Luma Payroll Gym
← Training / SFT + RL, β 0.001
KL β
0.001
Rubric
8
Steps
60 / 60
LR
1e-05
Group size
4-16
Epochs
2
Prompt
v4 interleaved demonstrations, calculate tool
GPU time
3.1h
Training curves, 60 steps

Mean reward

0% 50% 100% Step 0 Step 30 Step 60

KL divergence (k3)

0 0.002 0.004 0.006 Step 0 Step 30 Step 60

Policy entropy

0 0.002 0.004 0.006 Step 0 Step 30 Step 60

Completion length (tokens)

0 100 200 Step 0 Step 30 Step 60

Trap pass rate

0% 50% 100% Step 0 Step 30 Step 60

Payslip pass rate

0% 50% 100% Step 0 Step 30 Step 60

Correct clarifications

0% 50% 100% Step 0 Step 30 Step 60

Calculates through traps

0% 10% 20% 30% Step 0 Step 30 Step 60

Non-tied groups

0% 50% 100% Step 0 Step 30 Step 60
Sampled completions
Step 1
case4-4001-00220 · Calculation
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3043.47", "employee_contribution": "213.04", "allowed_deduction": "0.00", "taxable_pay": "2830.43", "income_tax": "193.04", "net_pay": "2637.39", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3043.47", "employee_contribution": "213.04", "allowed_deduction": "0.00", "taxable_pay": "2830.43", "income_tax": "193.04", "net_pay": "2637.39", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3043.47", "employee_contribution": "243.48", "allowed_deduction": "0.00", "taxable_pay": "2799.99", "income_tax": "252.00", "net_pay": "2547.99", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3043.47", "employee_contribution": "213.04", "allowed_deduction": "0.00", "taxable_pay": "2830.43", "income_tax": "193.04", "net_pay": "2637.39", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00379 · Calculation
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "5267.49", "employee_contribution": "320.00", "allowed_deduction": "0.00", "taxable_pay": "4947.49", "income_tax": "565.50", "net_pay": "4381.99", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "5267.49", "employee_contribution": "320.00", "allowed_deduction": "0.00", "taxable_pay": "4947.49", "income_tax": "565.50", "net_pay": "4381.99", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "5267.49", "employee_contribution": "320.00", "allowed_deduction": "0.00", "taxable_pay": "4947.49", "income_tax": "565.50", "net_pay": "4381.99", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "5267.49", "employee_contribution": "320.00", "allowed_deduction": "0.00", "taxable_pay": "4947.49", "income_tax": "565.50", "net_pay": "4381.99", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00080 · Trap CONFLICTING_GROSS_PAY
100% clarify · scored
{"decision": "clarify", "reason_code": "CONFLICTING_GROSS_PAY", "clauses": ["R7", "R9"], "explanation": "Payroll and contract gross pay differ and no approved amendment resolves it. Please reconcile the records or provide an approved amendment."}
100% clarify · scored
{"decision": "clarify", "reason_code": "CONFLICTING_GROSS_PAY", "clauses": ["R7", "R9"], "explanation": "Payroll and contract gross pay differ and no approved amendment resolves it. Please reconcile the records or provide an approved amendment."}
100% clarify · scored
{"decision": "clarify", "reason_code": "CONFLICTING_GROSS_PAY", "clauses": ["R7", "R9"], "explanation": "Payroll and contract gross pay differ and no approved amendment resolves it. Please reconcile the records or provide an approved amendment."}
100% clarify · scored
{"decision": "clarify", "reason_code": "CONFLICTING_GROSS_PAY", "clauses": ["R7", "R9"], "explanation": "Payroll and contract gross pay differ and no approved amendment resolves it. Please reconcile the records or provide an approved amendment."}
case4-4001-00228 · Trap MISSING_GROSS_PAY
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
Step 30
case4-4001-00348 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3179.10", "employee_contribution": "158.96", "allowed_deduction": "90.34", "taxable_pay": "2929.80", "income_tax": "182.98", "net_pay": "2746.82", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3179.10", "employee_contribution": "158.96", "allowed_deduction": "90.34", "taxable_pay": "2929.80", "income_tax": "182.98", "net_pay": "2746.82", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3179.10", "employee_contribution": "158.96", "allowed_deduction": "90.34", "taxable_pay": "2929.80", "income_tax": "182.98", "net_pay": "2746.82", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3179.10", "employee_contribution": "158.96", "allowed_deduction": "90.34", "taxable_pay": "2929.80", "income_tax": "182.98", "net_pay": "2746.82", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00134 · Calculation
-40% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "7524.49", "employee_contribution": "400.00", "allowed_deduction": "81.68", "taxable_pay": "7042.81", "income_tax": "915.71", "net_pay": "6127.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-40% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "7524.49", "employee_contribution": "400.00", "allowed_deduction": "81.68", "taxable_pay": "7042.81", "income_tax": "915.71", "net_pay": "6127.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-40% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "7524.49", "employee_contribution": "400.00", "allowed_deduction": "81.68", "taxable_pay": "7042.81", "income_tax": "915.71", "net_pay": "6127.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-40% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "7524.49", "employee_contribution": "400.00", "allowed_deduction": "81.68", "taxable_pay": "7042.81", "income_tax": "915.71", "net_pay": "6127.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00196 · Trap MISSING_PAYROLL_MONTH
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
case4-4001-00189 · Trap NO_APPLICABLE_REFERENCE
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
Step 60
case4-4001-00047 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1263.16", "employee_contribution": "63.16", "allowed_deduction": "0.00", "taxable_pay": "1200.00", "income_tax": "0.00", "net_pay": "1200.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1263.16", "employee_contribution": "63.16", "allowed_deduction": "0.00", "taxable_pay": "1200.00", "income_tax": "0.00", "net_pay": "1200.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1263.16", "employee_contribution": "75.79", "allowed_deduction": "0.00", "taxable_pay": "1187.37", "income_tax": "18.74", "net_pay": "1168.63", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1263.16", "employee_contribution": "75.79", "allowed_deduction": "0.00", "taxable_pay": "1187.37", "income_tax": "18.74", "net_pay": "1168.63", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00311 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1783.25", "employee_contribution": "107.00", "allowed_deduction": "10.11", "taxable_pay": "1666.14", "income_tax": "79.26", "net_pay": "1586.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1783.25", "employee_contribution": "107.00", "allowed_deduction": "10.11", "taxable_pay": "1666.14", "income_tax": "79.26", "net_pay": "1586.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1783.25", "employee_contribution": "107.00", "allowed_deduction": "10.11", "taxable_pay": "1666.14", "income_tax": "79.26", "net_pay": "1586.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1783.25", "employee_contribution": "107.00", "allowed_deduction": "10.11", "taxable_pay": "1666.14", "income_tax": "79.26", "net_pay": "1586.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"]}
case4-4001-00143 · Trap MISSING_PAYROLL_MONTH
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
100% clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide the payroll month."}
case4-4001-00195 · Trap NO_APPLICABLE_REFERENCE
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}
100% clarify · scored
{"decision": "clarify", "reason_code": "NO_APPLICABLE_REFERENCE", "clauses": ["R1", "R7"], "explanation": "No reference row covers this payroll month. Please provide an authoritative schedule that covers it."}