4461 lines
74 KiB
JSON
4461 lines
74 KiB
JSON
{
|
|
"table_of_contents": [
|
|
{
|
|
"title": "FAKULTAT F \u00a8 UR INFORMATIK \u00a8",
|
|
"heading_level": null,
|
|
"page_id": 0,
|
|
"polygon": [
|
|
[
|
|
148.21875,
|
|
132.00421142578125
|
|
],
|
|
[
|
|
445.2012939453125,
|
|
132.00421142578125
|
|
],
|
|
[
|
|
445.2012939453125,
|
|
157.466796875
|
|
],
|
|
[
|
|
148.21875,
|
|
157.466796875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Generating Swedish-style Crossword Puzzle\nMasks using Evolutionary Algorithms",
|
|
"heading_level": null,
|
|
"page_id": 0,
|
|
"polygon": [
|
|
[
|
|
87.0002212524414,
|
|
319.4296875
|
|
],
|
|
[
|
|
507.49249267578125,
|
|
319.4296875
|
|
],
|
|
[
|
|
507.49249267578125,
|
|
362.2344055175781
|
|
],
|
|
[
|
|
87.0002212524414,
|
|
362.2344055175781
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "FAKULTAT F \u00a8 UR INFORMATIK \u00a8",
|
|
"heading_level": null,
|
|
"page_id": 2,
|
|
"polygon": [
|
|
[
|
|
157.18359375,
|
|
132.00421142578125
|
|
],
|
|
[
|
|
453.72125244140625,
|
|
132.00421142578125
|
|
],
|
|
[
|
|
453.72125244140625,
|
|
157.466796875
|
|
],
|
|
[
|
|
157.18359375,
|
|
157.466796875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "DER TECHNISCHEN UNIVERSITAT M \u00a8 UNCHEN \u00a8",
|
|
"heading_level": null,
|
|
"page_id": 2,
|
|
"polygon": [
|
|
[
|
|
170.76016235351562,
|
|
168.22265625
|
|
],
|
|
[
|
|
440.9751281738281,
|
|
168.22265625
|
|
],
|
|
[
|
|
440.9751281738281,
|
|
183.11669921875
|
|
],
|
|
[
|
|
170.76016235351562,
|
|
183.11669921875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Bachelorarbeit in Informatik",
|
|
"heading_level": null,
|
|
"page_id": 2,
|
|
"polygon": [
|
|
[
|
|
215.15625,
|
|
232.8046875
|
|
],
|
|
[
|
|
395.69622802734375,
|
|
232.8046875
|
|
],
|
|
[
|
|
395.69622802734375,
|
|
249.5438232421875
|
|
],
|
|
[
|
|
215.15625,
|
|
249.5438232421875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Generating Swedish-style Crossword Puzzle Masks\nusing Evolutionary Algorithms",
|
|
"heading_level": null,
|
|
"page_id": 2,
|
|
"polygon": [
|
|
[
|
|
107.578125,
|
|
274.18359375
|
|
],
|
|
[
|
|
502.0587158203125,
|
|
274.18359375
|
|
],
|
|
[
|
|
502.0587158203125,
|
|
310.7048034667969
|
|
],
|
|
[
|
|
107.578125,
|
|
310.7048034667969
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Erzeugen von Schwedenr \u00a8atselmasken mit Evolution\u00a8aren\nAlgorithmen",
|
|
"heading_level": null,
|
|
"page_id": 2,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
339.15234375
|
|
],
|
|
[
|
|
521.6988525390625,
|
|
339.15234375
|
|
],
|
|
[
|
|
521.6988525390625,
|
|
375.864990234375
|
|
],
|
|
[
|
|
89.6484375,
|
|
375.864990234375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Acknowledgments",
|
|
"heading_level": null,
|
|
"page_id": 6,
|
|
"polygon": [
|
|
[
|
|
242.6484375,
|
|
133.8046875
|
|
],
|
|
[
|
|
367.56939697265625,
|
|
133.8046875
|
|
],
|
|
[
|
|
367.56939697265625,
|
|
149.09027099609375
|
|
],
|
|
[
|
|
242.6484375,
|
|
149.09027099609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Contents",
|
|
"heading_level": null,
|
|
"page_id": 8,
|
|
"polygon": [
|
|
[
|
|
89.947265625,
|
|
104.57171630859375
|
|
],
|
|
[
|
|
174.77435302734375,
|
|
104.57171630859375
|
|
],
|
|
[
|
|
174.77435302734375,
|
|
125.23431396484375
|
|
],
|
|
[
|
|
89.947265625,
|
|
125.23431396484375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Abstract",
|
|
"heading_level": null,
|
|
"page_id": 10,
|
|
"polygon": [
|
|
[
|
|
277.013671875,
|
|
134.578125
|
|
],
|
|
[
|
|
333.337158203125,
|
|
134.578125
|
|
],
|
|
[
|
|
333.337158203125,
|
|
149.09027099609375
|
|
],
|
|
[
|
|
277.013671875,
|
|
149.09027099609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Zusammenfassung",
|
|
"heading_level": null,
|
|
"page_id": 12,
|
|
"polygon": [
|
|
[
|
|
242.6484375,
|
|
133.41796875
|
|
],
|
|
[
|
|
367.9761962890625,
|
|
133.41796875
|
|
],
|
|
[
|
|
367.9761962890625,
|
|
149.09027099609375
|
|
],
|
|
[
|
|
242.6484375,
|
|
149.09027099609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1. About Genetic Algorithms",
|
|
"heading_level": null,
|
|
"page_id": 14,
|
|
"polygon": [
|
|
[
|
|
90.0,
|
|
105.29168701171875
|
