fix: make OCR portable and reliable across AMD64 and ARM64 (#519)

* fix: make OCR portable and reliable

* fix: harden OCR installation portability

* fix: pin OCR partials across downloads

* fix: make OCR execution reliably asynchronous

* fix: harden OCR portability and docs routes

* fix: preserve decoder and docs safeguards
This commit is contained in:
SnapOtter
2026-07-15 03:34:24 +08:00
committed by GitHub
parent 58121f205f
commit 991c981529
409 changed files with 67151 additions and 8076 deletions
@@ -0,0 +1,21 @@
{
"exactGroundTruth": "HOSPITAL\nOakwood Community Clinic\n450 North Main Street\nMadison, WI 53703\n(608) 555-0102\nPatient Name: Isabella Garcia \nMRN: 9884021 \nDOB: 11/05/1998 \nGender: Female \nAge: 26\nMRN: 9884021 \nAccession: B11269-25 \nDate: 06/20/2025\nThe patient is a 26-year-old female with a history of persistent asthma since childhood. She reports seasonal exacerbations, typically in the spring and fall. Current medications include a daily inhaled corticosteroid and an albuterol inhaler for rescue use, which she reports using 3-4 times per week recently. She has a known allergy to dust mites and pollen. No history of smoking.\nPROCEDURES:\nSpirometry (pre- and post-bronchodilator): Demonstrated a reversible obstructive pattern, consistent with asthma. FEV1 increased by 15% after albuterol administration. \nAllergy Skin Testing: Positive reaction to tree pollen and dust mites. \nChest X-ray (PA and Lateral): Lungs are clear. No acute infiltrate or edema.\nIMPRESSION:\nModerate persistent asthma, sub-optimally controlled based on recent increase in rescue inhaler use.\nAllergic rhinitis.\nPatient Name: Johnathan Smith MRN: 8675309 Age: 67\nElectronically Signed By: Dr. David Chen, M.D. \nDate: 06/23/2025 Time: 08:56",
"record": {
"doc_id": "poor_t7_s2",
"ground_truth": "HOSPITAL\nOakwood Community Clinic\n450 North Main Street\nMadison, WI 53703\n(608) 555-0102\nPatient Name: Isabella Garcia \nMRN: 9884021 \nDOB: 11/05/1998 \nGender: Female \nAge: 26\nMRN: 9884021 \nAccession: B11269-25 \nDate: 06/20/2025\nThe patient is a 26-year-old female with a history of persistent asthma since childhood. She reports seasonal exacerbations, typically in the spring and fall. Current medications include a daily inhaled corticosteroid and an albuterol inhaler for rescue use, which she reports using 3-4 times per week recently. She has a known allergy to dust mites and pollen. No history of smoking.\nPROCEDURES:\nSpirometry (pre- and post-bronchodilator): Demonstrated a reversible obstructive pattern, consistent with asthma. FEV1 increased by 15% after albuterol administration. \nAllergy Skin Testing: Positive reaction to tree pollen and dust mites. \nChest X-ray (PA and Lateral): Lungs are clear. No acute infiltrate or edema.\nIMPRESSION:\nModerate persistent asthma, sub-optimally controlled based on recent increase in rescue inhaler use.\nAllergic rhinitis.\nPatient Name: Johnathan Smith MRN: 8675309 Age: 67\nElectronically Signed By: Dr. David Chen, M.D. \nDate: 06/23/2025 Time: 08:56",
"hetero_id": "poor_t8_s1",
"homo_id": "poor_t7_s1",
"sample": 2,
"subset": "poor",
"template": 7
},
"source": {
"dataset": "ClinOCR-Bench/ClinOCR-Bench",
"globalRowIndex": 42,
"repositoryRevision": "cb7c0c48a4f3d1c9054fb6548ccef84768983472",
"rowGroup": 0,
"rowIndex": 42,
"split": "test",
"upstreamId": "poor_t7_s2"
}
}
@@ -0,0 +1,13 @@
{
"exactGroundTruth": "715\n중계\nJunggye\n中溪\n하계\nHagye\n下溪\n공릉\nGongneung\n孔陵",
"source": {
"dataset": "Wikimedia Commons",
"fileTimestamp": "2009-08-18T13:00:50Z",
