📋 Dashboard Overview
📋 Configuration Summaries
⚙️ text_active_think
📊 Samples: 10
🔍 Exploration
avg_node_coverage: 0.957
avg_edge_coverage: 0.461
avg_exploration_steps: 12.300
avg_action_cost: 11.300
avg_action_fail_ratio: 0.012
avg_valid_action_ratio: 1
avg_final_information_gain: 0.794
avg_false_belief_steps: 8.300
avg_false_belief_f1: 0.950
avg_false_belief_f1_position: 0.980
avg_false_belief_f1_facing: 0.917
avg_false_belief_action_cost: 7.300
avg_false_belief_action_cost_after_seen: 0.875
avg_action_counts:
move: 2.700
rotate: 7.700
return: 0
observe: 11.300
term: 0.900
forced_term: 0.100
query: 0
✅ Evaluation
avg_accuracy: 0.671
task_metrics:
DirectionEvaluationTask:
accuracy: 0.717
total_count: 30
task_score: 21.500
PovEvaluationTask:
accuracy: 0.717
total_count: 30
task_score: 21.500
BackwardPovTextEvaluationTask:
accuracy: 0.800
total_count: 30
task_score: 24
View2ActionTextEvaluationTask:
accuracy: 0.267
total_count: 30
task_score: 8
AlloMappingEvaluationTask:
accuracy: 0.780
total_count: 30
task_score: 23.409
RotEvaluationTask:
accuracy: 0.800
total_count: 30
task_score: 24
Location2ViewEvaluationTask:
accuracy: 0.567
total_count: 30
task_score: 17
View2LocationTextEvaluationTask:
accuracy: 0.741
total_count: 30
task_score: 22.231
Action2ViewEvaluationTask:
accuracy: 0.650
total_count: 30
task_score: 19.500
✅ Evaluation (prompt_cogmap)
avg_accuracy: 0.683
task_metrics:
DirectionEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
PovEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
BackwardPovTextEvaluationTask:
accuracy: 0.867
total_count: 30
task_score: 26
Action2ViewEvaluationTask:
accuracy: 0.650
total_count: 30
task_score: 19.500
View2ActionTextEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
AlloMappingEvaluationTask:
accuracy: 0.701
total_count: 30
task_score: 21.035
RotEvaluationTask:
accuracy: 0.867
total_count: 30
task_score: 26
Location2ViewEvaluationTask:
accuracy: 0.517
total_count: 30
task_score: 15.500
View2LocationTextEvaluationTask:
accuracy: 0.641
total_count: 30
task_score: 19.240
✅ Evaluation (use_gt_cogmap)
avg_accuracy: 0.954
task_metrics:
DirectionEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
PovEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
BackwardPovTextEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
Action2ViewEvaluationTask:
accuracy: 0.983
total_count: 30
task_score: 29.500
View2ActionTextEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
AlloMappingEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
RotEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
Location2ViewEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
View2LocationTextEvaluationTask:
accuracy: 0.940
total_count: 30
task_score: 28.197
✅ Evaluation (use_model_cogmap)
avg_accuracy: 0.676
task_metrics:
DirectionEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
PovEvaluationTask:
accuracy: 0.583
total_count: 30
task_score: 17.500
BackwardPovTextEvaluationTask:
accuracy: 0.833
total_count: 30
task_score: 25
Action2ViewEvaluationTask:
accuracy: 0.617
total_count: 30
task_score: 18.500
View2ActionTextEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
AlloMappingEvaluationTask:
accuracy: 0.739
total_count: 30
task_score: 22.180
RotEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
Location2ViewEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
View2LocationTextEvaluationTask:
accuracy: 0.681
total_count: 30
task_score: 20.424
🧠 Cognitive Map
exploration:
error:
global_vs_gt_global_avg:
dir: 0.822
facing: 0.953
overall: 0.865
pos: 0.820
newly_observed_vs_gt_local_avg:
dir: 0.780
facing: 1