|
],
|
|
[
|
|
367.0146789550781,
|
|
105.29168701171875
|
|
],
|
|
[
|
|
367.0146789550781,
|
|
125.95428466796875
|
|
],
|
|
[
|
|
90.0,
|
|
125.95428466796875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1.1. General Functionality",
|
|
"heading_level": null,
|
|
"page_id": 14,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
524.390625
|
|
],
|
|
[
|
|
262.4962158203125,
|
|
524.390625
|
|
],
|
|
[
|
|
262.4962158203125,
|
|
539.859375
|
|
],
|
|
[
|
|
89.6484375,
|
|
539.859375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1.2. Selection",
|
|
"heading_level": null,
|
|
"page_id": 15,
|
|
"polygon": [
|
|
[
|
|
64.546875,
|
|
539.6242980957031
|
|
],
|
|
[
|
|
154.32546997070312,
|
|
539.6242980957031
|
|
],
|
|
[
|
|
154.32546997070312,
|
|
553.9704895019531
|
|
],
|
|
[
|
|
64.546875,
|
|
553.9704895019531
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1.3. Mutation",
|
|
"heading_level": null,
|
|
"page_id": 17,
|
|
"polygon": [
|
|
[
|
|
63.75,
|
|
361.1953125
|
|
],
|
|
[
|
|
156.0,
|
|
361.1953125
|
|
],
|
|
[
|
|
156.0,
|
|
372.75
|
|
],
|
|
[
|
|
63.75,
|
|
372.75
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1.4. Crossover",
|
|
"heading_level": null,
|
|
"page_id": 18,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
296.61328125
|
|
],
|
|
[
|
|
184.078125,
|
|
296.61328125
|
|
],
|
|
[
|
|
184.078125,
|
|
311.0906982421875
|
|
],
|
|
[
|
|
89.6484375,
|
|
311.0906982421875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1.5. Diversity vs. Convergence",
|
|
"heading_level": null,
|
|
"page_id": 19,
|
|
"polygon": [
|
|
[
|
|
64.546875,
|
|
372.0234375
|
|
],
|
|
[
|
|
266.25177001953125,
|
|
372.0234375
|
|
],
|
|
[
|
|
266.25177001953125,
|
|
388.1309509277344
|
|
],
|
|
[
|
|
64.546875,
|
|
388.1309509277344
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "1.6. Summary",
|
|
"heading_level": null,
|
|
"page_id": 20,
|
|
"polygon": [
|
|
[
|
|
89.05078125,
|
|
209.6015625
|
|
],
|
|
[
|
|
182.45628356933594,
|
|
209.6015625
|
|
],
|
|
[
|
|
182.45628356933594,
|
|
224.690673828125
|
|
],
|
|
[
|
|
89.05078125,
|
|
224.690673828125
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "2. About Crossword Masks",
|
|
"heading_level": null,
|
|
"page_id": 22,
|
|
"polygon": [
|
|
[
|
|
89.05078125,
|
|
103.640625
|
|
],
|
|
[
|
|
349.854736328125,
|
|
103.640625
|
|
],
|
|
[
|
|
349.854736328125,
|
|
124.7542724609375
|
|
],
|
|
[
|
|
89.05078125,
|
|
124.7542724609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "2.1. Basic Definitions",
|
|
"heading_level": null,
|
|
"page_id": 23,
|
|
"polygon": [
|
|
[
|
|
64.248046875,
|
|
263.35546875
|
|
],
|
|
[
|
|
205.80953979492188,
|
|
263.35546875
|
|
],
|
|
[
|
|
205.80953979492188,
|
|
278.93084716796875
|
|
],
|
|
[
|
|
64.248046875,
|
|
278.93084716796875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "2.2. Validity Constraints",
|
|
"heading_level": null,
|
|
"page_id": 25,
|
|
"polygon": [
|
|
[
|
|
64.546875,
|
|
51.046875
|
|
],
|
|
[
|
|
225.729248046875,
|
|
51.046875
|
|
],
|
|
[
|
|
225.729248046875,
|
|
66.8902587890625
|
|
],
|
|
[
|
|
64.546875,
|
|
66.8902587890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "2.3. Quality Criteria",
|
|
"heading_level": null,
|
|
"page_id": 25,
|
|
"polygon": [
|
|
[
|
|
63.650390625,
|
|
580.46484375
|
|
],
|
|
[
|
|
197.97299194335938,
|
|
580.46484375
|
|
],
|
|
[
|
|
197.97299194335938,
|
|
596.8103637695312
|
|
],
|
|
[
|
|
63.650390625,
|
|
596.8103637695312
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3. Applying a Genetic Algorithm",
|
|
"heading_level": null,
|
|
"page_id": 28,
|
|
"polygon": [
|
|
[
|
|
88.453125,
|
|
104.80078125
|
|
],
|
|
[
|
|
404.40972900390625,
|
|
104.80078125
|
|
],
|
|
[
|
|
404.40972900390625,
|
|
125.71429443359375
|
|
],
|
|
[
|
|
88.453125,
|
|
125.71429443359375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.1. General Setup",
|
|
"heading_level": null,
|
|
"page_id": 28,
|
|
"polygon": [
|
|
[
|
|
89.349609375,
|
|
153.140625
|
|
],
|
|
[
|
|
213.12542724609375,
|
|
153.140625
|
|
],
|
|
[
|
|
213.12542724609375,
|
|
167.6904296875
|
|
],
|
|
[
|
|
89.349609375,
|
|
167.6904296875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2. The Fitness Function",