"pageId": 7592246,
"repositoryRevision": "1234274506",
"sha1": "fd1f0cc88f931af22576c7404270837916c60d8d",
"sha256": "a9ae819505be17d87393695bdadd1aaff47b0a8b81faec98b38408397942b3dc",
"sourceUrl": "https://upload.wikimedia.org/wikipedia/commons/c/cb/Hagye01.jpg",
"upstreamId": "7592246"
}
}
@@ -0,0 +1,398 @@
{
"exactGroundTruth": "1\nViet\nMilk\nCoffee\n25,000\n+Ice\n+M\nSubtotal\n25.000\nTotal\n25.000\nCASH\n25.000\nKembalian\n0",
"record": {
"ground_truth": {
"dontcare": [],
"gt_parse": {
"menu": {
"cnt": "1",
"nm": "Viet Milk Coffee",
"price": "25,000",
"sub": [
{
"nm": "+Ice"
},
{
"nm": "+M"
}
]
},
"sub_total": {
"subtotal_price": "25.000"
},
"total": {
"cashprice": "25.000",
"changeprice": "0",
"total_price": "25.000"
}
},
"meta": {
"image_id": 80,
"image_size": {
"height": 648,
"width": 432
},
"split": "test",
"version": "2.0.0"
},
"repeating_symbol": [
[
{
"quad": {
"x1": 61,
"x2": 387,
"x3": 391,
"x4": 62,
"y1": 316,
"y2": 301,
"y3": 315,
"y4": 330
},
"text": "-"
}
],
[
{
"quad": {
"x1": 63,
"x2": 396,
"x3": 397,
"x4": 65,
"y1": 407,
"y2": 393,
"y3": 406,
"y4": 423
},
"text": "-"
}
],
[
{
"quad": {
"x1": 64,
"x2": 401,
"x3": 402,
"x4": 68,
"y1": 464,
"y2": 448,
"y3": 462,
"y4": 478
},
"text": "-"
}
]
],
"roi": {
"x1": 48,
"x2": 405,
"x3": 412,
"x4": 48,
"y1": 59,
"y2": 24,
"y3": 559,
"y4": 558
},
"valid_line": [
{
"category": "menu.cnt",
"group_id": 3,
"sub_group_id": 0,
"words": [
{
"is_key": 0,
"quad": {
"x1": 65,
"x2": 75,
"x3": 76,
"x4": 65,
"y1": 350,
"y2": 351,
"y3": 369,
"y4": 367
},
"row_id": 1274853,
"text": "1"
}
]
},
{
"category": "menu.nm",
"group_id": 3,
"sub_group_id": 0,
"words": [
{
"is_key": 0,
"quad": {
"x1": 78,
"x2": 109,
"x3": 111,
"x4": 80,
"y1": 350,
"y2": 349,
"y3": 368,
"y4": 368
},
"row_id": 1274853,
"text": "Viet"
},
{
"is_key": 0,
"quad": {
"x1": 112,
"x2": 144,
"x3": 145,
"x4": 112,
"y1": 349,
"y2": 347,
"y3": 366,
"y4": 367
},
"row_id": 1274853,
"text": "Milk"
},
{
"is_key": 0,
"quad": {
"x1": 146,
"x2": 192,
"x3": 193,
"x4": 147,
"y1": 346,
"y2": 345,
"y3": 363,
"y4": 364
},
"row_id": 1274853,
"text": "Coffee"
}
]
},
{
"category": "menu.price",
"group_id": 3,
"sub_group_id": 0,
"words": [
{
"is_key": 0,
"quad": {
"x1": 339,
"x2": 383,
"x3": 385,
"x4": 340,
"y1": 337,
"y2": 334,
"y3": 353,
"y4": 355
},
"row_id": 1274853,
"text": "25,000"
}
]
},
{
"category": "menu.sub.nm",
"group_id": 3,
"sub_group_id": 0,
"words": [
{
"is_key": 0,
"quad": {
"x1": 73,
"x2": 105,
"x3": 105,
"x4": 73,
"y1": 369,
"y2": 369,
"y3": 387,
"y4": 387
},
"row_id": 1274854,
"text": "+Ice"
}
]
},
{
"category": "menu.sub.nm",
"group_id": 3,
"sub_group_id": 1,
"words": [
{
"is_key": 0,
"quad": {
"x1": 73,
"x2": 91,
"x3": 92,
"x4": 73,
"y1": 388,
"y2": 387,
"y3": 404,
"y4": 405
},
"row_id": 1274856,
"text": "+M"
}
]
},
{
"category": "sub_total.subtotal_price",
"group_id": 4,
"sub_group_id": 0,
"words": [
{
"is_key": 1,
"quad": {
"x1": 67,
"x2": 125,
"x3": 127,
"x4": 67,
"y1": 425,
"y2": 422,
"y3": 440,
"y4": 443
},
"row_id": 1274858,
"text": "Subtotal"
},
{
"is_key": 0,
"quad": {
"x1": 344,
"x2": 389,
"x3": 390,
"x4": 344,
"y1": 412,
"y2": 411,
"y3": 428,
"y4": 429
},
"row_id": 1274858,
"text": "25.000"
}
]
},
{
"category": "total.total_price",
"group_id": 5,
"sub_group_id": 0,
"words": [
{
"is_key": 1,
"quad": {
"x1": 68,
"x2": 104,
"x3": 106,
"x4": 69,
"y1": 443,
"y2": 442,
"y3": 459,
"y4": 460
},
"row_id": 1274861,
"text": "Total"
},
{
"is_key": 0,
"quad": {
"x1": 345,
"x2": 390,
"x3": 391,
"x4": 346,
"y1": 430,
"y2": 428,
"y3": 445,
"y4": 448
},
"row_id": 1274861,
"text": "25.000"