overall: 0.877
pos: 0.850
agent_vs_gt_agent_avg:
dir: 0.796
facing: 0.990
overall: 0.891
pos: 0.887
local_vs_gt_local_avg:
dir: 0.790
facing: 1
overall: 0.880
pos: 0.850
consistency:
position_update_avg: 0.689
facing_update_avg: 0.956
position_stability_avg: 0.689
facing_stability_avg: 0.956
local_vs_global_avg:
dir: 0.735
facing: 0.933
overall: 0.841
pos: 0.856
correctness:
last_global_vs_gt_full:
dir: 0.757
facing: 0.957
overall: 0.825
pos: 0.763
n_samples: Global: 10, Local: 10, Newly: 10
evaluation:
correctness:
(none)
🌫️ Fog Probe
recall_avg: 0.785
f1_avg: 0.605
precision_avg: 0.523
n_samples: 10
🧭 False Belief CogMap
inertia: 0.181
changed:
dir: None
facing: 0.650
overall: None
pos: 0.668
retention:
dir: None
facing: 0
overall: None
pos: 0.376
unchanged:
dir: 0.609
facing: 0.779
overall: 0.677
pos: 0.643
unchanged_retention:
dir: None
facing: 0.865
overall: None
pos: 0.761
unchanged_retention_minus_retention:
facing: 1
pos: 0.685
unchanged_exploration:
dir: 0.789
facing: 1
overall: 0.862
pos: 0.795
📈 Correlation
cogmap_acc_correlations:
avg_accuracy:
pearson_r: 0.810
p_value: 0.004
significant: True
n_samples: 10
DirectionEvaluationTask:
pearson_r: 0.380
p_value: 0.279
significant: False
n_samples: 10
View2ActionTextEvaluationTask:
pearson_r: 0.165
p_value: 0.650
significant: False
n_samples: 10
RotDualEvaluationTask:
pearson_r: NaN
p_value: NaN
significant: False
n_samples: 10
View2LocationTextEvaluationTask:
pearson_r: 0.132
p_value: 0.717
significant: False
n_samples: 10
RotEvaluationTask:
pearson_r: 0.403
p_value: 0.248
significant: False
n_samples: 10
AlloMappingEvaluationTask:
pearson_r: 0.720
p_value: 0.019
significant: True
n_samples: 10
Location2ViewEvaluationTask:
pearson_r: 0.409
p_value: 0.240
significant: False
n_samples: 10
PovEvaluationTask:
pearson_r: 0.631
p_value: 0.050
significant: False
n_samples: 10
Action2ViewEvaluationTask:
pearson_r: 0.715
p_value: 0.020
significant: True
n_samples: 10
BackwardPovTextEvaluationTask:
pearson_r: 0.399
p_value: 0.253
significant: False
n_samples: 10
cogmap_infogain_correlation:
pearson_r: 0.403
p_value: 0.249
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: 0.910
task_metrics:
DirectionEvaluationTask:
accuracy: 0.800
total_count: 30
task_score: 24
PovEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
BackwardPovTextEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
View2ActionTextEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
AlloMappingEvaluationTask:
accuracy: 0.993
total_count: 30
task_score: 29.785
RotEvaluationTask:
accuracy: 0.967
total_count: 30
task_score: 29
Location2ViewEvaluationTask:
accuracy: 0.900
total_count: 30
task_score: 27
View2LocationTextEvaluationTask:
accuracy: 0.951
total_count: 30
task_score: 28.543
Action2ViewEvaluationTask:
accuracy: 0.917
total_count: 30
task_score: 27.500
🧠 Cognitive Map
exploration:
correctness:
global_full:
(none)
n_samples: 0
⚙️ vision_active_think
📊 Samples: 10
🔍 Exploration
avg_node_coverage: 0.993
avg_edge_coverage: 0.537
avg_exploration_steps: 19.300
avg_action_cost: 17.900
avg_action_fail_ratio: 0.051
avg_valid_action_ratio: 1
avg_final_information_gain: 0.866
avg_false_belief_steps: 13.300
avg_false_belief_f1: 0.550
avg_false_belief_f1_position: 0.780
avg_false_belief_f1_facing: 0.117
avg_false_belief_action_cost: 12.300
avg_false_belief_action_cost_after_seen: 4
avg_action_counts:
move: 4.900
rotate: 12.500
return: 0
observe: 17.900
term: 0.900
forced_term: 0.100
query: 0
✅ Evaluation
avg_accuracy: 0.478
task_metrics:
DirectionEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
PovEvaluationTask:
accuracy: 0.367