|
|
"heading_level": null,
|
|
"page_id": 28,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
567.3440856933594
|
|
],
|
|
[
|
|
255.60406494140625,
|
|
567.3440856933594
|
|
],
|
|
[
|
|
255.60406494140625,
|
|
581.6902770996094
|
|
],
|
|
[
|
|
89.6484375,
|
|
581.6902770996094
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.1. Coverage",
|
|
"heading_level": null,
|
|
"page_id": 29,
|
|
"polygon": [
|
|
[
|
|
63.94921875,
|
|
195.2901611328125
|
|
],
|
|
[
|
|
149.017822265625,
|
|
195.2901611328125
|
|
],
|
|
[
|
|
149.017822265625,
|
|
207.245361328125
|
|
],
|
|
[
|
|
63.94921875,
|
|
207.245361328125
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.2. Word Lengths",
|
|
"heading_level": null,
|
|
"page_id": 29,
|
|
"polygon": [
|
|
[
|
|
64.248046875,
|
|
628.7301483154297
|
|
],
|
|
[
|
|
174.50863647460938,
|
|
628.7301483154297
|
|
],
|
|
[
|
|
174.50863647460938,
|
|
640.6853485107422
|
|
],
|
|
[
|
|
64.248046875,
|
|
640.6853485107422
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.3. Clustering",
|
|
"heading_level": null,
|
|
"page_id": 30,
|
|
"polygon": [
|
|
[
|
|
88.751953125,
|
|
306.66796875
|
|
],
|
|
[
|
|
180.64707946777344,
|
|
306.66796875
|
|
],
|
|
[
|
|
180.64707946777344,
|
|
318.7253723144531
|
|
],
|
|
[
|
|
88.751953125,
|
|
318.7253723144531
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.4. Invalid Definition Fields of Type 3,4,5,6",
|
|
"heading_level": null,
|
|
"page_id": 30,
|
|
"polygon": [
|
|
[
|
|
89.05078125,
|
|
612.94921875
|
|
],
|
|
[
|
|
338.87109375,
|
|
612.94921875
|
|
],
|
|
[
|
|
338.87109375,
|
|
625.8054351806641
|
|
],
|
|
[
|
|
89.05078125,
|
|
625.8054351806641
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.5. Dead Ends",
|
|
"heading_level": null,
|
|
"page_id": 31,
|
|
"polygon": [
|
|
[
|
|
63.3515625,
|
|
53.3671875
|
|
],
|
|
[
|
|
157.46823120117188,
|
|
53.3671875
|
|
],
|
|
[
|
|
157.46823120117188,
|
|
66.24517822265625
|
|
],
|
|
[
|
|
63.3515625,
|
|
66.24517822265625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.6. Result",
|
|
"heading_level": null,
|
|
"page_id": 31,
|
|
"polygon": [
|
|
[
|
|
64.546875,
|
|
119.8828125
|
|
],
|
|
[
|
|
133.10113525390625,
|
|
119.8828125
|
|
],
|
|
[
|
|
133.10113525390625,
|
|
132.72528076171875
|
|
],
|
|
[
|
|
64.546875,
|
|
132.72528076171875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.2.7. Localized Fitness",
|
|
"heading_level": null,
|
|
"page_id": 31,
|
|
"polygon": [
|
|
[
|
|
64.845703125,
|
|
586.65234375
|
|
],
|
|
[
|
|
191.78822326660156,
|
|
586.65234375
|
|
],
|
|
[
|
|
191.78822326660156,
|
|
600.3650360107422
|
|
],
|
|
[
|
|
64.845703125,
|
|
600.3650360107422
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.3. Initialization",
|
|
"heading_level": null,
|
|
"page_id": 32,
|
|
"polygon": [
|
|
[
|
|
88.751953125,
|
|
330.2578125
|
|
],
|
|
[
|
|
204.965087890625,
|
|
330.2578125
|
|
],
|
|
[
|
|
204.965087890625,
|
|
345.5305480957031
|
|
],
|
|
[
|
|
88.751953125,
|
|
345.5305480957031
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.4. Mutation",
|
|
"heading_level": null,
|
|
"page_id": 33,
|
|
"polygon": [
|
|
[
|
|
63.94921875,
|
|
557.9837951660156
|
|
],
|
|
[
|
|
155.16526794433594,
|
|
557.9837951660156
|
|
],
|
|
[
|
|
155.16526794433594,
|
|
572.3299865722656
|
|
],
|
|
[
|
|
63.94921875,
|
|
572.3299865722656
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "\u2022 Field Type Probabilities:",
|
|
"heading_level": null,
|
|
"page_id": 33,
|
|
"polygon": [
|
|
[
|
|
80.27984619140625,
|
|
648.9140625
|
|
],
|
|
[
|
|
216.052734375,
|
|
648.9140625
|
|
],
|
|
[
|
|
216.052734375,
|
|
662.8359375
|
|
],
|
|
[
|
|
80.27984619140625,
|
|
662.8359375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "\u2022 Centralized Mutation:",
|
|
"heading_level": null,
|
|
"page_id": 34,
|
|
"polygon": [
|
|
[
|
|
105.0,
|
|
410.25
|
|
],
|
|
[
|
|
228.75,
|
|
410.25
|
|
],
|
|
[
|
|
228.75,
|
|
420.0
|
|
],
|
|
[
|
|
105.0,
|
|
420.0
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "\u2022 Guided Mutation:",
|
|
"heading_level": null,
|
|
"page_id": 34,
|
|
"polygon": [
|
|
[
|
|
105.0,
|
|
552.62109375
|
|
],
|
|
[
|
|
208.5,
|
|
