ERP-DocIQ / backend /evals /report.json
kenmandal's picture
Deploy latest: ERP DocIQ NLQ chatbot + reasoning models (MiniCPM3-4B/Command R7B) + ERP fine-tuning + extreme OCR docs
082d661 verified
Raw
History Blame Contribute Delete
24.9 kB
{
"aggregate": {
"overall": {
"documents": 13,
"exact_match": 0.932,
"field_f1": 0.938,
"line_item_f1": 0.667,
"financial_consistency_rate": 1.0,
"doc_type_accuracy": 1.0
},
"by_type": {
"contract": {
"documents": 2,
"exact_match": 0.818,
"field_f1": 0.856,
"financial_consistency_rate": 1.0
},
"invoice": {
"documents": 5,
"exact_match": 1.0,
"field_f1": 1.0,
"financial_consistency_rate": 1.0
},
"purchase_order": {
"documents": 2,
"exact_match": 0.863,
"field_f1": 0.925,
"financial_consistency_rate": 1.0
},
"receipt": {
"documents": 2,
"exact_match": 1.0,
"field_f1": 1.0,
"financial_consistency_rate": 1.0
},
"subscription_memo": {
"documents": 2,
"exact_match": 0.875,
"field_f1": 0.817,
"financial_consistency_rate": 1.0
}
},
"by_difficulty": {
"standard": {
"documents": 10,
"exact_match": 0.911,
"field_f1": 0.92,
"financial_consistency_rate": 1.0
},
"dense_table": {
"documents": 1,
"exact_match": 1.0,
"field_f1": 1.0,
"financial_consistency_rate": 1.0
},
"multicurrency": {
"documents": 1,
"exact_match": 1.0,
"field_f1": 1.0,
"financial_consistency_rate": 1.0
},
"missing_fields": {
"documents": 1,
"exact_match": 1.0,
"field_f1": 1.0,
"financial_consistency_rate": 1.0
}
}
},
"documents": [
{
"doc_id": "contract_msa_digital",
"predicted_type": "contract",
"difficulty": "standard",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "contract",
"exact_match": 0.909,
"field_f1": 0.897,
"precision": 1.0,
"recall": 0.812,
"fields_scored": 11,
"line_item_f1": null,
"line_items_applicable": false,
"financial_consistent": true,
"per_field": {
"contract_number": {
"exact": true,
"pred": "MSA-2026-014",
"gt": "MSA-2026-014"
},
"title": {
"exact": false,
"pred": null,
"gt": "Master Services Agreement"
},
"party_a": {
"exact": true,
"pred": "Acme Industrial Supplies",
"gt": "Acme Industrial Supplies"
},
"party_b": {
"exact": true,
"pred": "Globex Corporation",
"gt": "Globex Corporation"
},
"effective_date": {
"exact": true,
"pred": "2026-01-01",
"gt": "2026-01-01"
},
"expiration_date": {
"exact": true,
"pred": "2027-12-31",
"gt": "2027-12-31"
},
"contract_value": {
"exact": true,
"pred": 250000.0,
"gt": 250000.0
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"governing_law": {
"exact": true,
"pred": "Delaware",
"gt": "Delaware"
},
"auto_renew": {
"exact": true,
"pred": true,
"gt": true
},
"termination_notice_days": {
"exact": true,
"pred": 60,
"gt": 60
}
}
}
},
{
"doc_id": "contract_scanned",
"predicted_type": "contract",
"difficulty": "standard",
"channel": "scanned",
"confidence": 0.8,
"requires_review": true,
"cost_usd": 0.0,
"score": {
"doc_type": "contract",
"exact_match": 0.727,
"field_f1": 0.815,
"precision": 1.0,
"recall": 0.688,
"fields_scored": 11,
"line_item_f1": null,
"line_items_applicable": false,
"financial_consistent": true,
"per_field": {
"contract_number": {
"exact": true,
"pred": "NDA-7781",
"gt": "NDA-7781"
},
"title": {
"exact": false,
"pred": null,
"gt": "Mutual Non-Disclosure Agreement"
},
"party_a": {
"exact": true,
"pred": "Stark Components",
"gt": "Stark Components"
},
"party_b": {
"exact": true,
"pred": "Wayne Enterprises",
"gt": "Wayne Enterprises"
},
"effective_date": {
"exact": true,
"pred": "2026-03-15",
"gt": "2026-03-15"
},
"expiration_date": {
"exact": true,
"pred": "2029-03-14",
"gt": "2029-03-14"
},
"contract_value": {
"exact": false,
"pred": null,
"gt": 0.0
},
"currency": {
"exact": false,
"pred": null,
"gt": "USD"
},
"governing_law": {
