bertose-affinose-training-code / data /vocab /confidence_analysis.json
supanthadey1's picture
Add BERTose and AFFINose training code release
1d6f391 verified
Raw
History Blame Contribute Delete
8.7 kB
{
"optimal_thresholds": {
"0.85": {
"threshold": 0.5,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100
},
"0.9": {
"threshold": 0.5,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100
},
"0.95": {
"threshold": 0.5,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100
}
},
"summary_statistics": {
"n_samples": 100,
"mean_confidence": 0.9788418018817902,
"median_confidence": 0.9999498724937439,
"overall_accuracy": 0.96
},
"threshold_statistics": [
{
"threshold": 0.5,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.51,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.52,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.53,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.54,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.55,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.56,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.5700000000000001,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.5800000000000001,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.5900000000000001,
"accuracy": 0.96,
"acceptance_rate": 1.0,
"n_accepted": 100,
"n_correct": 96
},
{
"threshold": 0.6000000000000001,
"accuracy": 0.9595959595959596,
"acceptance_rate": 0.99,
"n_accepted": 99,
"n_correct": 95
},
{
"threshold": 0.6100000000000001,
"accuracy": 0.9595959595959596,
"acceptance_rate": 0.99,
"n_accepted": 99,
"n_correct": 95
},
{
"threshold": 0.6200000000000001,
"accuracy": 0.9595959595959596,
"acceptance_rate": 0.99,
"n_accepted": 99,
"n_correct": 95
},
{
"threshold": 0.6300000000000001,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.6400000000000001,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.6500000000000001,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.6600000000000001,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.6700000000000002,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.6800000000000002,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.6900000000000002,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.7000000000000002,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.7100000000000002,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.7200000000000002,
"accuracy": 0.9591836734693877,
"acceptance_rate": 0.98,
"n_accepted": 98,
"n_correct": 94
},
{
"threshold": 0.7300000000000002,
"accuracy": 0.9690721649484536,
"acceptance_rate": 0.97,
"n_accepted": 97,
"n_correct": 94
},
{
"threshold": 0.7400000000000002,
"accuracy": 0.9690721649484536,
"acceptance_rate": 0.97,
"n_accepted": 97,
"n_correct": 94
},
{
"threshold": 0.7500000000000002,
"accuracy": 0.9690721649484536,
"acceptance_rate": 0.97,
"n_accepted": 97,
"n_correct": 94
},
{
"threshold": 0.7600000000000002,
"accuracy": 0.9690721649484536,
"acceptance_rate": 0.97,
"n_accepted": 97,
"n_correct": 94
},
{
"threshold": 0.7700000000000002,
"accuracy": 0.9791666666666666,
"acceptance_rate": 0.96,
"n_accepted": 96,
"n_correct": 94
},
{
"threshold": 0.7800000000000002,
"accuracy": 0.9791666666666666,
"acceptance_rate": 0.96,
"n_accepted": 96,
"n_correct": 94
},
{
"threshold": 0.7900000000000003,
"accuracy": 0.9791666666666666,
"acceptance_rate": 0.96,
"n_accepted": 96,
"n_correct": 94
},
{
"threshold": 0.8000000000000003,
"accuracy": 0.9789473684210527,
"acceptance_rate": 0.95,
"n_accepted": 95,
"n_correct": 93
},
{
"threshold": 0.8100000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8200000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8300000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8400000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8500000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8600000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8700000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8800000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.8900000000000003,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.9000000000000004,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.9100000000000004,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.9200000000000004,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.9300000000000004,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.9400000000000004,
"accuracy": 0.9787234042553191,
"acceptance_rate": 0.94,
"n_accepted": 94,
"n_correct": 92
},
{
"threshold": 0.9500000000000004,
"accuracy": 0.989010989010989,
"acceptance_rate": 0.91,
"n_accepted": 91,
"n_correct": 90
},
{
"threshold": 0.9600000000000004,
"accuracy": 0.9887640449438202,
"acceptance_rate": 0.89,
"n_accepted": 89,
"n_correct": 88
},
{
"threshold": 0.9700000000000004,
"accuracy": 0.9886363636363636,
"acceptance_rate": 0.88,
"n_accepted": 88,
"n_correct": 87
},
{
"threshold": 0.9800000000000004,
"accuracy": 0.9885057471264368,
"acceptance_rate": 0.87,
"n_accepted": 87,
"n_correct": 86
},
{
"threshold": 0.9900000000000004,
"accuracy": 1.0,
"acceptance_rate": 0.84,
"n_accepted": 84,
"n_correct": 84
}
]
}