552.62109375
|
|
],
|
|
[
|
|
208.5,
|
|
563.25
|
|
],
|
|
[
|
|
105.0,
|
|
563.25
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "\u2022 Predefined Mutation:",
|
|
"heading_level": null,
|
|
"page_id": 35,
|
|
"polygon": [
|
|
[
|
|
80.0859375,
|
|
53.75390625
|
|
],
|
|
[
|
|
198.44728088378906,
|
|
53.75390625
|
|
],
|
|
[
|
|
198.44728088378906,
|
|
66.06463623046875
|
|
],
|
|
[
|
|
80.0859375,
|
|
66.06463623046875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.5. Crossover",
|
|
"heading_level": null,
|
|
"page_id": 37,
|
|
"polygon": [
|
|
[
|
|
63.94921875,
|
|
51.8203125
|
|
],
|
|
[
|
|
158.94029235839844,
|
|
51.8203125
|
|
],
|
|
[
|
|
158.94029235839844,
|
|
66.8902587890625
|
|
],
|
|
[
|
|
63.94921875,
|
|
66.8902587890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.6. Results",
|
|
"heading_level": null,
|
|
"page_id": 40,
|
|
"polygon": [
|
|
[
|
|
88.751953125,
|
|
51.8203125
|
|
],
|
|
[
|
|
167.28958129882812,
|
|
51.8203125
|
|
],
|
|
[
|
|
167.28958129882812,
|
|
66.8902587890625
|
|
],
|
|
[
|
|
88.751953125,
|
|
66.8902587890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "3.7. Discussion",
|
|
"heading_level": null,
|
|
"page_id": 44,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
51.8203125
|
|
],
|
|
[
|
|
191.1653594970703,
|
|
51.8203125
|
|
],
|
|
[
|
|
191.1653594970703,
|
|
66.8902587890625
|
|
],
|
|
[
|
|
89.6484375,
|
|
66.8902587890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "4. Memetic Algorithm Approach",
|
|
"heading_level": null,
|
|
"page_id": 48,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
104.0916748046875
|
|
],
|
|
[
|
|
400.34527587890625,
|
|
104.0916748046875
|
|
],
|
|
[
|
|
400.34527587890625,
|
|
124.7542724609375
|
|
],
|
|
[
|
|
89.6484375,
|
|
124.7542724609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "4.1. Basic Idea",
|
|
"heading_level": null,
|
|
"page_id": 48,
|
|
"polygon": [
|
|
[
|
|
88.453125,
|
|
148.88671875
|
|
],
|
|
[
|
|
185.2529296875,
|
|
148.88671875
|
|
],
|
|
[
|
|
185.2529296875,
|
|
164.6900634765625
|
|
],
|
|
[
|
|
88.453125,
|
|
164.6900634765625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "4.2. Implementation",
|
|
"heading_level": null,
|
|
"page_id": 49,
|
|
"polygon": [
|
|
[
|
|
64.248046875,
|
|
114.08203125
|
|
],
|
|
[
|
|
199.8050537109375,
|
|
114.08203125
|
|
],
|
|
[
|
|
199.8050537109375,
|
|
129.8902587890625
|
|
],
|
|
[
|
|
64.248046875,
|
|
129.8902587890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "4.3. Results",
|
|
"heading_level": null,
|
|
"page_id": 51,
|
|
"polygon": [
|
|
[
|
|
64.546875,
|
|
51.046875
|
|
],
|
|
[
|
|
142.32940673828125,
|
|
51.046875
|
|
],
|
|
[
|
|
142.32940673828125,
|
|
66.8902587890625
|
|
],
|
|
[
|
|
64.546875,
|
|
66.8902587890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "5. Practical Results",
|
|
"heading_level": null,
|
|
"page_id": 54,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
104.0916748046875
|
|
],
|
|
[
|
|
271.014404296875,
|
|
104.0916748046875
|
|
],
|
|
[
|
|
271.014404296875,
|
|
124.7542724609375
|
|
],
|
|
[
|
|
89.6484375,
|
|
124.7542724609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "6. Further Work",
|
|
"heading_level": null,
|
|
"page_id": 56,
|
|
"polygon": [
|
|
[
|
|
90.0,
|
|
103.640625
|
|
],
|
|
[
|
|
242.18515014648438,
|
|
103.640625
|
|
],
|
|
[
|
|
242.18515014648438,
|
|
124.7542724609375
|
|
],
|
|
[
|
|
90.0,
|
|
124.7542724609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Appendix",
|
|
"heading_level": null,
|
|
"page_id": 58,
|
|
"polygon": [
|
|
[
|
|
247.4296875,
|
|
263.67987060546875
|
|
],
|
|
[
|
|
362.19366455078125,
|
|
263.67987060546875
|
|
],
|
|
[
|
|
362.19366455078125,
|
|
288.87890625
|
|
],
|
|
[
|
|
247.4296875,
|
|
288.87890625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "A. Code",
|
|
"heading_level": null,
|
|
"page_id": 60,
|
|
"polygon": [
|
|
[
|
|
87.75,
|
|
103.5
|
|
],
|
|
[
|
|
171.75,
|
|
103.5
|
|
],
|
|
[
|
|
171.75,
|
|
120.26953125
|
|
],
|
|
[
|
|
87.75,
|
|
120.26953125
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Algorithm 1: Mutation",
|
|
"heading_level": null,
|
|
"page_id": 60,
|
|
"polygon": [
|
|
[
|
|
98.25,
|
|
159.75
|
|
],
|
|