}
]
},
{
"category": "total.cashprice",
"group_id": 5,
"sub_group_id": 0,
"words": [
{
"is_key": 1,
"quad": {
"x1": 71,
"x2": 103,
"x3": 107,
"x4": 73,
"y1": 477,
"y2": 476,
"y3": 503,
"y4": 505
},
"row_id": 1274864,
"text": "CASH"
},
{
"is_key": 0,
"quad": {
"x1": 345,
"x2": 392,
"x3": 394,
"x4": 346,
"y1": 467,
"y2": 465,
"y3": 492,
"y4": 494
},
"row_id": 1274864,
"text": "25.000"
}
]
},
{
"category": "total.changeprice",
"group_id": 5,
"sub_group_id": 0,
"words": [
{
"is_key": 1,
"quad": {
"x1": 73,
"x2": 138,
"x3": 143,
"x4": 76,
"y1": 503,
"y2": 501,
"y3": 524,
"y4": 526
},
"row_id": 1274867,
"text": "Kembalian"
},
{
"is_key": 0,
"quad": {
"x1": 380,
"x2": 392,
"x3": 391,
"x4": 380,
"y1": 490,
"y2": 490,
"y3": 514,
"y4": 513
},
"row_id": 1274867,
"text": "0"
}
]
}
]
},
"image_path": null,
"raw_ground_truth": "{\"gt_parse\": {\"menu\": {\"nm\": \"Viet Milk Coffee\", \"cnt\": \"1\", \"price\": \"25,000\", \"sub\": [{\"nm\": \"+Ice\"}, {\"nm\": \"+M\"}]}, \"sub_total\": {\"subtotal_price\": \"25.000\"}, \"total\": {\"total_price\": \"25.000\", \"cashprice\": \"25.000\", \"changeprice\": \"0\"}}, \"meta\": {\"version\": \"2.0.0\", \"split\": \"test\", \"image_id\": 80, \"image_size\": {\"width\": 432, \"height\": 648}}, \"valid_line\": [{\"words\": [{\"quad\": {\"x2\": 75, \"y3\": 369, \"x3\": 76, \"y4\": 367, \"x1\": 65, \"y1\": 350, \"x4\": 65, \"y2\": 351}, \"is_key\": 0, \"row_id\": 1274853, \"text\": \"1\"}], \"category\": \"menu.cnt\", \"group_id\": 3, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 109, \"y3\": 368, \"x3\": 111, \"y4\": 368, \"x1\": 78, \"y1\": 350, \"x4\": 80, \"y2\": 349}, \"is_key\": 0, \"row_id\": 1274853, \"text\": \"Viet\"}, {\"quad\": {\"x2\": 144, \"y3\": 366, \"x3\": 145, \"y4\": 367, \"x1\": 112, \"y1\": 349, \"x4\": 112, \"y2\": 347}, \"is_key\": 0, \"row_id\": 1274853, \"text\": \"Milk\"}, {\"quad\": {\"x2\": 192, \"y3\": 363, \"x3\": 193, \"y4\": 364, \"x1\": 146, \"y1\": 346, \"x4\": 147, \"y2\": 345}, \"is_key\": 0, \"row_id\": 1274853, \"text\": \"Coffee\"}], \"category\": \"menu.nm\", \"group_id\": 3, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 383, \"y3\": 353, \"x3\": 385, \"y4\": 355, \"x1\": 339, \"y1\": 337, \"x4\": 340, \"y2\": 334}, \"is_key\": 0, \"row_id\": 1274853, \"text\": \"25,000\"}], \"category\": \"menu.price\", \"group_id\": 3, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 105, \"y3\": 387, \"x3\": 105, \"y4\": 387, \"x1\": 73, \"y1\": 369, \"x4\": 73, \"y2\": 369}, \"is_key\": 0, \"row_id\": 1274854, \"text\": \"+Ice\"}], \"category\": \"menu.sub.nm\", \"group_id\": 3, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 91, \"y3\": 404, \"x3\": 92, \"y4\": 405, \"x1\": 73, \"y1\": 388, \"x4\": 73, \"y2\": 387}, \"is_key\": 0, \"row_id\": 1274856, \"text\": \"+M\"}], \"category\": \"menu.sub.nm\", \"group_id\": 3, \"sub_group_id\": 1}, {\"words\": [{\"quad\": {\"x2\": 125, \"y3\": 440, \"x3\": 127, \"y4\": 443, \"x1\": 67, \"y1\": 425, \"x4\": 67, \"y2\": 422}, \"is_key\": 1, \"row_id\": 1274858, \"text\": \"Subtotal\"}, {\"quad\": {\"x2\": 389, \"y3\": 428, \"x3\": 390, \"y4\": 429, \"x1\": 344, \"y1\": 412, \"x4\": 344, \"y2\": 411}, \"is_key\": 0, \"row_id\": 1274858, \"text\": \"25.000\"}], \"category\": \"sub_total.subtotal_price\", \"group_id\": 4, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 104, \"y3\": 459, \"x3\": 106, \"y4\": 460, \"x1\": 68, \"y1\": 443, \"x4\": 69, \"y2\": 442}, \"is_key\": 1, \"row_id\": 1274861, \"text\": \"Total\"}, {\"quad\": {\"x2\": 390, \"y3\": 445, \"x3\": 391, \"y4\": 