Upload model/evaluasi_hasil.json with huggingface_hub
Browse files- model/evaluasi_hasil.json +158 -0
model/evaluasi_hasil.json
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"e1": {
|
| 3 |
+
"skor": 0.7,
|
| 4 |
+
"detail": [
|
| 5 |
+
{
|
| 6 |
+
"valid": "Peneliti itu mempublikasikan temuan barunya ke jurnal internasional.",
|
| 7 |
+
"invalid": "Peneliti itu publikasi temuan baru ke jurnal internasional.",
|
| 8 |
+
"margin": -0.044843,
|
| 9 |
+
"lulus": false
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"valid": "Hakim memutuskan bahwa terdakwa terbukti bersalah.",
|
| 13 |
+
"invalid": "Hakim putuskan terdakwa terbukti salah bersalah.",
|
| 14 |
+
"margin": 0.071239,
|
| 15 |
+
"lulus": true
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"valid": "Semua siswa mengerjakan tugas mereka dengan tekun.",
|
| 19 |
+
"invalid": "Semua siswa kerjakan tugas mereka dengan tekun tekun.",
|
| 20 |
+
"margin": 0.02677,
|
| 21 |
+
"lulus": true
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"valid": "Pemerintah menetapkan kebijakan baru untuk sektor pertanian.",
|
| 25 |
+
"invalid": "Pemerintah tetap kebijakan baru sektor pertanian.",
|
| 26 |
+
"margin": 0.069682,
|
| 27 |
+
"lulus": true
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"valid": "Dokumen penting itu ditandatangani oleh direktur utama.",
|
| 31 |
+
"invalid": "Dokumen penting itu tandatangan direktur utama.",
|
| 32 |
+
"margin": -0.022988,
|
| 33 |
+
"lulus": false
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"valid": "Warga desa membangun jembatan baru di atas sungai.",
|
| 37 |
+
"invalid": "Warga desa bangun jembatan baru atas sungai.",
|
| 38 |
+
"margin": 0.039954,
|
| 39 |
+
"lulus": true
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"valid": "Tim peneliti menganalisis data dari berbagai sumber terpercaya.",
|
| 43 |
+
"invalid": "Tim peneliti analisis data berbagai sumber percaya.",
|
| 44 |
+
"margin": 0.031953,
|
| 45 |
+
"lulus": true
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"valid": "Menteri Pendidikan meluncurkan program pelatihan bagi guru.",
|
| 49 |
+
"invalid": "Menteri Pendidikan luncur program latih bagi guru.",
|
| 50 |
+
"margin": 0.070614,
|
| 51 |
+
"lulus": true
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"valid": "Pengusaha muda itu mengembangkan bisnis teknologi pertanian.",
|
| 55 |
+
"invalid": "Pengusaha muda itu kembang bisnis teknologi pertanian.",
|
| 56 |
+
"margin": -0.117268,
|
| 57 |
+
"lulus": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"valid": "Anak-anak bermain di taman pada sore hari yang cerah.",
|
| 61 |
+
"invalid": "Anak-anak main taman sore hari cerah.",
|
| 62 |
+
"margin": 0.06512,
|
| 63 |
+
"lulus": true
|
| 64 |
+
}
|
| 65 |
+
]
|
| 66 |
+
},
|
| 67 |
+
"e2": {
|
| 68 |
+
"skor": 1.0,
|
| 69 |
+
"detail": [
|
| 70 |
+
{
|
| 71 |
+
"root": "sinkronisasi",
|
| 72 |
+
"bentuk": "menyinkronisasikan",
|
| 73 |
+
"lulus": true
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"root": "partisipasi",
|
| 77 |
+
"bentuk": "memartisipasikan",
|
| 78 |
+
"lulus": true
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"root": "transformasi",
|
| 82 |
+
"bentuk": "menransformasikan",
|
| 83 |
+
"lulus": true
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"root": "akselerasi",
|
| 87 |
+
"bentuk": "mengakselerasikan",
|
| 88 |
+
"lulus": true
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"root": "digitalisasi",
|
| 92 |
+
"bentuk": "didigitalisasikan",
|
| 93 |
+
"lulus": true
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"root": "optimalisasi",
|
| 97 |
+
"bentuk": "mengoptimalisasikan",
|
| 98 |
+
"lulus": true
|
| 99 |
+
}
|
| 100 |
+
]
|
| 101 |
+
},
|
| 102 |
+
"e3": {
|
| 103 |
+
"skor": 1.0,
|
| 104 |
+
"detail": [
|
| 105 |
+
{
|
| 106 |
+
"deskripsi": "Proposisi baru: teknolog mengembangkan algoritma",
|
| 107 |
+
"kalimat": "Teknolog mengembangkan algoritma di laboratorium",
|
| 108 |
+
"lulus": true
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"deskripsi": "Proposisi pasif baru: sistem dioperasikan operator",
|
| 112 |
+
"kalimat": "Sistem dioperasikan oleh operator",
|
| 113 |
+
"lulus": true
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"deskripsi": "Proposisi atribusi: kebijakan adalah reformasi",
|
| 117 |
+
"kalimat": "Kebijakan menjadi reformasi",
|
| 118 |
+
"lulus": true
|
| 119 |
+
}
|
| 120 |
+
]
|
| 121 |
+
},
|
| 122 |
+
"e4": {
|
| 123 |
+
"skor": 1.0,
|
| 124 |
+
"detail": [
|
| 125 |
+
{
|
| 126 |
+
"deskripsi": "Vonis hakim → status terpidana (chain 1 langkah)",
|
| 127 |
+
"lulus": true
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"deskripsi": "Aksi membeli → kepemilikan (chain 1 langkah)",
|
| 131 |
+
"lulus": true
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"deskripsi": "Keputusan pejabat → dampak kebijakan (chain 2 langkah)",
|
| 135 |
+
"lulus": true
|
| 136 |
+
}
|
| 137 |
+
]
|
| 138 |
+
},
|
| 139 |
+
"e5": {
|
| 140 |
+
"skor": 1.0,
|
| 141 |
+
"entitas": 10,
|
| 142 |
+
"inferensi": 0,
|
| 143 |
+
"detail": [
|
| 144 |
+
{
|
| 145 |
+
"test": "resolusi referensi",
|
| 146 |
+
"lulus": true
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"test": "akumulasi inferensi",
|
| 150 |
+
"lulus": true
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"test": "query ke konteks",
|
| 154 |
+
"lulus": true
|
| 155 |
+
}
|
| 156 |
+
]
|
| 157 |
+
}
|
| 158 |
+
}
|