[
|
|
212.25,
|
|
159.75
|
|
],
|
|
[
|
|
212.25,
|
|
170.54296875
|
|
],
|
|
[
|
|
98.25,
|
|
170.54296875
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Algorithm 2: Crossover",
|
|
"heading_level": null,
|
|
"page_id": 61,
|
|
"polygon": [
|
|
[
|
|
73.810546875,
|
|
57.62109375
|
|
],
|
|
[
|
|
190.30941772460938,
|
|
57.62109375
|
|
],
|
|
[
|
|
190.30941772460938,
|
|
68.82464599609375
|
|
],
|
|
[
|
|
73.810546875,
|
|
68.82464599609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Algorithm 3: Basic Hillclimber",
|
|
"heading_level": null,
|
|
"page_id": 62,
|
|
"polygon": [
|
|
[
|
|
98.912109375,
|
|
57.62109375
|
|
],
|
|
[
|
|
248.50917053222656,
|
|
57.62109375
|
|
],
|
|
[
|
|
248.50917053222656,
|
|
68.9447021484375
|
|
],
|
|
[
|
|
98.912109375,
|
|
68.9447021484375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Algorithm 4: Basic Genetic Algorithm",
|
|
"heading_level": null,
|
|
"page_id": 63,
|
|
"polygon": [
|
|
[
|
|
72.9140625,
|
|
56.4609375
|
|
],
|
|
[
|
|
259.11322021484375,
|
|
56.4609375
|
|
],
|
|
[
|
|
259.11322021484375,
|
|
68.9447021484375
|
|
],
|
|
[
|
|
72.9140625,
|
|
68.9447021484375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Algorithm 5: Memetic Approach",
|
|
"heading_level": null,
|
|
"page_id": 64,
|
|
"polygon": [
|
|
[
|
|
97.41796875,
|
|
57.0
|
|
],
|
|
[
|
|
261.0,
|
|
57.0
|
|
],
|
|
[
|
|
261.0,
|
|
68.0625
|
|
],
|
|
[
|
|
97.41796875,
|
|
68.0625
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "B. Sample Masks",
|
|
"heading_level": null,
|
|
"page_id": 66,
|
|
"polygon": [
|
|
[
|
|
89.05078125,
|
|
103.640625
|
|
],
|
|
[
|
|
257.45452880859375,
|
|
103.640625
|
|
],
|
|
[
|
|
257.45452880859375,
|
|
124.7542724609375
|
|
],
|
|
[
|
|
89.05078125,
|
|
124.7542724609375
|
|
]
|
|
]
|
|
},
|
|
{
|
|
"title": "Bibliography",
|
|
"heading_level": null,
|
|
"page_id": 72,
|
|
"polygon": [
|
|
[
|
|
89.6484375,
|
|
104.02734375
|
|
],
|
|
[
|
|
215.00863647460938,
|
|
104.02734375
|
|
],
|
|
[
|
|
215.00863647460938,
|
|
124.91015625
|
|
],
|
|
[
|
|
89.6484375,
|
|
124.91015625
|
|
]
|
|
]
|
|
}
|
|
],
|
|
"page_stats": [
|
|
{
|
|
"page_id": 0,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
23
|
|
],
|
|
[
|
|
"Line",
|
|
6
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"Picture",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 1,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
33
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 2,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
35
|
|
],
|
|
[
|
|
"Line",
|
|
12
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
5
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"Picture",
|
|
2
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 3,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
33
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 4,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
46
|
|
],
|
|
[
|
|
"Span",
|
|
5
|
|
],
|
|
[
|
|
"Line",
|
|
3
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 5,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
33
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 6,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
27
|
|
],
|
|
[
|
|
"Line",
|
|
10
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 7,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Line",
|
|
1
|
|
],
|
|
[
|
|
"Span",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 8,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
145
|
|
],
|
|
[
|
|
"TableCell",
|
|
132
|
|
],
|
|
[
|
|
"Line",
|
|
35
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"TableOfContents",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 9,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
40
|
|
],
|
|
[
|
|
"TableCell",
|
|
27
|
|
],
|
|
[
|
|
"Line",
|
|
11
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"TableOfContents",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 10,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
92
|
|
],
|
|
[
|
|
"Line",
|
|
29
|
|
],
|
|
[
|
|
"Text",
|
|
4
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 11,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
33
