count: 30
task_score: 22.831
✅ Evaluation (use_model_cogmap)
avg_accuracy: 0.554
task_metrics:
DirectionEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
PovEvaluationTask:
accuracy: 0.300
total_count: 30
task_score: 9
BackwardPovTextEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
BackwardPovVisionEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
Action2ViewEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
View2ActionTextEvaluationTask:
accuracy: 0.500
total_count: 30
task_score: 15
View2ActionVisionEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
AlloMappingEvaluationTask:
accuracy: 0.629
total_count: 30
task_score: 18.861
RotEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
Location2ViewEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
View2LocationTextEvaluationTask:
accuracy: 0.622
total_count: 30
task_score: 18.657
View2LocationVisionEvaluationTask:
accuracy: 0.557
total_count: 30
task_score: 16.697
🧠 Cognitive Map
exploration:
consistency:
facing_stability_avg: 0.597
local_vs_global_avg:
dir: 0.677
pos: 0.689
facing: 0.538
overall: 0.635
facing_update_avg: 0.597
position_update_avg: 0.630
position_stability_avg: 0.630
correctness:
last_global_vs_gt_full:
dir: 0.670
pos: 0.639
facing: 0.299
overall: 0.536
error:
local_vs_gt_local_avg:
dir: 0.733
pos: 0.681
facing: 0.437
overall: 0.617
newly_observed_vs_gt_local_avg:
dir: 0.696
pos: 0.671
facing: 0.328
overall: 0.565
agent_vs_gt_agent_avg:
dir: 0.675
pos: 0.728
facing: 0.991
overall: 0.798
global_vs_gt_global_avg:
dir: 0.663
pos: 0.657
facing: 0.401
overall: 0.574
n_samples: Global: 10, Local: 10, Newly: 10
evaluation:
correctness:
(none)
🌫️ Fog Probe
precision_avg: 0.732
f1_avg: 0.684
recall_avg: 0.707
n_samples: 10
🧭 False Belief CogMap
inertia: 0.135
changed:
dir: None
pos: 0.657
facing: 0.400
overall: None
retention:
dir: None
pos: 0.349
facing: 0.450
overall: None
unchanged:
dir: 0.588
pos: 0.607
facing: 0.326
overall: 0.507
unchanged_retention:
dir: None
pos: 0.727
facing: 0.669
overall: None
unchanged_retention_minus_retention:
pos: 0.745
facing: 0.017
unchanged_exploration:
dir: 0.656
pos: 0.650
facing: 0.186
overall: 0.497
📈 Correlation
cogmap_acc_correlations:
avg_accuracy:
pearson_r: 0.748
p_value: 0.013
significant: True
n_samples: 10
BackwardPovVisionEvaluationTask:
pearson_r: 0.771
p_value: 0.009
significant: True
n_samples: 10
View2LocationVisionEvaluationTask:
pearson_r: 0.339
p_value: 0.338
significant: False
n_samples: 10
Location2ViewEvaluationTask:
pearson_r: 0.236
p_value: 0.511
significant: False
n_samples: 10
View2LocationTextEvaluationTask:
pearson_r: 0.636
p_value: 0.048
significant: True
n_samples: 10
Action2ViewEvaluationTask:
pearson_r: 0.550
p_value: 0.100
significant: False
n_samples: 10
RotDualEvaluationTask:
pearson_r: 0.492
p_value: 0.149
significant: False
n_samples: 10
AlloMappingEvaluationTask:
pearson_r: 0.597
p_value: 0.069
significant: False
n_samples: 10
PovEvaluationTask:
pearson_r: 0.383
p_value: 0.274
significant: False
n_samples: 10
DirectionEvaluationTask:
pearson_r: -0.339
p_value: 0.338
significant: False
n_samples: 10
RotEvaluationTask:
pearson_r: -0.051
p_value: 0.890
significant: False
n_samples: 10
BackwardPovTextEvaluationTask:
pearson_r: 0.728
p_value: 0.017
significant: True
n_samples: 10
View2ActionTextEvaluationTask:
pearson_r: 0.446
p_value: 0.196
significant: False
n_samples: 10
View2ActionVisionEvaluationTask:
pearson_r: 0.239
p_value: 0.507
significant: False
n_samples: 10
cogmap_infogain_correlation:
pearson_r: 0.498
p_value: 0.143
significant: False
n_samples: 10
n_samples: 10
Performance Charts
Information Gain per Turn
Cognitive Map (Update)
Cognitive Map (Full)
Cognitive Map (Self-Tracking)
Fog Probe F1
Fog Probe Precision
Fog Probe Recall
FB CogMap (Unchanged)
Position Update
Facing Update
Position Stability
Facing Stability
CogMap vs Accuracy
CogMap vs InfoGain
⚙️ vision_passive_think_scout
📊 Samples: 10
🔍 Exploration
avg_node_coverage: None
avg_edge_coverage: None
avg_exploration_steps: None
avg_action_cost: None
avg_action_fail_ratio: None
avg_valid_action_ratio: None
avg_final_information_gain: None
avg_false_belief_steps: None
avg_false_belief_f1: None
avg_false_belief_f1_position: None
avg_false_belief_f1_facing: None
avg_false_belief_action_cost: None
avg_false_belief_action_cost_after_seen: None
✅ Evaluation
avg_accuracy: 0.617
task_metrics:
Location2ViewEvaluationTask:
accuracy: 0.683
total_count: 30
task_score: 20.500
View2LocationTextEvaluationTask:
accuracy: 0.716
total_count: 30
task_score: 21.494
View2LocationVisionEvaluationTask:
accuracy: 0.572
total_count: 30
task_score: 17.170
DirectionEvaluationTask:
accuracy: 0.583
total_count: 30
task_score: 17.500
PovEvaluationTask:
accuracy: 0.417
total_count: 30
task_score: 12.500
BackwardPovTextEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
BackwardPovVisionEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
View2ActionTextEvaluationTask:
accuracy: 0.500
total_count: 30
task_score: 15
View2ActionVisionEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
AlloMappingEvaluationTask:
accuracy: 0.685
total_count: 30
task_score: 20.559
RotEvaluationTask:
accuracy: 0.833
total_count: 30
task_score: 25
Action2ViewEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
🧠 Cognitive Map
exploration:
correctness:
global_full:
(none)
n_samples: 0