{ "schemaVersion": 1, "dataset": { "id": "synthetic-invoice-review-v1", "kind": "synthetic", "scenarioCount": 16 }, "policy": { "baseline": "Compare supplier_id and the literal invoice_number; validate all supplied records and check amount/currency conflicts.", "normalization": "Candidate ignores ASCII letter case, spaces and hyphens in invoice numbers only. Supplier IDs remain exact. Leading zeros are preserved; zero-only collisions require review.", "matchScope": "Each independent scenario compares its final batch record with the supplied ledger and earlier batch records. Nothing is remembered across scenarios.", "actions": { "humanReviewRequired": true, "automaticApproval": false, "automaticRejection": false, "automaticPayment": false } }, "summary": { "baseline": { "correct": 12, "total": 16, "counts": { "NEEDS_REVIEW": 7, "POSSIBLE_DUPLICATE": 3, "NO_MATCH": 6 } }, "candidate": { "correct": 16, "total": 16, "counts": { "NEEDS_REVIEW": 9, "POSSIBLE_DUPLICATE": 4, "NO_MATCH": 3 } } }, "measurementLimit": "Counts show agreement with manually assigned expectations on 16 deliberately chosen synthetic scenarios, not accuracy on real invoices or evidence of savings.", "cases": [ { "id": "exact-ledger", "title": "Exact copy of a ledger invoice", "expected": "POSSIBLE_DUPLICATE", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true }, "candidate": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "formatting-variation", "title": "Spaces replace the invoice-number hyphen", "expected": "POSSIBLE_DUPLICATE", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": " INV 1042 ", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true }, "candidate": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "normalized_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "letter-case", "title": "Invoice-number letters change case", "expected": "POSSIBLE_DUPLICATE", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "inv-1042", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true }, "candidate": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "normalized_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "different-supplier", "title": "The same invoice number belongs to another supplier", "expected": "NO_MATCH", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-002", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true } }, { "id": "amount-conflict", "title": "The invoice number matches but the amount changes", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "125.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "amount_or_currency_conflict", "explanation": "At least one matching supplier/number reference has a different amount or currency; inspect the source records.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "amount_or_currency_conflict", "explanation": "At least one matching supplier/number reference has a different amount or currency; inspect the source records.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "currency-conflict", "title": "The invoice number matches but the currency changes", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "EUR" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "amount_or_currency_conflict", "explanation": "At least one matching supplier/number reference has a different amount or currency; inspect the source records.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "amount_or_currency_conflict", "explanation": "At least one matching supplier/number reference has a different amount or currency; inspect the source records.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "missing-number", "title": "The extracted invoice number is missing", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "target: missing invoice_number", "target: invoice_number must contain ASCII letters/digits, spaces or hyphens, 1–64 characters" ], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "target: missing invoice_number", "target: invoice_number must contain ASCII letters/digits, spaces or hyphens, 1–64 characters" ], "reviewRequired": true } }, { "id": "invalid-amount", "title": "The amount uses an unsupported decimal separator", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120,00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "target: amount must be a positive decimal string, at most 999999999.99 and two decimal places" ], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "target: amount must be a positive decimal string, at most 999999999.99 and two decimal places" ], "reviewRequired": true } }, { "id": "leading-zero-ambiguity", "title": "Removing leading zeros would create a match", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-001042", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "ambiguous_leading_zeros", "explanation": "A number matches only after removing leading zeros from digit groups. The example does not assume these numbers are equivalent.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "leading_zero_ambiguity", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "earlier-batch-copy", "title": "A duplicate is present earlier in the current batch", "expected": "POSSIBLE_DUPLICATE", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, "ledger": [], "priorBatch": [ { "id": "batch-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ] }, "baseline": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "batch", "id": "batch-1", "basis": "literal_number", "record": { "id": "batch-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true }, "candidate": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "batch", "id": "batch-1", "basis": "literal_number", "record": { "id": "batch-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "new-number", "title": "No matching invoice number exists in the supplied context", "expected": "NO_MATCH", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1043", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true } }, { "id": "repeated-input-id", "title": "The same input record ID appears twice", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, "ledger": [], "priorBatch": [ { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "repeated_record_id", "explanation": "A record ID occurs more than once in the supplied context; check the import before interpreting matches.", "matches": [], "issues": [ "repeated id: incoming-1" ], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "repeated_record_id", "explanation": "A record ID occurs more than once in the supplied context; check the import before interpreting matches.", "matches": [], "issues": [ "repeated id: incoming-1" ], "reviewRequired": true } }, { "id": "mixed-reference-conflict", "title": "An exact match and a formatted match disagree on amount", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, { "id": "ledger-2", "supplier_id": "SUP-001", "invoice_number": "inv 1042", "amount": "125.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "POSSIBLE_DUPLICATE", "reason": "matching_reference", "explanation": "The supplier, compared invoice number, amount and currency match a supplied reference. A person must decide whether this is a duplicate.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "amount_or_currency_conflict", "explanation": "At least one matching supplier/number reference has a different amount or currency; inspect the source records.", "matches": [ { "scope": "ledger", "id": "ledger-1", "basis": "literal_number", "record": { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } }, { "scope": "ledger", "id": "ledger-2", "basis": "normalized_number", "record": { "id": "ledger-2", "supplier_id": "SUP-001", "invoice_number": "inv 1042", "amount": "125.00", "currency": "USD" } } ], "issues": [], "reviewRequired": true } }, { "id": "invalid-reference", "title": "An earlier reference invoice has incomplete data", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "ledger[0]: missing amount", "ledger[0]: amount must be a positive decimal string, at most 999999999.99 and two decimal places" ], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "ledger[0]: missing amount", "ledger[0]: amount must be a positive decimal string, at most 999999999.99 and two decimal places" ], "reviewRequired": true } }, { "id": "distinct-leading-zero-number", "title": "Leading zeros are kept on a genuinely different number", "expected": "NO_MATCH", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-001043", "amount": "120.00", "currency": "USD" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true }, "candidate": { "classification": "NO_MATCH", "reason": "no_reference_match", "explanation": "No reference matches within the supplied ledger and earlier batch under this rule. This is not permission to approve or pay.", "matches": [], "issues": [], "reviewRequired": true } }, { "id": "unsupported-currency", "title": "The invoice currency is outside this example", "expected": "NEEDS_REVIEW", "input": { "target": { "id": "incoming-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "JPY" }, "ledger": [ { "id": "ledger-1", "supplier_id": "SUP-001", "invoice_number": "INV-1042", "amount": "120.00", "currency": "USD" } ], "priorBatch": [] }, "baseline": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "target: currency must be USD, EUR or GBP in this example" ], "reviewRequired": true }, "candidate": { "classification": "NEEDS_REVIEW", "reason": "invalid_input", "explanation": "The target or supplied reference data is incomplete, invalid or outside this example's supported format.", "matches": [], "issues": [ "target: currency must be USD, EUR or GBP in this example" ], "reviewRequired": true } } ] }