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 12,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
47
|
|
],
|
|
[
|
|
"Line",
|
|
24
|
|
],
|
|
[
|
|
"Text",
|
|
4
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 13,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
33
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 14,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
76
|
|
],
|
|
[
|
|
"Line",
|
|
32
|
|
],
|
|
[
|
|
"Text",
|
|
8
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 15,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
93
|
|
],
|
|
[
|
|
"Line",
|
|
32
|
|
],
|
|
[
|
|
"Text",
|
|
4
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 16,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Line",
|
|
63
|
|
],
|
|
[
|
|
"Span",
|
|
42
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 17,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Line",
|
|
41
|
|
],
|
|
[
|
|
"Span",
|
|
29
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 18,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
159
|
|
],
|
|
[
|
|
"Line",
|
|
45
|
|
],
|
|
[
|
|
"Text",
|
|
4
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 19,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
124
|
|
],
|
|
[
|
|
"Line",
|
|
46
|
|
],
|
|
[
|
|
"Text",
|
|
7
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"Footnote",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 20,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
84
|
|
],
|
|
[
|
|
"Line",
|
|
35
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"Footnote",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 21,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
9
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 22,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
234
|
|
],
|
|
[
|
|
"Line",
|
|
107
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 23,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
177
|
|
],
|
|
[
|
|
"Line",
|
|
40
|
|
],
|
|
[
|
|
"Text",
|
|
15
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 24,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
33
|
|
],
|
|
[
|
|
"Line",
|
|
13
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 25,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
73
|
|
],
|
|
[
|
|
"Line",
|
|
25
|
|
],
|
|
[
|
|
"ListItem",
|
|
4
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 26,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
87
|
|
],
|
|
[
|
|
"Line",
|
|
28
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"ListItem",
|
|
3
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 27,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
26
|
|
],
|
|
[
|
|
"Line",
|
|
9
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 28,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
219
|
|
],
|
|
[
|
|
"Line",
|
|
85
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
3
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 29,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
84
|
|
],
|
|
[
|
|
"Line",
|
|
34
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"ListItem",
|
|
5
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 30,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
232
|
|
],
|
|
[
|
|
"TableCell",
|
|
90
|
|
],
|
|
[
|
|
"Line",
|
|
57
|
|
],
|
|
[
|
|
"Table",
|
|
4
|
|
],
|
|
[
|
|
"Reference",
|
|
4
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"TableGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 31,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
93
|
|
],
|
|
[
|
|
"Line",
|
|
37
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"Reference",
|
|
4
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
3
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 32,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
72
|
|
],
|
|
[
|
|
"Line",
|
|
28
|
|
],
|
|
[
|
|
"Text",
|
|
6
|
|
],
|
|
[
|
|
"ListItem",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 33,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
64
|
|
],
|
|
[
|
|
"Line",
|
|
18
|
|
],
|
|
[
|
|
"Caption",
|
|
3
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Picture",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"PictureGroup",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 34,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