"exact": true,
"pred": "New York",
"gt": "New York"
},
"auto_renew": {
"exact": true,
"pred": false,
"gt": false
},
"termination_notice_days": {
"exact": true,
"pred": 30,
"gt": 30
}
}
}
},
{
"doc_id": "invoice_acme_digital",
"predicted_type": "invoice",
"difficulty": "standard",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "invoice",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 9,
"line_item_f1": 1.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"invoice_number": {
"exact": true,
"pred": "INV-1001",
"gt": "INV-1001"
},
"issue_date": {
"exact": true,
"pred": "2026-07-15",
"gt": "2026-07-15"
},
"due_date": {
"exact": true,
"pred": "2026-08-14",
"gt": "2026-08-14"
},
"vendor_name": {
"exact": true,
"pred": "Acme Industrial Supplies",
"gt": "Acme Industrial Supplies"
},
"bill_to_name": {
"exact": true,
"pred": "Globex Corporation",
"gt": "Globex Corporation"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 300.0,
"gt": 300.0
},
"tax_amount": {
"exact": true,
"pred": 30.0,
"gt": 30.0
},
"total": {
"exact": true,
"pred": 330.0,
"gt": 330.0
}
}
}
},
{
"doc_id": "invoice_dense_table",
"predicted_type": "invoice",
"difficulty": "dense_table",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "invoice",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 9,
"line_item_f1": 1.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"invoice_number": {
"exact": true,
"pred": "INV-9120",
"gt": "INV-9120"
},
"issue_date": {
"exact": true,
"pred": "2026-06-01",
"gt": "2026-06-01"
},
"due_date": {
"exact": true,
"pred": "2026-07-01",
"gt": "2026-07-01"
},
"vendor_name": {
"exact": true,
"pred": "Wayne Enterprises",
"gt": "Wayne Enterprises"
},
"bill_to_name": {
"exact": true,
"pred": "Oscorp",
"gt": "Oscorp"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 2140.0,
"gt": 2140.0
},
"tax_amount": {
"exact": true,
"pred": 214.0,
"gt": 214.0
},
"total": {
"exact": true,
"pred": 2354.0,
"gt": 2354.0
}
}
}
},
{
"doc_id": "invoice_globalparts_eur",
"predicted_type": "invoice",
"difficulty": "multicurrency",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "invoice",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 9,
"line_item_f1": 1.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"invoice_number": {
"exact": true,
"pred": "GP-2026-558",
"gt": "GP-2026-558"
},
"issue_date": {
"exact": true,
"pred": "2026-05-03",
"gt": "2026-05-03"
},
"due_date": {
"exact": true,
"pred": "2026-06-02",
"gt": "2026-06-02"
},
"vendor_name": {
"exact": true,
"pred": "GlobalParts GmbH",
"gt": "GlobalParts GmbH"
},
"bill_to_name": {
"exact": true,
"pred": "Initech LLC",
"gt": "Initech LLC"
},
"currency": {
"exact": true,
"pred": "EUR",
"gt": "EUR"
},
"subtotal": {
"exact": true,
"pred": 1840.0,
"gt": 1840.0
},
"tax_amount": {
"exact": true,
"pred": 349.6,
"gt": 349.6
},
"total": {
"exact": true,
"pred": 2189.6,
"gt": 2189.6
}
}
}
},
{
"doc_id": "invoice_missing_total",
"predicted_type": "invoice",
"difficulty": "missing_fields",
"channel": "digital",
"confidence": 0.72,
"requires_review": true,
"cost_usd": 0.0,
"score": {
"doc_type": "invoice",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 6,
"line_item_f1": 1.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"invoice_number": {
"exact": true,
"pred": "INV-3300",
"gt": "INV-3300"
},
"issue_date": {
"exact": true,
"pred": "2026-02-10",
"gt": "2026-02-10"
},
"vendor_name": {
"exact": true,
"pred": "Stark Components",
"gt": "Stark Components"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 1200.0,
"gt": 1200.0
},
"tax_amount": {
"exact": true,
"pred": 96.0,
"gt": 96.0
}
}
}
},
{
"doc_id": "invoice_scanned_basic",
"predicted_type": "invoice",
