
~~~~~~~~~~ dict: degree analysis ~~~~~~~~~~

===== key: Type Match =====
total consistent rate: 384, total: 1200, ratio: 32.0
error: invalid rate: 50, total: 1200, ratio: 4.17
       - deviate: 13, invalid ratio: 26.0, total ratio: 1.08
error: inconsistent rate: 766, total: 1200, ratio: 63.83
       - deviate: 148, invalid ratio: 19.32, total ratio: 12.33
total_deviate rate: 187, total: 1200, ratio: 15.58
average confidence: 79.57
average confidence of correct: 88.93
average confidence of hallucination: 92.05
===== key: Type Shift =====
total consistent rate: 397, total: 1200, ratio: 33.08
error: invalid rate: 50, total: 1200, ratio: 4.17
       - deviate: 5, invalid ratio: 10.0, total ratio: 0.42
error: inconsistent rate: 753, total: 1200, ratio: 62.75
       - deviate: 59, invalid ratio: 7.84, total ratio: 4.92
total_deviate rate: 64, total: 1200, ratio: 5.33
average confidence: 77.65
average confidence of correct: 89.01
average confidence of hallucination: 84.48

~~~~~~~~~~ dict: position analysis ~~~~~~~~~~

===== key: par1_hop1 =====
total consistent rate: 181, total: 600, ratio: 30.17
error: invalid rate: 38, total: 600, ratio: 6.33
       - deviate: 9, invalid ratio: 23.68, total ratio: 1.5
error: inconsistent rate: 381, total: 600, ratio: 63.5
       - deviate: 55, invalid ratio: 14.44, total ratio: 9.17
total_deviate rate: 70, total: 600, ratio: 11.67
average confidence: 78.61
average confidence of correct: 88.75
average confidence of hallucination: 92.54
===== key: par2_hop1 =====
total consistent rate: 189, total: 600, ratio: 31.5
error: invalid rate: 19, total: 600, ratio: 3.17
       - deviate: 1, invalid ratio: 5.26, total ratio: 0.17
error: inconsistent rate: 392, total: 600, ratio: 65.33
       - deviate: 38, invalid ratio: 9.69, total ratio: 6.33
total_deviate rate: 50, total: 600, ratio: 8.33
average confidence: 77.56
average confidence of correct: 89.2
average confidence of hallucination: 85.13
===== key: par2_hop2 =====
total consistent rate: 195, total: 600, ratio: 32.5
error: invalid rate: 26, total: 600, ratio: 4.33
       - deviate: 8, invalid ratio: 30.77, total ratio: 1.33
error: inconsistent rate: 379, total: 600, ratio: 63.17
       - deviate: 27, invalid ratio: 7.12, total ratio: 4.5
total_deviate rate: 42, total: 600, ratio: 7.0
average confidence: 78.52
average confidence of correct: 88.63
average confidence of hallucination: 87.73
===== key: triangle_hop1 =====
total consistent rate: 216, total: 600, ratio: 36.0
error: invalid rate: 17, total: 600, ratio: 2.83
       - deviate: 0, invalid ratio: 0.0, total ratio: 0.0
error: inconsistent rate: 367, total: 600, ratio: 61.17
       - deviate: 87, invalid ratio: 23.71, total ratio: 14.5
total_deviate rate: 89, total: 600, ratio: 14.83
average confidence: 79.76
average confidence of correct: 89.29
average confidence of hallucination: 92.31

~~~~~~~~~~ dict: method analysis ~~~~~~~~~~

===== key: Object =====
total consistent rate: 193, total: 800, ratio: 24.12
error: invalid rate: 47, total: 800, ratio: 5.88
       - deviate: 15, invalid ratio: 31.91, total ratio: 1.88
error: inconsistent rate: 560, total: 800, ratio: 70.0
       - deviate: 156, invalid ratio: 27.86, total ratio: 19.5
total_deviate rate: 190, total: 800, ratio: 23.75
average confidence: 79.01
average confidence of correct: 88.22
average confidence of hallucination: 90.69
===== key: Subject =====
total consistent rate: 338, total: 800, ratio: 42.25
error: invalid rate: 26, total: 800, ratio: 3.25
       - deviate: 2, invalid ratio: 7.69, total ratio: 0.25
error: inconsistent rate: 436, total: 800, ratio: 54.5
       - deviate: 21, invalid ratio: 4.82, total ratio: 2.62
total_deviate rate: 28, total: 800, ratio: 3.5
average confidence: 79.42
average confidence of correct: 89.87
average confidence of hallucination: 89.37
===== key: Unrelated =====
total consistent rate: 250, total: 800, ratio: 31.25
error: invalid rate: 27, total: 800, ratio: 3.38
       - deviate: 1, invalid ratio: 3.7, total ratio: 0.12
error: inconsistent rate: 523, total: 800, ratio: 65.38
       - deviate: 30, invalid ratio: 5.74, total ratio: 3.75
total_deviate rate: 33, total: 800, ratio: 4.12
average confidence: 77.41
average confidence of correct: 88.69
average confidence of hallucination: 87.64