36
|
|
],
|
|
[
|
|
"Line",
|
|
35
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 35,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
107
|
|
],
|
|
[
|
|
"Line",
|
|
31
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"ListItem",
|
|
2
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Picture",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"PictureGroup",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 36,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
60
|
|
],
|
|
[
|
|
"Line",
|
|
22
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 37,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
74
|
|
],
|
|
[
|
|
"Line",
|
|
26
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 38,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
136
|
|
],
|
|
[
|
|
"Line",
|
|
41
|
|
],
|
|
[
|
|
"TableCell",
|
|
21
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"ListItem",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Table",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"TableGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 39,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
19
|
|
],
|
|
[
|
|
"Line",
|
|
5
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 40,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
136
|
|
],
|
|
[
|
|
"Line",
|
|
25
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"ListItem",
|
|
3
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 41,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Line",
|
|
38
|
|
],
|
|
[
|
|
"Span",
|
|
18
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 42,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
107
|
|
],
|
|
[
|
|
"Line",
|
|
38
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 43,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
65
|
|
],
|
|
[
|
|
"Line",
|
|
19
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 44,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
155
|
|
],
|
|
[
|
|
"Line",
|
|
54
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 45,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
94
|
|
],
|
|
[
|
|
"Line",
|
|
26
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 46,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
55
|
|
],
|
|
[
|
|
"Line",
|
|
26
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 47,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
11
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 48,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
62
|
|
],
|
|
[
|
|
"Line",
|
|
22
|
|
],
|
|
[
|
|
"Text",
|
|
3
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 49,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
78
|
|
],
|
|
[
|
|
"Line",
|
|
26
|
|
],
|
|
[
|
|
"Text",
|
|
4
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 50,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
71
|
|
],
|
|
[
|
|
"Line",
|
|
26
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 51,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
126
|
|
],
|
|
[
|
|
"Line",
|
|
31
|
|
],
|
|
[
|
|
"ListItem",
|
|
4
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Text",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 52,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Line",
|
|
37
|
|
],
|
|
[
|
|
"Span",
|
|
10
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 53,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Line",
|
|
34
|
|
],
|
|
[
|
|
"Span",
|
|
13
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"Caption",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 54,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
75
|
|
],
|
|
[
|
|
"Line",
|
|
30
|
|
],
|
|
[
|
|
"Text",
|
|
5
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"Footnote",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 55,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
7
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 56,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
111
|
|
],
|
|
[
|
|
"Line",
|
|
34
|
|
],
|
|
[
|
|
"Text",
|
|
2
|
|
],
|
|
[
|
|