total_count: 30
task_score: 11
BackwardPovTextEvaluationTask:
accuracy: 0.600
total_count: 30
task_score: 18
BackwardPovVisionEvaluationTask:
accuracy: 0.233
total_count: 30
task_score: 7
View2ActionTextEvaluationTask:
accuracy: 0.367
total_count: 30
task_score: 11
View2ActionVisionEvaluationTask:
accuracy: 0.400
total_count: 30
task_score: 12
AlloMappingEvaluationTask:
accuracy: 0.481
total_count: 30
task_score: 14.425
RotEvaluationTask:
accuracy: 0.700
total_count: 30
task_score: 21
Location2ViewEvaluationTask:
accuracy: 0.367
total_count: 30
task_score: 11
View2LocationTextEvaluationTask:
accuracy: 0.504
total_count: 30
task_score: 15.115
View2LocationVisionEvaluationTask:
accuracy: 0.414
total_count: 30
task_score: 12.431
Action2ViewEvaluationTask:
accuracy: 0.383
total_count: 30
task_score: 11.500
✅ Evaluation (prompt_cogmap)
avg_accuracy: 0.391
task_metrics:
DirectionEvaluationTask:
accuracy: 0.350
total_count: 30
task_score: 10.500
PovEvaluationTask:
accuracy: 0.283
total_count: 30
task_score: 8.500
BackwardPovTextEvaluationTask:
accuracy: 0.533
total_count: 30
task_score: 16
BackwardPovVisionEvaluationTask:
accuracy: 0.400
total_count: 30
task_score: 12
Action2ViewEvaluationTask:
accuracy: 0.350
total_count: 30
task_score: 10.500
View2ActionTextEvaluationTask:
accuracy: 0.367
total_count: 30
task_score: 11
View2ActionVisionEvaluationTask:
accuracy: 0.400
total_count: 30
task_score: 12
AlloMappingEvaluationTask:
accuracy: 0.438
total_count: 30
task_score: 13.145
RotEvaluationTask:
accuracy: 0.400
total_count: 30
task_score: 12
Location2ViewEvaluationTask:
accuracy: 0.350
total_count: 30
task_score: 10.500
View2LocationTextEvaluationTask:
accuracy: 0.444
total_count: 30
task_score: 13.315
View2LocationVisionEvaluationTask:
accuracy: 0.398
total_count: 30
task_score: 11.949
✅ Evaluation (use_gt_cogmap)
avg_accuracy: 0.940
task_metrics:
DirectionEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
PovEvaluationTask:
accuracy: 1
total_count: 30
task_score: 30
BackwardPovTextEvaluationTask:
accuracy: 0.933
total_count: 30
task_score: 28
BackwardPovVisionEvaluationTask:
accuracy: 0.767
total_count: 30
task_score: 23
Action2ViewEvaluationTask:
accuracy: 0.950
total_count: 30
task_score: 28.500
View2ActionTextEvaluationTask:
accuracy: 0.600
total_count: 30
task_score: 18
View2ActionVisionEvaluationTask:
accuracy: 0.633
total_count: 30
task_score: 19
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: 0.978
total_count: 30
task_score: 29.342
View2LocationVisionEvaluationTask:
accuracy: 0.779
total_count: 30
task_score: 23.377
✅ Evaluation (use_model_cogmap)
avg_accuracy: 0.396
task_metrics:
DirectionEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
PovEvaluationTask:
accuracy: 0.167
total_count: 30
task_score: 5
BackwardPovTextEvaluationTask:
accuracy: 0.433
total_count: 30
task_score: 13
BackwardPovVisionEvaluationTask:
accuracy: 0.500
total_count: 30
task_score: 15
Action2ViewEvaluationTask:
accuracy: 0.450
total_count: 30
task_score: 13.500
View2ActionTextEvaluationTask:
accuracy: 0.367
total_count: 30
task_score: 11
View2ActionVisionEvaluationTask:
accuracy: 0.500
total_count: 30
task_score: 15
AlloMappingEvaluationTask:
accuracy: 0.397
total_count: 30
task_score: 11.916
RotEvaluationTask:
accuracy: 0.500
total_count: 30
task_score: 15
Location2ViewEvaluationTask:
accuracy: 0.283
total_count: 30
task_score: 8.500
View2LocationTextEvaluationTask:
accuracy: 0.498
total_count: 30
task_score: 14.945
View2LocationVisionEvaluationTask:
accuracy: 0.391
total_count: 30
task_score: 11.734
🧠 Cognitive Map
exploration:
error:
global_vs_gt_global_avg:
dir: 0.497
facing: 0.297
overall: 0.447
pos: 0.546
newly_observed_vs_gt_local_avg:
dir: 0.642
facing: 0.383
overall: 0.594
pos: 0.756
agent_vs_gt_agent_avg:
dir: 0.568
facing: 0.979
overall: 0.745
pos: 0.687
local_vs_gt_local_avg:
dir: 0.643
facing: 0.314
overall: 0.566
pos: 0.740
consistency:
position_update_avg: 0.572
facing_update_avg: 0.603
position_stability_avg: 0.572
facing_stability_avg: 0.603
local_vs_global_avg:
dir: 0.446
facing: 0.528
overall: 0.529
pos: 0.615
correctness:
last_global_vs_gt_full:
dir: 0.420
facing: 0.206
overall: 0.373
pos: 0.493
n_samples: Global: 10, Local: 10, Newly: 10
evaluation:
correctness:
(none)
🌫️ Fog Probe
recall_avg: 0.609
f1_avg: 0.552
precision_avg: 0.551
n_samples: 10
🧭 False Belief CogMap
inertia: 0.402
changed:
dir: None
facing: 0.300
overall: None
pos: 0.461
retention:
dir: None
facing: 0.550
overall: None
pos: 0.415
unchanged:
dir: 0.373
facing: 0.245
overall: 0.359
pos: 0.458
unchanged_retention:
dir: None
facing: 0.740
overall: None
pos: 0.594
unchanged_retention_minus_retention:
facing: 0.105
pos: 0.442
unchanged_exploration:
dir: 0.471
facing: 0.113
overall: 0.371
pos: 0.529
📈 Correlation
cogmap_acc_correlations:
avg_accuracy:
pearson_r: -0.229
p_value: 0.524
significant: False
n_samples: 10
DirectionEvaluationTask:
pearson_r: -0.107
p_value: 0.769
significant: False
n_samples: 10
View2ActionTextEvaluationTask:
pearson_r: -0.428
p_value: 0.217
significant: False
n_samples: 10
RotDualEvaluationTask:
pearson_r: 0.228
p_value: 0.526
significant: False
n_samples: 10
View2LocationTextEvaluationTask:
pearson_r: -0.207
p_value: 0.567
significant: False
n_samples: 10
RotEvaluationTask:
pearson_r: 0.553
p_value: 0.098
significant: False
n_samples: 10
AlloMappingEvaluationTask:
pearson_r: 0.269
p_value: 0.452
significant: False
n_samples: 10
View2LocationVisionEvaluationTask:
pearson_r: -0.094
p_value: 0.797
significant: False
n_samples: 10
Location2ViewEvaluationTask:
pearson_r: 0.190
p_value: 0.598
significant: False
n_samples: 10
View2ActionVisionEvaluationTask:
pearson_r: -0.497
p_value: 0.144
significant: False
n_samples: 10
PovEvaluationTask:
pearson_r: -0.117
p_value: 0.747
significant: False
n_samples: 10
Action2ViewEvaluationTask:
pearson_r: -0.665
p_value: 0.036
significant: True
n_samples: 10
BackwardPovVisionEvaluationTask:
pearson_r: -0.311
p_value: 0.382
significant: False
n_samples: 10
BackwardPovTextEvaluationTask:
pearson_r: -0.186
p_value: 0.607
significant: False
n_samples: 10
cogmap_infogain_correlation:
pearson_r: 0.157
p_value: 0.665
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: 0.572
task_metrics:
DirectionEvaluationTask:
accuracy: 0.517
total_count: 30
task_score: 15.500
PovEvaluationTask:
accuracy: 0.350
total_count: 30
task_score: 10.500
BackwardPovTextEvaluationTask:
accuracy: 0.633
total_count: 30
task_score: 19
BackwardPovVisionEvaluationTask:
accuracy: 0.367
total_count: 30
task_score: 11
View2ActionTextEvaluationTask:
accuracy: 0.400
total_count: 30
task_score: 12
View2ActionVisionEvaluationTask:
accuracy: 0.433
total_count: 30
task_score: 13
AlloMappingEvaluationTask:
accuracy: 0.658
total_count: 30
task_score: 19.745
RotEvaluationTask:
accuracy: 0.867
total_count: 30
task_score: 26
Location2ViewEvaluationTask:
accuracy: 0.467
total_count: 30
task_score: 14
View2LocationTextEvaluationTask:
accuracy: 0.592
total_count: 30
task_score: 17.759
View2LocationVisionEvaluationTask:
accuracy: 0.594
total_count: 30
task_score: 17.821
Action2ViewEvaluationTask:
accuracy: 0.667
total_count: 30
task_score: 20
🧠 Cognitive Map
exploration:
correctness:
global_full:
(none)
n_samples: 0