"difficulty": "standard",
"channel": "scanned",
"confidence": 0.8,
"requires_review": true,
"cost_usd": 0.0,
"score": {
"doc_type": "invoice",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 9,
"line_item_f1": 0.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"invoice_number": {
"exact": true,
"pred": "INV-7741",
"gt": "INV-7741"
},
"issue_date": {
"exact": true,
"pred": "2026-03-22",
"gt": "2026-03-22"
},
"due_date": {
"exact": true,
"pred": "2026-04-21",
"gt": "2026-04-21"
},
"vendor_name": {
"exact": true,
"pred": "Northwind Traders",
"gt": "Northwind Traders"
},
"bill_to_name": {
"exact": true,
"pred": "Contoso Ltd",
"gt": "Contoso Ltd"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 540.0,
"gt": 540.0
},
"tax_amount": {
"exact": true,
"pred": 43.2,
"gt": 43.2
},
"total": {
"exact": true,
"pred": 583.2,
"gt": 583.2
}
}
}
},
{
"doc_id": "po_acme_digital",
"predicted_type": "purchase_order",
"difficulty": "standard",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "purchase_order",
"exact_match": 0.909,
"field_f1": 0.941,
"precision": 0.941,
"recall": 0.941,
"fields_scored": 11,
"line_item_f1": 1.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"order_number": {
"exact": false,
"pred": "Purchase",
"gt": "PO-100481"
},
"order_date": {
"exact": true,
"pred": "2026-07-02",
"gt": "2026-07-02"
},
"delivery_date": {
"exact": true,
"pred": "2026-07-20",
"gt": "2026-07-20"
},
"vendor_name": {
"exact": true,
"pred": "Acme Industrial",
"gt": "Acme Industrial"
},
"buyer_name": {
"exact": true,
"pred": "Globex Procurement",
"gt": "Globex Procurement"
},
"ship_to": {
"exact": true,
"pred": "12 Industrial Way, Springfield",
"gt": "12 Industrial Way, Springfield"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 12000.0,
"gt": 12000.0
},
"tax_amount": {
"exact": true,
"pred": 450.0,
"gt": 450.0
},
"total": {
"exact": true,
"pred": 12450.0,
"gt": 12450.0
},
"payment_terms": {
"exact": true,
"pred": "Net 30",
"gt": "Net 30"
}
}
}
},
{
"doc_id": "po_scanned",
"predicted_type": "purchase_order",
"difficulty": "standard",
"channel": "scanned",
"confidence": 0.52,
"requires_review": true,
"cost_usd": 0.0,
"score": {
"doc_type": "purchase_order",
"exact_match": 0.818,
"field_f1": 0.909,
"precision": 0.938,
"recall": 0.882,
"fields_scored": 11,
"line_item_f1": 0.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"order_number": {
"exact": false,
"pred": "Purchase",
"gt": "PO-100483"
},
"order_date": {
"exact": true,
"pred": "2026-04-11",
"gt": "2026-04-11"
},
"delivery_date": {
"exact": true,
"pred": "2026-05-01",
"gt": "2026-05-01"
},
"vendor_name": {
"exact": true,
"pred": "Initech Supplies",
"gt": "Initech Supplies"
},
"buyer_name": {
"exact": true,
"pred": "Contoso Ops",
"gt": "Contoso Ops"
},
"ship_to": {
"exact": true,
"pred": "9 Market St, Metropolis",
"gt": "9 Market St, Metropolis"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 900.0,
"gt": 900.0
},
"tax_amount": {
"exact": true,
"pred": 80.0,
"gt": 80.0
},
"total": {
"exact": false,
"pred": null,
"gt": 980.0
},
"payment_terms": {
"exact": true,
"pred": "Net 15",
"gt": "Net 15"
}
}
}
},
{
"doc_id": "receipt_digital",
"predicted_type": "receipt",
"difficulty": "standard",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "receipt",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 7,
"line_item_f1": 1.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"merchant": {
"exact": true,
"pred": "City Hardware",
"gt": "City Hardware"
},
"date": {
"exact": true,
"pred": "2026-06-18",
"gt": "2026-06-18"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 47.0,
"gt": 47.0
},
"tax_amount": {
"exact": true,
"pred": 3.76,
"gt": 3.76
},