"Reference",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Footnote",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 57,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
7
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 58,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
3
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 59,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"TableCell",
|
|
33
|
|
],
|
|
[
|
|
"Form",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 60,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
33
|
|
],
|
|
[
|
|
"Line",
|
|
23
|
|
],
|
|
[
|
|
"Reference",
|
|
3
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
2
|
|
],
|
|
[
|
|
"Code",
|
|
1
|
|
],
|
|
[
|
|
"Text",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 61,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
138
|
|
],
|
|
[
|
|
"Line",
|
|
15
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Code",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 62,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
107
|
|
],
|
|
[
|
|
"Line",
|
|
16
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Text",
|
|
1
|
|
],
|
|
[
|
|
"Code",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 63,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
265
|
|
],
|
|
[
|
|
"Line",
|
|
32
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Code",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 64,
|
|
"text_extraction_method": "surya",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
124
|
|
],
|
|
[
|
|
"Line",
|
|
76
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"Code",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 65,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
5
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 66,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
3
|
|
],
|
|
[
|
|
"Line",
|
|
2
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"Reference",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 67,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
127
|
|
],
|
|
[
|
|
"TableCell",
|
|
86
|
|
],
|
|
[
|
|
"Line",
|
|
11
|
|
],
|
|
[
|
|
"Caption",
|
|
3
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Table",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"TableGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 68,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
121
|
|
],
|
|
[
|
|
"TableCell",
|
|
57
|
|
],
|
|
[
|
|
"Line",
|
|
10
|
|
],
|
|
[
|
|
"Caption",
|
|
3
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"Table",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"TableGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 69,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
127
|
|
],
|
|
[
|
|
"TableCell",
|
|
83
|
|
],
|
|
[
|
|
"Line",
|
|
11
|
|
],
|
|
[
|
|
"Caption",
|
|
3
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Table",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"TableGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 70,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
121
|
|
],
|
|
[
|
|
"TableCell",
|
|
54
|
|
],
|
|
[
|
|
"Line",
|
|
10
|
|
],
|
|
[
|
|
"Caption",
|
|
3
|
|
],
|
|
[
|
|
"Figure",
|
|
2
|
|
],
|
|
[
|
|
"Table",
|
|
2
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
2
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"TableGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 71,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
13
|
|
],
|
|
[
|
|
"Line",
|
|
4
|
|
],
|
|
[
|
|
"PageHeader",
|
|
1
|
|
],
|
|
[
|
|
"Figure",
|
|
1
|
|
],
|
|
[
|
|
"Caption",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"FigureGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
},
|
|
{
|
|
"page_id": 72,
|
|
"text_extraction_method": "pdftext",
|
|
"block_counts": [
|
|
[
|
|
"Span",
|
|
53
|
|
],
|
|
[
|
|
"Line",
|
|
19
|
|
],
|
|
[
|
|
"ListItem",
|
|
8
|
|
],
|
|
[
|
|
"SectionHeader",
|
|
1
|
|
],
|
|
[
|
|
"PageFooter",
|
|
1
|
|
],
|
|
[
|
|
"ListGroup",
|
|
1
|
|
]
|
|
],
|
|
"block_metadata": {
|
|
"llm_request_count": 0,
|
|
"llm_error_count": 0,
|
|
"llm_tokens_used": 0,
|
|
"previous_text": "",
|
|
"previous_type": "",
|
|
"previous_order": 0
|
|
}
|
|
}
|
|
],
|
|
"debug_data_path": "debug_data/swedish_crossword_puzzle"
|
|
} |