448, \"x1\": 345, \"y1\": 430, \"x4\": 346, \"y2\": 428}, \"is_key\": 0, \"row_id\": 1274861, \"text\": \"25.000\"}], \"category\": \"total.total_price\", \"group_id\": 5, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 103, \"y3\": 503, \"x3\": 107, \"y4\": 505, \"x1\": 71, \"y1\": 477, \"x4\": 73, \"y2\": 476}, \"is_key\": 1, \"row_id\": 1274864, \"text\": \"CASH\"}, {\"quad\": {\"x2\": 392, \"y3\": 492, \"x3\": 394, \"y4\": 494, \"x1\": 345, \"y1\": 467, \"x4\": 346, \"y2\": 465}, \"is_key\": 0, \"row_id\": 1274864, \"text\": \"25.000\"}], \"category\": \"total.cashprice\", \"group_id\": 5, \"sub_group_id\": 0}, {\"words\": [{\"quad\": {\"x2\": 138, \"y3\": 524, \"x3\": 143, \"y4\": 526, \"x1\": 73, \"y1\": 503, \"x4\": 76, \"y2\": 501}, \"is_key\": 1, \"row_id\": 1274867, \"text\": \"Kembalian\"}, {\"quad\": {\"x2\": 392, \"y3\": 514, \"x3\": 391, \"y4\": 513, \"x1\": 380, \"y1\": 490, \"x4\": 380, \"y2\": 490}, \"is_key\": 0, \"row_id\": 1274867, \"text\": \"0\"}], \"category\": \"total.changeprice\", \"group_id\": 5, \"sub_group_id\": 0}], \"roi\": {\"x2\": 405, \"y3\": 559, \"x3\": 412, \"y4\": 558, \"x1\": 48, \"y1\": 59, \"x4\": 48, \"y2\": 24}, \"repeating_symbol\": [[{\"quad\": {\"x2\": 387, \"y3\": 315, \"x3\": 391, \"y4\": 330, \"x1\": 61, \"y1\": 316, \"x4\": 62, \"y2\": 301}, \"text\": \"-\"}], [{\"quad\": {\"x2\": 396, \"y3\": 406, \"x3\": 397, \"y4\": 423, \"x1\": 63, \"y1\": 407, \"x4\": 65, \"y2\": 393}, \"text\": \"-\"}], [{\"quad\": {\"x2\": 401, \"y3\": 462, \"x3\": 402, \"y4\": 478, \"x1\": 64, \"y1\": 464, \"x4\": 68, \"y2\": 448}, \"text\": \"-\"}]], \"dontcare\": []}"
},
"source": {
"dataset": "naver-clova-ix/cord-v2",
"globalRowIndex": 80,
"repositoryRevision": "7f0115a4b758a71d6473b8d085751692da2fef98",
"rowGroup": 0,
"rowIndex": 80,
"split": "test",
"upstreamId": "80"
}
}
@@ -0,0 +1,978 @@
{
"exactGroundTruth": "抗菌消臭防臭\nマスクの消臭・抗菌スプレー\n¥マスクにスプレーするだけで/\nウイルス・菌・ニオイを24時間制御!\nW効果\n消臭成分\n抗菌成分\nMISとは?\n特許\n取得清\n第6125400号\n●菌が”生きられない”\nお子様にも安心\n24\n24時間\nミントの香りで\nリフレッシュ\n第三者による各種試験データ取得済み\n※全てのウイルス・菌・ニオイに効果があるわけではありません。\n使用方法\n容器を軽く振り、キャップを外して、マスクの内側・外側それぞれに約10cm離して\n外側に\n内側に\n*使用開始時、数回の空押しが必要な場合があります。\n*スプレーしてなじませた後、よく乾かしてから使用してください。\n*色落ちやシミが気になるものは、目立たない箇所で試してから使用してください。\n*逆さにして使用しないでください。\n注意※<UNK>用中のマスクに直接スプレーしないでください\n抗菌成分\n柿渋エキス\nMIS(特許取得)\n環境をつくる新発想\n●安全性にとことん\nこだわった抗菌剤\n効果持続\n界面活性剤フリー\nアルコールフリー\n適量(1~2プッシュ)をスプレーした後、軽くもみこんでなじませてください。\n24時間抗菌\n※",
"record": {
"answer": "4プッシュ",
"evidence": [
"bbox-0021",
"bbox-0038"
],
"fields": {
"date": {
"polygon_ids": [],
"value": null
},
"line_items": [],
"receipt_id": {
"polygon_ids": [],
"value": null
},
"store_address": {
"polygon_ids": [],
"value": null
},
"store_name": {
"polygon_ids": [],
"value": null
},
"tax_amount": {
"polygon_ids": [],
"value": null
},
"time": {
"polygon_ids": [],
"value": null
},
"total_amount": {
"polygon_ids": [],
"value": null
}
},
"filename": "0001.jpg",
"image_id": "0001",
"polygons": [
{
"direction": null,
"polygon": [
[
546.05,
1.32
],
[
899.32,
2
],
[
895.68,
40.68
],
[
542.42,
36
]
],
"polygon_id": "bbox-0001",
"text": "抗菌消臭防臭"
},
{
"direction": null,
"polygon": [
[
401,
53
],
[
963,
62
],
[
962,
116
],
[
400,
107
]
],
"polygon_id": "bbox-0002",
"text": "マスクの消臭・抗菌スプレー"
},
{
"direction": null,
"polygon": [
[
91,
136
],
[
549,
145
],
[
548,
181
],
[
90,
172
]
],
"polygon_id": "bbox-0003",
"text": "¥マスクにスプレーするだけで/"
},
{
"direction": null,
"polygon": [
[
86.32,
177.05
],
[
799.95,
184.74
],
[
796.32,
246.63
],
[
82.68,
238.95
]
],
"polygon_id": "bbox-0004",
"text": "ウイルス・菌・ニオイを24時間制御!"
