Files
SnapOtter/tests/fixtures/ocr-real/annotations/jawildtext-board-0127.json
T
SnapOtterandGitHub 991c981529 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
2026-07-15 03:34:24 +08:00

151 lines
3.3 KiB
JSON

{
"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"
}
}