218 lines
4.8 KiB
JSON
218 lines
4.8 KiB
JSON
{
|
|
"cases": [
|
|
{
|
|
"id": "synth_invoice_001",
|
|
"family": "synthetic_invoice",
|
|
"license": "DocQube",
|
|
"source": "public/samples/invoices/synth_invoice_001.pdf",
|
|
"pair": "pdf_xlsx",
|
|
"bars": {
|
|
"cell_match_min": 0.85,
|
|
"prose_tokens": [
|
|
"Invoice",
|
|
"AcmeCorp",
|
|
"Total"
|
|
],
|
|
"text_recall_min": null
|
|
},
|
|
"gt": {
|
|
"grid": [
|
|
[
|
|
"Desc",
|
|
"Qty",
|
|
"Amount"
|
|
],
|
|
[
|
|
"Service",
|
|
"1",
|
|
"100"
|
|
],
|
|
[
|
|
"Tax",
|
|
"1",
|
|
"10"
|
|
]
|
|
],
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "self-gen invoice"
|
|
},
|
|
{
|
|
"id": "synth_table_001",
|
|
"family": "pubtabnet",
|
|
"license": "DocQube",
|
|
"source": "public/samples/pubtab/synth_table_001.pdf",
|
|
"pair": "pdf_xlsx",
|
|
"bars": {
|
|
"cell_match_min": 0.9,
|
|
"prose_tokens": [],
|
|
"text_recall_min": null
|
|
},
|
|
"gt": {
|
|
"grid": [
|
|
[
|
|
"Item",
|
|
"Qty",
|
|
"Price"
|
|
],
|
|
[
|
|
"Widget",
|
|
"2",
|
|
"10"
|
|
],
|
|
[
|
|
"Gadget",
|
|
"1",
|
|
"25"
|
|
]
|
|
],
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "self-gen stand-in for PubTabNet until fetch"
|
|
},
|
|
{
|
|
"id": "synth_digital_001",
|
|
"family": "doclaynet",
|
|
"license": "DocQube",
|
|
"source": "public/samples/doclaynet/synth_digital_001.pdf",
|
|
"pair": "pdf_docx",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [],
|
|
"text_recall_min": 0.95
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"expected_tokens": [
|
|
"Digital",
|
|
"Report",
|
|
"AlphaBridge"
|
|
],
|
|
"notes": "self-gen digital layout stand-in"
|
|
},
|
|
{
|
|
"id": "synth_multicol_001",
|
|
"family": "doclaynet",
|
|
"license": "DocQube",
|
|
"source": "public/samples/doclaynet/synth_multicol_001.pdf",
|
|
"pair": "pdf_docx",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [],
|
|
"text_recall_min": 0.8
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"expected_tokens": [
|
|
"ColumnLeftOne",
|
|
"ColumnRightOne"
|
|
],
|
|
"notes": "two-column reading-order stress"
|
|
},
|
|
{
|
|
"id": "path_a_docx",
|
|
"family": "path_a",
|
|
"license": "DocQube",
|
|
"source": "public/samples/path_a/path_a_sample.docx",
|
|
"pair": "docx_pdf",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [
|
|
"PathAParagraphToken"
|
|
],
|
|
"text_recall_min": null
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "DOCX\u2192PDF Path A"
|
|
},
|
|
{
|
|
"id": "path_a_xlsx",
|
|
"family": "path_a",
|
|
"license": "DocQube",
|
|
"source": "public/samples/path_a/path_a_sample.xlsx",
|
|
"pair": "xlsx_pdf",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [
|
|
"HeaderA",
|
|
"CellAlpha"
|
|
],
|
|
"text_recall_min": null
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "XLSX\u2192PDF Path A"
|
|
},
|
|
{
|
|
"id": "images_png_pdf",
|
|
"family": "images",
|
|
"license": "DocQube",
|
|
"source": "public/samples/images/smoke.png",
|
|
"pair": "png_pdf",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [],
|
|
"text_recall_min": null
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "PNG\u2192PDF"
|
|
},
|
|
{
|
|
"id": "cord_placeholder",
|
|
"family": "cord",
|
|
"license": "CC-BY-4.0",
|
|
"source": "public/samples/cord/.gitkeep",
|
|
"pair": "pdf_txt",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [],
|
|
"text_recall_min": 0.5
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "placeholder until fetch_public_eval.py",
|
|
"optional": true
|
|
},
|
|
{
|
|
"id": "sroie_placeholder",
|
|
"family": "sroie",
|
|
"license": "CC-BY-4.0",
|
|
"source": "public/samples/sroie/.gitkeep",
|
|
"pair": "pdf_txt",
|
|
"bars": {
|
|
"cell_match_min": null,
|
|
"prose_tokens": [],
|
|
"text_recall_min": 0.5
|
|
},
|
|
"gt": {
|
|
"grid": null,
|
|
"text_file": null,
|
|
"regions_coco": null
|
|
},
|
|
"notes": "placeholder until fetch_public_eval.py",
|
|
"optional": true
|
|
}
|
|
]
|
|
} |