},
{
"direction": null,
"polygon": [
[
89,
261
],
[
137,
258
],
[
143,
369.95
],
[
95,
372.95
]
],
"polygon_id": "bbox-0005",
"text": "W効果"
},
{
"direction": null,
"polygon": [
[
181.53,
255.11
],
[
316.74,
258.42
],
[
315.42,
300.26
],
[
180.21,
296.95
]
],
"polygon_id": "bbox-0006",
"text": "消臭成分"
},
{
"direction": null,
"polygon": [
[
625,
270
],
[
717,
268
],
[
717,
292.63
],
[
625,
294.63
]
],
"polygon_id": "bbox-0007",
"text": "抗菌成分"
},
{
"direction": null,
"polygon": [
[
619.74,
298
],
[
815.95,
299.68
],
[
816.26,
341.63
],
[
620.05,
339.95
]
],
"polygon_id": "bbox-0008",
"text": "MISとは?"
},
{
"direction": null,
"polygon": [
[
852.37,
167.68
],
[
959.58,
168.68
],
[
959.58,
211
],
[
852.37,
210
]
],
"polygon_id": "bbox-0009",
"text": "特許"
},
{
"direction": null,
"polygon": [
[
848,
216
],
[
961,
217
],
[
961,
250
],
[
848,
249
]
],
"polygon_id": "bbox-0010",
"text": "取得清"
},
{
"direction": null,
"polygon": [
[
852.89,
253.17
],
[
966.58,
253.06
],
[
961.87,
277.66
],
[
853.83,
278.72
]
],
"polygon_id": "bbox-0011",
"text": "第6125400号"
},
{
"direction": null,
"polygon": [
[
610.83,
371.11
],
[
940,
366.11
],
[
938.28,
404.87
],
[
611,
408.92
]
],
"polygon_id": "bbox-0012",
"text": "●菌が”生きられない”"
},
{
"direction": null,
"polygon": [
[
232.06,
407.23
],
[
389.06,
409.23
],
[
390,
438.72
],
[
233,
436.72
]
],
"polygon_id": "bbox-0013",
"text": "お子様にも安心"
},
{
"direction": null,
"polygon": [
[
114,
435.17
],
[
174,
435.17
],
[
174.94,
484.72
],
[
114.94,
484.72
]
],
"polygon_id": "bbox-0014",
"text": "24"
},
{
"direction": null,
"polygon": [
[
98,
515.23
],
[
200.11,
515.28
],
[
200.11,
548.87
],
[
99.89,
548.81
]
],
"polygon_id": "bbox-0015",
"text": "24時間"
},
{
"direction": null,
"polygon": [
[
436,
520
],
[
574.6,
520.94
],
[
574.6,
548.94
],
[
436,
548
]
],
"polygon_id": "bbox-0016",
"text": "ミントの香りで"
},
{
"direction": null,
"polygon": [
[
446.11,
551.23
],
[
562.77,
551.23
],
[
559,
581.72
],
[
445.17,
581.72
]
],
"polygon_id": "bbox-0017",
"text": "リフレッシュ"
},
{
"direction": null,
"polygon": [
[
616.34,
558.06
],
[
937.66,
551.11
],
[
940.49,
575.83
],
[
619.17,
582.77
]
],
"polygon_id": "bbox-0018",
"text": "第三者による各種試験データ取得済み"
},
{
"direction": null,
"polygon": [
[
484.28,
613.11
],
[
979,
606.11
],
[
977.11,
629.77
],
[
482.4,
636.77
]
],
"polygon_id": "bbox-0019",
"text": "※全てのウイルス・菌・ニオイに効果があるわけではありません。"
},
{
"direction": null,
"polygon": [
[
120,
626.17
],
[
238.83,
626.17
],
[
238.83,
656.83
],
[
120,
656.83
]
],
"polygon_id": "bbox-0020",
"text": "使用方法"
},
{
"direction": null,
"polygon": [
[
86,
664.06
],
[
969.6,
662.06
],
[
965.83,
694.64
],
[
82.23,
696.64
]
],
"polygon_id": "bbox-0021",
"text": "容器を軽く振り、キャップを外して、マスクの内側・外側それぞれに約10cm離して"
},
{
"direction": null,
"polygon": [
[
316.11,
751.23
],
[
388.83,
751.23
],
[
388.83,
775.77
],
[
316.11,
775.77
]
],
"polygon_id": "bbox-0022",
"text": "外側に"
},
{
"direction": null,
"polygon": [
[
598.17,
748.28
],
[
670.77,
748.28
],
[
672.66,
774.77
],
[
600.06,
774.77
]
],
"polygon_id": "bbox-0023",
"text": "内側に"
},
{
"direction": null,
"polygon": [
[
111,
948
],
[
673,
940
],
[
673,
965.83
],
[
111,
973.83
]
],
"polygon_id": "bbox-0024",
"text": "*使用開始時、数回の空押しが必要な場合があります。"
},
{
"direction": null,
"polygon": [
[
112,
973.06
],
[
792,
966.06
],
[
792,
992.83
],
[
112,
999.83
]
],
"polygon_id": "bbox-0025",
"text": "*スプレーしてなじませた後、よく乾かしてから使用してください。"
},
{
"direction": null,
"polygon": [
[
112,
998.06
],
[
950,
994.06
],
[
950,
1023.72