"total": {
"exact": true,
"pred": 50.76,
"gt": 50.76
},
"payment_method": {
"exact": true,
"pred": "Visa card ending 4242",
"gt": "Visa card ending 4242"
}
}
}
},
{
"doc_id": "receipt_scanned",
"predicted_type": "receipt",
"difficulty": "standard",
"channel": "scanned",
"confidence": 0.8,
"requires_review": true,
"cost_usd": 0.0,
"score": {
"doc_type": "receipt",
"exact_match": 1.0,
"field_f1": 1.0,
"precision": 1.0,
"recall": 1.0,
"fields_scored": 7,
"line_item_f1": 0.0,
"line_items_applicable": true,
"financial_consistent": true,
"per_field": {
"merchant": {
"exact": true,
"pred": "QuickMart",
"gt": "QuickMart"
},
"date": {
"exact": true,
"pred": "2026-05-30",
"gt": "2026-05-30"
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"subtotal": {
"exact": true,
"pred": 23.5,
"gt": 23.5
},
"tax_amount": {
"exact": true,
"pred": 1.88,
"gt": 1.88
},
"total": {
"exact": true,
"pred": 25.38,
"gt": 25.38
},
"payment_method": {
"exact": true,
"pred": "Cash",
"gt": "Cash"
}
}
}
},
{
"doc_id": "subscription_memo_pos",
"predicted_type": "subscription_memo",
"difficulty": "standard",
"channel": "digital",
"confidence": 1.0,
"requires_review": false,
"cost_usd": 0.0,
"score": {
"doc_type": "subscription_memo",
"exact_match": 0.917,
"field_f1": 0.875,
"precision": 0.933,
"recall": 0.824,
"fields_scored": 12,
"line_item_f1": null,
"line_items_applicable": false,
"financial_consistent": true,
"per_field": {
"memo_number": {
"exact": true,
"pred": "SUB-2026-0091",
"gt": "SUB-2026-0091"
},
"subscription_name": {
"exact": false,
"pred": "MEMO",
"gt": "POS Cloud Platform"
},
"vendor_name": {
"exact": true,
"pred": "Initech Supplies",
"gt": "Initech Supplies"
},
"account_id": {
"exact": true,
"pred": "ACC-55821",
"gt": "ACC-55821"
},
"plan": {
"exact": true,
"pred": "Enterprise (500 lanes)",
"gt": "Enterprise (500 lanes)"
},
"billing_cycle": {
"exact": true,
"pred": "annual",
"gt": "annual"
},
"start_date": {
"exact": true,
"pred": "2025-08-01",
"gt": "2025-08-01"
},
"renewal_date": {
"exact": true,
"pred": "2026-08-01",
"gt": "2026-08-01"
},
"amount": {
"exact": true,
"pred": 84000.0,
"gt": 84000.0
},
"currency": {
"exact": true,
"pred": "USD",
"gt": "USD"
},
"auto_renew": {
"exact": true,
"pred": true,
"gt": true
},
"status": {
"exact": true,
"pred": "active",
"gt": "active"
}
}
}
},
{
"doc_id": "subscription_memo_scanned",
"predicted_type": "subscription_memo",
"difficulty": "standard",
"channel": "scanned",
"confidence": 0.8,
"requires_review": true,
"cost_usd": 0.0,
"score": {
"doc_type": "subscription_memo",
"exact_match": 0.833,
"field_f1": 0.759,
"precision": 0.846,
"recall": 0.688,
"fields_scored": 12,
"line_item_f1": null,
"line_items_applicable": false,
"financial_consistent": true,
"per_field": {
"memo_number": {
"exact": true,
"pred": "SUB-2026-0145",
"gt": "SUB-2026-0145"
},
"subscription_name": {
"exact": false,
"pred": "MEMO",
"gt": "Store Wi-Fi & Analytics"
},
"vendor_name": {
"exact": true,
"pred": "GlobalParts GmbH",
"gt": "GlobalParts GmbH"
},
"account_id": {
"exact": true,
"pred": "ACC-77310",
"gt": "ACC-77310"
},
"plan": {
"exact": true,
"pred": "Standard",
"gt": "Standard"
},
"billing_cycle": {
"exact": true,
"pred": "monthly",
"gt": "monthly"
},
"start_date": {
"exact": true,
"pred": "2026-01-15",
"gt": "2026-01-15"
},
"renewal_date": {
"exact": true,
"pred": "2026-07-15",
"gt": "2026-07-15"
},
"amount": {
"exact": true,
"pred": 2500.0,
"gt": 2500.0
},
"currency": {
"exact": true,
"pred": "EUR",
"gt": "EUR"
},
"auto_renew": {
"exact": false,
"pred": true,
"gt": false
},
"status": {
"exact": true,
"pred": "pending",
"gt": "pending"
}
}
}
}
],
"routing_policy": "offline",
"active_tier": "offline"
}