{ "schemaVersion": 1, "benchmarkId": "2026-07-19-paddlevl16-v1", "generatorVersion": "2026-07-19.quality-v1", "license": "CC0-1.0", "synthetic": true, "containsPersonalData": false, "generationCommand": "python3 scripts/generate_conversion_quality_dataset.py", "samples": [ { "id": "scanned-purchase-register", "documentType": "scanned-document", "sourceMode": "image-only", "scanQuality": "clean-image-only", "pages": 1, "columns": [ "Entry", "Supplier", "Date", "Category", "Amount USD" ], "rows": [ [ "PR-001", "Northwind Test Supply", "2026-07-03", "Packaging", "425.30" ], [ "PR-002", "Cedar Example Works", "2026-07-08", "Parts", "1180.00" ], [ "PR-003", "Beacon Synthetic Freight", "2026-07-14", "Transport", "690.75" ] ], "sourceFile": "scanned-purchase-register.pdf", "sourcePath": "apps/web/public/samples/document-library/scanned-purchase-register.pdf", "sourceSha256": "f1ff0daadb897d9c3b8ec078da244067c640e8efcd64c4642f958b2f1fb6a64b", "referenceSampleId": "scanned-purchase-register" }, { "id": "multipage-shipment-register", "documentType": "multi-page-table", "sourceMode": "selectable-text", "scanQuality": "digital-selectable-text", "pages": 2, "columns": [ "Shipment", "Origin", "Destination", "Packages", "Gross kg" ], "rows": [ [ "SHP-1001", "Lisbon", "Montreal", "18", "420.0" ], [ "SHP-1002", "Valencia", "Manzanillo", "24", "612.5" ], [ "SHP-1003", "Almaty", "Warsaw", "11", "278.0" ], [ "SHP-1004", "Busan", "Rotterdam", "32", "845.4" ], [ "SHP-1005", "Osaka", "Seattle", "15", "390.2" ], [ "SHP-1006", "Lima", "Madrid", "9", "215.8" ] ], "sourceFile": "multipage-shipment-register.pdf", "sourcePath": "apps/web/public/samples/document-library/multipage-shipment-register.pdf", "sourceSha256": "ac94115066de771a58a2f11e1a7d1982e9d7aa71fa4ec47a78eeddfad20e45ba", "referenceSampleId": "multipage-shipment-register" }, { "id": "bank-statement", "documentType": "bank-statement", "sourceMode": "selectable-text", "scanQuality": "digital-selectable-text", "pages": 1, "columns": [ "Date", "Reference", "Description", "Debit USD", "Credit USD", "Balance USD" ], "rows": [ [ "2026-07-01", "OPEN", "Opening balance", "", "", "8200.00" ], [ "2026-07-04", "TRX-1001", "Synthetic supplier payment", "1250.00", "", "6950.00" ], [ "2026-07-09", "TRX-1002", "Synthetic customer receipt", "", "2100.00", "9050.00" ], [ "2026-07-15", "TRX-1003", "Synthetic freight payment", "735.50", "", "8314.50" ] ], "sourceFile": "bank-statement.pdf", "sourcePath": "apps/web/public/samples/document-library/bank-statement.pdf", "sourceSha256": "028e0cfc6fb1794efc2774049756b2a7040217e034e375402738e884a81d72d7", "referenceSampleId": "bank-statement" }, { "id": "commercial-invoice", "documentType": "invoice", "sourceMode": "selectable-text", "scanQuality": "digital-selectable-text", "pages": 1, "columns": [ "Line", "Description", "HS code", "Quantity", "Unit price USD", "Line total USD" ], "rows": [ [ "1", "Synthetic stainless fastener", "7318.15", "200", "1.25", "250.00" ], [ "2", "Synthetic sealing ring", "4016.93", "100", "0.80", "80.00" ], [ "3", "Synthetic packing insert", "4823.90", "50", "0.50", "25.00" ] ], "sourceFile": "commercial-invoice.pdf", "sourcePath": "apps/web/public/samples/document-library/commercial-invoice.pdf", "sourceSha256": "cb430ae7bad1f4270a9594fb0da0d6eb1792beb9240ca76c8fefa31b1e0af84b", "referenceSampleId": "commercial-invoice" }, { "id": "customs-declaration", "documentType": "customs-declaration", "sourceMode": "selectable-text", "scanQuality": "digital-selectable-text", "pages": 1, "columns": [ "Item", "Commodity", "HS code", "Origin", "Customs value USD", "Gross kg" ], "rows": [ [ "1", "Synthetic machine fittings", "7307.99", "PT", "4800.00", "380.0" ], [ "2", "Synthetic rubber