Skip to content

Commit c9e0cbf

Browse files
e06084e06084
committed
x
1 parent 2fc2668 commit c9e0cbf

3 files changed

Lines changed: 520 additions & 0 deletions

File tree

‎results/preprocessed_html_evaluation_report.csv‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
extractor,dataset,total_samples,success_rate,overall,code_edit,formula_edit,table_TEDS,table_edit,text_edit
2+
llm-webkit,preprocessed_html_test,2,1.0,0.5029,0.5,1.0,0.5,0.5,0.0143

‎results/preprocessed_html_evaluation_results.json‎

Lines changed: 223 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,223 @@
1+
{
2+
"metadata": {
3+
"dataset_name": "preprocessed_html_test",
4+
"extractor_name": "llm-webkit",
5+
"timestamp": "2025-08-06T16:58:51.991543",
6+
"total_samples": 2
7+
},
8+
"overall_metrics": {
9+
"code_edit": 0.5,
10+
"formula_edit": 1.0,
11+
"table_edit": 0.5,
12+
"table_TEDS": 0.5,
13+
"text_edit": 0.01428571428571429,
14+
"overall": 0.5028571428571429
15+
},
16+
"sample_results": [
17+
{
18+
"sample_id": "preprocessed_sample_1",
19+
"extraction_success": true,
20+
"extraction_time": 0.9301280975341797,
21+
"metrics": {
22+
"code_edit": {
23+
"score": 0.0,
24+
"success": true,
25+
"details": {
26+
"distance": 208,
27+
"predicted_length": 0,
28+
"groundtruth_length": 208,
29+
"normalized": true,
30+
"predicted_code_length": 0,
31+
"groundtruth_code_length": 208,
32+
"content_type": "code"
33+
}
34+
},
35+
"formula_edit": {
36+
"score": 1.0,
37+
"success": true,
38+
"details": {
39+
"distance": 0,
40+
"predicted_length": 0,
41+
"groundtruth_length": 0,
42+
"normalized": true,
43+
"predicted_formula_length": 0,
44+
"groundtruth_formula_length": 0,
45+
"content_type": "formula"
46+
}
47+
},
48+
"table_edit": {
49+
"score": 1.0,
50+
"success": true,
51+
"details": {
52+
"distance": 0,
53+
"predicted_length": 0,
54+
"groundtruth_length": 0,
55+
"normalized": true,
56+
"predicted_table_length": 0,
57+
"groundtruth_table_length": 0,
58+
"content_type": "table"
59+
}
60+
},
61+
"table_TEDS": {
62+
"score": 1.0,
63+
"success": true,
64+
"details": {
65+
"edit_distance": 0.0,
66+
"predicted_nodes": 3,
67+
"groundtruth_nodes": 3,
68+
"max_nodes": 3,
69+
"structure_only": false,
70+
"algorithm": "TEDS",
71+
"content_type": "table"
72+
}
73+
},
74+
"text_edit": {
75+
"score": 0.02857142857142858,
76+
"success": true,
77+
"details": {
78+
"distance": 68,
79+
"predicted_length": 29,
80+
"groundtruth_length": 70,
81+
"normalized": true,
82+
"predicted_text_length": 29,
83+
"groundtruth_text_length": 70,
84+
"content_type": "text"
85+
}
86+
},
87+
"overall": {
88+
"score": 0.6057142857142856,
89+
"success": true,
90+
"details": {
91+
"source": "average_of_all_metrics",
92+
"description": "Overall score as average of all successful metrics",
93+
"successful_metrics": 5,
94+
"failed_metrics": 0,
95+
"individual_scores": {
96+
"code_edit": 0.0,
97+
"formula_edit": 1.0,
98+
"table_edit": 1.0,
99+
"table_TEDS": 1.0,
100+
"text_edit": 0.02857142857142858
101+
}
102+
}
103+
}
104+
},
105+
"sample_metadata": {
106+
"url": null,
107+
"domain": null,
108+
"language": null,
109+
"content_type": null,
110+
"difficulty": null
111+
}
112+
},
113+
{
114+
"sample_id": "preprocessed_sample_2",
115+
"extraction_success": true,
116+
"extraction_time": 0.0038819313049316406,
117+
"metrics": {
118+
"code_edit": {
119+
"score": 1.0,
120+
"success": true,
121+
"details": {
122+
"distance": 0,
123+
"predicted_length": 0,
124+
"groundtruth_length": 0,
125+
"normalized": true,
126+
"predicted_code_length": 0,
127+
"groundtruth_code_length": 0,
128+
"content_type": "code"
129+
}
130+
},
131+
"formula_edit": {
132+
"score": 1.0,
133+
"success": true,
134+
"details": {
135+
"distance": 0,
136+
"predicted_length": 0,
137+
"groundtruth_length": 0,
138+
"normalized": true,
139+
"predicted_formula_length": 0,
140+
"groundtruth_formula_length": 0,
141+
"content_type": "formula"
142+
}
143+
},
144+
"table_edit": {
145+
"score": 0.0,
146+
"success": true,
147+
"details": {
148+
"distance": 102,
149+
"predicted_length": 0,
150+
"groundtruth_length": 102,
151+
"normalized": true,
152+
"predicted_table_length": 0,
153+
"groundtruth_table_length": 102,
154+
"content_type": "table"
155+
}
156+
},
157+
"table_TEDS": {
158+
"score": 0.0,
159+
"success": true,
160+
"details": {
161+
"edit_distance": 13.0,
162+
"predicted_nodes": 3,
163+
"groundtruth_nodes": 13,
164+
"max_nodes": 13,
165+
"structure_only": false,
166+
"algorithm": "TEDS",
167+
"content_type": "table"
168+
}
169+
},
170+
"text_edit": {
171+
"score": 0.0,
172+
"success": true,
173+
"details": {
174+
"distance": 35,
175+
"predicted_length": 13,
176+
"groundtruth_length": 35,
177+
"normalized": true,
178+
"predicted_text_length": 13,
179+
"groundtruth_text_length": 35,
180+
"content_type": "text"
181+
}
182+
},
183+
"overall": {
184+
"score": 0.4,
185+
"success": true,
186+
"details": {
187+
"source": "average_of_all_metrics",
188+
"description": "Overall score as average of all successful metrics",
189+
"successful_metrics": 5,
190+
"failed_metrics": 0,
191+
"individual_scores": {
192+
"code_edit": 1.0,
193+
"formula_edit": 1.0,
194+
"table_edit": 0.0,
195+
"table_TEDS": 0.0,
196+
"text_edit": 0.0
197+
}
198+
}
199+
}
200+
},
201+
"sample_metadata": {
202+
"url": null,
203+
"domain": null,
204+
"language": null,
205+
"content_type": null,
206+
"difficulty": null
207+
}
208+
}
209+
],
210+
"category_metrics": null,
211+
"error_analysis": {
212+
"total_samples": 2,
213+
"failed_count": 0,
214+
"success_rate": 1.0,
215+
"common_errors": {},
216+
"sample_errors": []
217+
},
218+
"extractor_config": {
219+
"use_preprocessed_html": true,
220+
"preprocessed_html_field": "llm_webkit_html"
221+
},
222+
"metric_config": {}
223+
}

0 commit comments

Comments
 (0)