],
[
112,
1027.72
]
],
"polygon_id": "bbox-0026",
"text": "*色落ちやシミが気になるものは、目立たない箇所で試してから使用してください。"
},
{
"direction": null,
"polygon": [
[
112,
1029
],
[
484.55,
1022
],
[
484.55,
1048.77
],
[
112,
1055.77
]
],
"polygon_id": "bbox-0027",
"text": "*逆さにして使用しないでください。"
},
{
"direction": null,
"polygon": [
[
171.58,
1066.83
],
[
796.72,
1063.06
],
[
796.72,
1080.89
],
[
171.58,
1084.66
]
],
"polygon_id": "bbox-0028",
"text": "注意※<UNK>用中のマスクに直接スプレーしないでください"
},
{
"direction": null,
"polygon": [
[
390.13,
261.25
],
[
515.13,
261.25
],
[
515.13,
303.35
],
[
390.13,
303.35
]
],
"polygon_id": "bbox-0029",
"text": "抗菌成分"
},
{
"direction": null,
"polygon": [
[
171.71,
305.98
],
[
329.61,
305.98
],
[
329.61,
346.77
],
[
171.71,
346.77
]
],
"polygon_id": "bbox-0030",
"text": "柿渋エキス"
},
{
"direction": null,
"polygon": [
[
365.13,
309.93
],
[
550.66,
309.93
],
[
550.66,
350.72
],
[
365.13,
350.72
]
],
"polygon_id": "bbox-0031",
"text": "MIS(特許取得)"
},
{
"direction": null,
"polygon": [
[
643.87,
411.84
],
[
943.87,
411.84
],
[
943.87,
449.57
],
[
643.87,
449.57
]
],
"polygon_id": "bbox-0032",
"text": "環境をつくる新発想"
},
{
"direction": null,
"polygon": [
[
613.68,
461.84
],
[
905.19,
461.84
],
[
906.13,
500.52
],
[
614.62,
500.52
]
],
"polygon_id": "bbox-0033",
"text": "●安全性にとことん"
},
{
"direction": null,
"polygon": [
[
643.87,
504.29
],
[
911.79,
504.29
],
[
910.85,
542.03
],
[
642.92,
542.03
]
],
"polygon_id": "bbox-0034",
"text": "こだわった抗菌剤"
},
{
"direction": null,
"polygon": [
[
97.64,
549.57
],
[
201.42,
549.57
],
[
201.42,
582.59
],
[
97.64,
582.59
]
],
"polygon_id": "bbox-0035",
"text": "効果持続"
},
{
"direction": null,
"polygon": [
[
234.43,
518.44
],
[
398.58,
518.44
],
[
398.58,
550.52
],
[
234.43,
550.52
]
],
"polygon_id": "bbox-0036",
"text": "界面活性剤フリー"
},
{
"direction": null,
"polygon": [
[
226.89,
551.46
],
[
405.19,
551.46
],
[
405.19,
582.59
],
[
226.89,
582.59
]
],
"polygon_id": "bbox-0037",
"text": "アルコールフリー"
},
{
"direction": null,
"polygon": [
[
89.15,
698.63
],
[
928.77,
698.63
],
[
927.83,
727.87
],
[
88.21,
727.87
]
],
"polygon_id": "bbox-0038",
"text": "適量(1~2プッシュ)をスプレーした後、軽くもみこんでなじませてください。"
},
{
"direction": null,
"polygon": [
[
721.74,
740.61
],
[
903.68,
740.61
],
[
903.68,
776.73
],
[
721.74,
776.73
]
],
"polygon_id": "bbox-0039",
"text": "24時間抗菌"
},
{
"direction": null,
"polygon": [
[
785.36,
177.09
],
[
801.02,
177.09
],
[
801.02,
194.56
],
[
785.36,
194.56
]
],
"polygon_id": "bbox-0040",
"text": "※"
}
],
"question": "本製品はマスクの外側と内側に最大何プッシュする必要があるでしょうか?",
"subset": "board_vqa",
"tool": null,
"writer_id": null
},
"source": {
"dataset": "llm-jp/jawildtext",
"globalRowIndex": 0,
"repositoryRevision": "627ca7ea7c224ffe1accff8737991fc2240784fa",
"rowGroup": 0,
"rowIndex": 0,
"split": "train",
"upstreamId": "0001"
}
}
@@ -0,0 +1,656 @@
{
"exactGroundTruth": "ソーシャルアパートメント日野入居者各位\n給水設備点検に伴う\n断水のお知らせ\n啓時下ますますご清祥の段、お喜び申し上げます。\nは当社の管理業務につきまして、ご理解ご協力を、誠に有難うございます。\n記\n清掃日:6月12日金曜日\n断水時間:13時00分~16時00分\n※作業開始は、12時30分頃からとなります。\n(注意)断水後、はじめて水を使用する場合\n1、飲料水及び消火用として、バケツ・浴槽などに汲み置きをして下さい。\n敬具\n2.断水時間中でも、作業が終了次第通水する事がありますので、蛇口は必ず閉めてくだ\n3、断水後の再運転の時は、最初に洗面又は浴室などの蛇口を使用し、台所・トイレはスト\n4、通水の際、赤水、濁り水が出ましてもそのまま放水してください。その後、清水に戻りま\n建物管理会社:(株)ビケンテクノ\n03-5789-2933\nこの度、当建物で給水設備の清掃及び点検を下記の日程で実施致します。\n中は断水となりますことでご入居者の皆様方には、大変ご迷惑•ご不便を\nけ致しますが、ご協力の下さいますようお願い申し上げます。\nさい。\nレーナのゴミ詰まりによる給水不良の原因となりますので、必ず最後に出すようにして\n下さい。\nす。\n施工会社:日本設備保全(株)\n048-483-1427",
"record": {
"answer": "3時間",
"evidence": [
"bbox-0001",
"bbox-0008"
],