seals", "4016.93", "ES", "1250.00", "95.0" ] ], "sourceFile": "customs-declaration.pdf", "sourcePath": "apps/web/public/samples/document-library/customs-declaration.pdf", "sourceSha256": "f175292f4c1d4d6690a8d075690aac6f3f0bce34d6f5e2bb5e0440bdfe148efe", "referenceSampleId": "customs-declaration" }, { "id": "bill-of-lading", "documentType": "bill-of-lading", "sourceMode": "selectable-text", "scanQuality": "digital-selectable-text", "pages": 1, "columns": [ "Container", "Seal", "Packages", "Description", "Gross kg", "Measurement m3" ], "rows": [ [ "FVTU1234567", "SEAL-TEST-01", "120 cartons", "Synthetic machine parts", "8450.0", "28.5" ], [ "FVTU7654321", "SEAL-TEST-02", "80 cartons", "Synthetic sealing products", "3920.0", "14.2" ] ], "sourceFile": "bill-of-lading.pdf", "sourcePath": "apps/web/public/samples/document-library/bill-of-lading.pdf", "sourceSha256": "ef6fb7ae5124fa916a599064dbada4fcf9e06ac328ec44019b103ceade221c81", "referenceSampleId": "bill-of-lading" }, { "id": "air-waybill", "documentType": "air-waybill", "sourceMode": "selectable-text", "scanQuality": "digital-selectable-text", "pages": 1, "columns": [ "Piece", "Route", "Nature of goods", "Chargeable kg", "Rate USD", "Charge USD" ], "rows": [ [ "1", "MAD-FRA-YUL", "Synthetic instrument parts", "85.0", "4.20", "357.00" ], [ "2", "MAD-FRA-YUL", "Synthetic document pouch", "2.0", "4.20", "8.40" ] ], "sourceFile": "air-waybill.pdf", "sourcePath": "apps/web/public/samples/document-library/air-waybill.pdf", "sourceSha256": "688e5ec34d59919e8417f5ecf1aefeca387ff56a45ae900bbac0b24b2d3a8113", "referenceSampleId": "air-waybill" }, { "id": "scanned-purchase-register-moderate", "documentType": "scanned-document", "sourceMode": "image-only", "scanQuality": "moderate-resampled-skew", "pages": 1, "columns": [ "Entry", "Supplier", "Date", "Category", "Amount USD" ], "rows": [ [ "PR-001", "Northwind Test Supply", "2026-07-03", "Packaging", "425.30" ], [ "PR-002", "Cedar Example Works", "2026-07-08", "Parts", "1180.00" ], [ "PR-003", "Beacon Synthetic Freight", "2026-07-14", "Transport", "690.75" ] ], "sourceFile": "scanned-purchase-register-moderate.pdf", "sourcePath": "apps/web/public/benchmarks/conversion-quality/2026-07-19-paddlevl16-v1/inputs/scanned-purchase-register-moderate.pdf", "sourceSha256": "1e25e088a17299e35529acf23d74de4ee77d920e8031c9fcc81b8577bcf4e418", "referenceSampleId": "scanned-purchase-register" }, { "id": "scanned-purchase-register-poor", "documentType": "scanned-document", "sourceMode": "image-only", "scanQuality": "poor-low-contrast-blur-skew", "pages": 1, "columns": [ "Entry", "Supplier", "Date", "Category", "Amount USD" ], "rows": [ [ "PR-001", "Northwind Test Supply", "2026-07-03", "Packaging", "425.30" ], [ "PR-002", "Cedar Example Works", "2026-07-08", "Parts", "1180.00" ], [ "PR-003", "Beacon Synthetic Freight", "2026-07-14", "Transport", "690.75" ] ], "sourceFile": "scanned-purchase-register-poor.pdf", "sourcePath": "apps/web/public/benchmarks/conversion-quality/2026-07-19-paddlevl16-v1/inputs/scanned-purchase-register-poor.pdf", "sourceSha256": "0cd3f8b273633fad70328d80d0a72fce42e86d65e3a44aae779d0178406905e9", "referenceSampleId": "scanned-purchase-register" }, { "id": "scanned-purchase-register-cropped", "documentType": "scanned-document", "sourceMode": "image-only", "scanQuality": "failure-right-edge-cropped", "pages": 1, "columns": [ "Entry", "Supplier", "Date", "Category", "Amount USD" ], "rows": [ [ "PR-001", "Northwind Test Supply", "2026-07-03", "Packaging", "425.30" ], [ "PR-002", "Cedar Example Works", "2026-07-08", "Parts", "1180.00" ], [ "PR-003", "Beacon Synthetic Freight", "2026-07-14", "Transport", "690.75" ] ], "sourceFile": "scanned-purchase-register-cropped.pdf", "sourcePath": "apps/web/public/benchmarks/conversion-quality/2026-07-19-paddlevl16-v1/inputs/scanned-purchase-register-cropped.pdf", "sourceSha256": "982ebe4c227a628204025e1302140ec7951b45e0e46c7560f0f2196ec49fec61", "referenceSampleId": "scanned-purchase-register" } ] }