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

===== key: Type Match =====
total consistent rate: 416, total: 1200, ratio: 34.67
error: invalid rate: 24, total: 1200, ratio: 2.0
       - deviate: 7, invalid ratio: 29.17, total ratio: 0.58
error: inconsistent rate: 760, total: 1200, ratio: 63.33
       - deviate: 154, invalid ratio: 20.26, total ratio: 12.83
total_deviate rate: 186, total: 1200, ratio: 15.5
average confidence: 79.35
average confidence of correct: 90.78
average confidence of hallucination: 92.2
===== key: Type Shift =====
total consistent rate: 454, total: 1200, ratio: 37.83
error: invalid rate: 25, total: 1200, ratio: 2.08
       - deviate: 3, invalid ratio: 12.0, total ratio: 0.25
error: inconsistent rate: 721, total: 1200, ratio: 60.08
       - deviate: 28, invalid ratio: 3.88, total ratio: 2.33
total_deviate rate: 34, total: 1200, ratio: 2.83
average confidence: 77.82
average confidence of correct: 90.48
average confidence of hallucination: 86.46

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

===== key: par1_hop1 =====
total consistent rate: 179, total: 600, ratio: 29.83
error: invalid rate: 18, total: 600, ratio: 3.0
       - deviate: 3, invalid ratio: 16.67, total ratio: 0.5
error: inconsistent rate: 403, total: 600, ratio: 67.17
       - deviate: 34, invalid ratio: 8.44, total ratio: 5.67
total_deviate rate: 51, total: 600, ratio: 8.5
average confidence: 78.11
average confidence of correct: 91.46
average confidence of hallucination: 94.87
===== key: par2_hop1 =====
total consistent rate: 206, total: 600, ratio: 34.33
error: invalid rate: 14, total: 600, ratio: 2.33
       - deviate: 3, invalid ratio: 21.43, total ratio: 0.5
error: inconsistent rate: 380, total: 600, ratio: 63.33
       - deviate: 21, invalid ratio: 5.53, total ratio: 3.5
total_deviate rate: 28, total: 600, ratio: 4.67
average confidence: 76.24
average confidence of correct: 89.24
average confidence of hallucination: 77.4
===== key: triangle_hop1 =====
total consistent rate: 258, total: 600, ratio: 43.0
error: invalid rate: 12, total: 600, ratio: 2.0
       - deviate: 4, invalid ratio: 33.33, total ratio: 0.67
error: inconsistent rate: 330, total: 600, ratio: 55.0
       - deviate: 82, invalid ratio: 24.85, total ratio: 13.67
total_deviate rate: 95, total: 600, ratio: 15.83
average confidence: 81.32
average confidence of correct: 91.37
average confidence of hallucination: 92.91
===== key: child_hop1 =====
total consistent rate: 227, total: 600, ratio: 37.83
error: invalid rate: 5, total: 600, ratio: 0.83
       - deviate: 0, invalid ratio: 0.0, total ratio: 0.0
error: inconsistent rate: 368, total: 600, ratio: 61.33
       - deviate: 45, invalid ratio: 12.23, total ratio: 7.5
total_deviate rate: 46, total: 600, ratio: 7.67
average confidence: 78.67
average confidence of correct: 90.41
average confidence of hallucination: 93.85

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

===== key: Object =====
total consistent rate: 235, total: 800, ratio: 29.38
error: invalid rate: 30, total: 800, ratio: 3.75
       - deviate: 10, invalid ratio: 33.33, total ratio: 1.25
error: inconsistent rate: 535, total: 800, ratio: 66.88
       - deviate: 129, invalid ratio: 24.11, total ratio: 16.12
total_deviate rate: 161, total: 800, ratio: 20.12
average confidence: 78.81
average confidence of correct: 90.65
average confidence of hallucination: 92.34
===== key: Subject =====
total consistent rate: 358, total: 800, ratio: 44.75
error: invalid rate: 11, total: 800, ratio: 1.38
       - deviate: 0, invalid ratio: 0.0, total ratio: 0.0
error: inconsistent rate: 431, total: 800, ratio: 53.87
       - deviate: 20, invalid ratio: 4.64, total ratio: 2.5
total_deviate rate: 21, total: 800, ratio: 2.62
average confidence: 79.33
average confidence of correct: 91.15
average confidence of hallucination: 90.62
===== key: Unrelated =====
total consistent rate: 277, total: 800, ratio: 34.62
error: invalid rate: 8, total: 800, ratio: 1.0
       - deviate: 0, invalid ratio: 0.0, total ratio: 0.0
error: inconsistent rate: 515, total: 800, ratio: 64.38
       - deviate: 33, invalid ratio: 6.41, total ratio: 4.12
total_deviate rate: 38, total: 800, ratio: 4.75
average confidence: 77.63
average confidence of correct: 90.06
average confidence of hallucination: 87.08