"fields": {
"date": {
"polygon_ids": [],
"value": null
},
"line_items": [],
"receipt_id": {
"polygon_ids": [],
"value": null
},
"store_address": {
"polygon_ids": [],
"value": null
},
"store_name": {
"polygon_ids": [],
"value": null
},
"tax_amount": {
"polygon_ids": [],
"value": null
},
"time": {
"polygon_ids": [],
"value": null
},
"total_amount": {
"polygon_ids": [],
"value": null
}
},
"filename": "0049.jpg",
"image_id": "0049",
"polygons": [
{
"direction": null,
"polygon": [
[
0,
571
],
[
1710,
509
],
[
1713,
604
],
[
0,
666
]
],
"polygon_id": "bbox-0001",
"text": "ソーシャルアパートメント日野入居者各位"
},
{
"direction": null,
"polygon": [
[
451,
837
],
[
1485,
813
],
[
1487,
933
],
[
454,
957
]
],
"polygon_id": "bbox-0002",
"text": "給水設備点検に伴う"
},
{
"direction": null,
"polygon": [
[
580,
1010
],
[
1369,
991
],
[
1371,
1100
],
[
583,
1119
]
],
"polygon_id": "bbox-0003",
"text": "断水のお知らせ"
},
{
"direction": null,
"polygon": [
[
0,
1238
],
[
1370,
1213
],
[
1371,
1270
],
[
0,
1295
]
],
"polygon_id": "bbox-0004",
"text": "啓時下ますますご清祥の段、お喜び申し上げます。"
},
{
"direction": null,
"polygon": [
[
0,
1310
],
[
1968,
1269
],
[
1974,
1348.82
],
[
0,
1383.29
]
],
"polygon_id": "bbox-0005",
"text": "は当社の管理業務につきまして、ご理解ご協力を、誠に有難うございます。"
},
{
"direction": null,
"polygon": [
[
952,
1717
],
[
1039,
1717
],
[
1039,
1785
],
[
952,
1785
]
],
"polygon_id": "bbox-0006",
"text": "記"
},
{
"direction": null,
"polygon": [
[
468,
1866
],
[
1517,
1846
],
[
1518,
1927
],
[
470,
1948
]
],
"polygon_id": "bbox-0007",
"text": "清掃日:6月12日金曜日"
},
{
"direction": null,
"polygon": [
[
194,
1983
],
[
1832,
1961
],
[
1833,
2038
],
[
195,
2060
]
],
"polygon_id": "bbox-0008",
"text": "断水時間:13時00分~16時00分"
},
{
"direction": null,
"polygon": [
[
862,
2074
],
[
1879,
2065
],
[
1879,
2112
],
[
862,
2121
]
],
"polygon_id": "bbox-0009",
"text": "※作業開始は、12時30分頃からとなります。"
},
{
"direction": null,
"polygon": [
[
48,
2214
],
[
1040,
2198
],
[
1041,
2246
],
[
49,
2262
]
],
"polygon_id": "bbox-0010",
"text": "(注意)断水後、はじめて水を使用する場合"
},
{
"direction": null,
"polygon": [
[
54,
2273
],
[
1644,
2260
],
[
1644,
2308
],
[
54,
2321
]
],
"polygon_id": "bbox-0011",
"text": "1、飲料水及び消火用として、バケツ・浴槽などに汲み置きをして下さい。"
},
{
"direction": null,
"polygon": [
[
1974,
1578
],
[
2089,
1577
],
[
2089,
1626
],
[
1974,
1627
]
],
"polygon_id": "bbox-0012",
"text": "敬具"
},
{
"direction": null,
"polygon": [
[
56.46,
2320.61
],
[
2044,
2305.93
],
[
2049.54,
2385.1
],
[
62,
2393.24
]
],
"polygon_id": "bbox-0013",
"text": "2.断水時間中でも、作業が終了次第通水する事がありますので、蛇口は必ず閉めてくだ"
},
{
"direction": null,
"polygon": [
[
82,
2447
],
[
2046.5,
2441.5
],
[
2049.33,
2503.18
],
[
65,
2514.35
]
],
"polygon_id": "bbox-0014",
"text": "3、断水後の再運転の時は、最初に洗面又は浴室などの蛇口を使用し、台所・トイレはスト"
},
{
"direction": null,
"polygon": [
[
99.34,
2629.31
],
[
2033.17,
2628
],
[
2038.5,
2683.36
],
[
99,
2696
]
],
"polygon_id": "bbox-0015",
"text": "4、通水の際、赤水、濁り水が出ましてもそのまま放水してください。その後、清水に戻りま"
},
{
"direction": null,
"polygon": [
[
1118,
2844
],
[
1935,
2833
],
[
1936,
2885
],
[
1119,
2896
]
],
"polygon_id": "bbox-0016",
"text": "建物管理会社:(株)ビケンテクノ"
},
{
"direction": null,
"polygon": [
[
1576.46,
2906
],
[
2010.17,
2893.5
],
[
2005.67,
2947.18
],
[
1572.96,
2959.68
]
],
"polygon_id": "bbox-0017",
"text": "03-5789-2933"
},
{
"direction": null,
"polygon": [
[
-43.57,
1367.21
],
[
1858.63,
1354.14
],
[
1878.24,
1419.51
],
[
-10.88,
1452.19
]
],
"polygon_id": "bbox-0018",
"text": "この度、当建物で給水設備の清掃及び点検を下記の日程で実施致します。"
},
{
"direction": null,
"polygon": [
[
-4.35,
1458.73
],
[
1956.68,
1426.04
],
[
1956.68,
1497.95
],
[
-4.35,
1543.7
]
],
"polygon_id": "bbox-0019",
"text": "中は断水となりますことでご入居者の皆様方には、大変ご迷惑•ご不便を"
},
{
"direction": null,
"polygon": [
[
2.19,
1530.63
],
[
8.73,
1609.07
],
[
1616.77,
1589.46
],
[
1623.31,
1504.48
]
],
"polygon_id": "bbox-0020",
"text": "け致しますが、ご協力の下さいますようお願い申し上げます。"
},
{
"direction": null,
"polygon": [
[
139.46,
2393.48
],
[
132.92,
2445.78
],
[
250.59,
2445.78
],
[
250.59,
2393.48
]
],
"polygon_id": "bbox-0021",
"text": "さい。"
},
{
"direction": null,
"polygon": [
[
138.81,
2525.28
],
[
144.48,
2573.44
],
[
2037.87,
2562.1
],
[
2040.71,
2511.11
]
],
"polygon_id": "bbox-0022",
"text": "レーナのゴミ詰まりによる給水不良の原因となりますので、必ず最後に出すようにして"
},
{
"direction": null,
"polygon": [
[
167.14,
2581.94
],
[
167.14,
2621.6
],
[
325.79,
2627.26
],
[
322.96,
2584.77
]
],
"polygon_id": "bbox-0023",
"text": "下さい。"
},
{
"direction": null,
"polygon": [
[
172.81,
2698.09
],
[
167.14,
2737.75
],
[
252.13,
2737.75
],
[
252.13,
2695.26
]
],
"polygon_id": "bbox-0024",
"text": "す。"
},
{
"direction": null,
"polygon": [
[
1246.78,
2974.71
],
[
1242.83,
3030.05
],
[
2005.73,
3014.24
],
[
2009.68,
2954.95
]
],
"polygon_id": "bbox-0025",
"text": "施工会社:日本設備保全(株)"
},
{
"direction": null,
"polygon": [
[
1578.82,
3037.96
],
[
1586.73,
3089.35
],
[
1997.83,
3077.49
],
[
1989.92,
3026.1
]
],
"polygon_id": "bbox-0026",
"text": "048-483-1427"
}
],
"question": "このアパートで断水される時間は何時間でしょう?",
"subset": "board_vqa",
"tool": null,
"writer_id": null
},
"source": {
"dataset": "llm-jp/jawildtext",
"globalRowIndex": 57,
"repositoryRevision": "627ca7ea7c224ffe1accff8737991fc2240784fa",
"rowGroup": 1,
"rowIndex": 19,
"split": "train",
"upstreamId": "0049"
}
}
@@ -0,0 +1,150 @@
{
"exactGroundTruth": "葛西城復元図\n今までの発掘成果を基に書き起こしたもので、葛西城の占地している微高地\nの東側には中川、西側には湿地があり、自然の地の利を活かした縄張りを行っ\nっていた。本丸をはじめとする郭は、水堀と土塁によって防御されていた。",
"record": {
"answer": "湿地",
"evidence": [
"bbox-0002",
"bbox-0003"
],
"fields": {
"date": {
"polygon_ids": [],
"value": null
},
"line_items": [],
"receipt_id": {
"polygon_ids": [],
"value": null
},
"store_address": {
"polygon_ids": [],
"value": null
},
"store_name": {
"polygon_ids": [],
"value": null
},
"tax_amount": {
"polygon_ids": [],
"value": null
},
"time": {
"polygon_ids": [],
"value": null
},
"total_amount": {
"polygon_ids": [],
"value": null
}
},
"filename": "0127.jpg",
"image_id": "0127",
"polygons": [
{
"direction": null,
"polygon": [
[
973,
739
],
[
3163,
749
],
[
3162,
1008
],
[
972,
998
]
],
"polygon_id": "bbox-0001",
"text": "葛西城復元図"
},
{
"direction": null,
"polygon": [
[
906,
2342
],
[
3224.84,
2342
],
[
3236.68,
2414.7
],
[
902.05,
2410.75
]
],
"polygon_id": "bbox-0002",
"text": "今までの発掘成果を基に書き起こしたもので、葛西城の占地している微高地"
},
{
"direction": null,
"polygon": [
[
898.62,
2447.13
],
[
3227.42,
2447.13
],
[
3227.42,
2514.23
],
[
898.62,
2514.23
]
],
"polygon_id": "bbox-0003",
"text": "の東側には中川、西側には湿地があり、自然の地の利を活かした縄張りを行っ"
},
{
"direction": null,
"polygon": [
[
898.62,
2557.64
],
[
3156.37,
2549.75
],
[
3203.74,
2624.75
],
[
898.62,
2624.75
]
],
"polygon_id": "bbox-0004",
"text": "っていた。本丸をはじめとする郭は、水堀と土塁によって防御されていた。"
}
],
"question": "中川から微高地を挟んで反対側には何があるでしょう?",
"subset": "board_vqa",
"tool": null,
"writer_id": null
},
"source": {
"dataset": "llm-jp/jawildtext",
"globalRowIndex": 126,
"repositoryRevision": "627ca7ea7c224ffe1accff8737991fc2240784fa",
"rowGroup": 3,
"rowIndex": 12,
"split": "train",
"upstreamId": "0127"
}
}
File diff suppressed because it is too large Load Diff