Luma Payroll Gym
← Training / SFT + RL, β 0.001, seed 8
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
3.4h
Training curves, 60 steps

Mean reward

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

KL divergence (k3)

0 0.01 0.02 0.03 Step 0 Step 30 Step 60

Policy entropy

0 0.0025 0.005 0.0075 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% 20% 40% Step 0 Step 30 Step 60

Non-tied groups

0% 50% 100% Step 0 Step 30 Step 60
Sampled completions
Step 1
case4-4001-00341 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9060.19", "employee_contribution": "360.00", "allowed_deduction": "345.74", "taxable_pay": "8354.45", "income_tax": "1143.80", "net_pay": "7210.65", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9060.19", "employee_contribution": "360.00", "allowed_deduction": "345.74", "taxable_pay": "8354.45", "income_tax": "1143.80", "net_pay": "7210.65", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9060.19", "employee_contribution": "360.00", "allowed_deduction": "345.74", "taxable_pay": "8354.45", "income_tax": "1143.80", "net_pay": "7210.65", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9060.19", "employee_contribution": "360.00", "allowed_deduction": "345.74", "taxable_pay": "8354.45", "income_tax": "1143.80", "net_pay": "7210.65", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00362 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1465.43", "employee_contribution": "87.93", "allowed_deduction": "177.50", "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": "1465.43", "employee_contribution": "87.93", "allowed_deduction": "177.50", "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": "1465.43", "employee_contribution": "87.93", "allowed_deduction": "177.50", "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": "1465.43", "employee_contribution": "87.93", "allowed_deduction": "177.50", "taxable_pay": "1200.00", "income_tax": "0.00", "net_pay": "1200.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00168 · 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."}
case4-4001-00101 · 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
case4-4001-00139 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4500.00", "employee_contribution": "225.00", "allowed_deduction": "0.00", "taxable_pay": "4275.00", "income_tax": "444.00", "net_pay": "3831.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4500.00", "employee_contribution": "225.00", "allowed_deduction": "0.00", "taxable_pay": "4275.00", "income_tax": "444.00", "net_pay": "3831.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4500.00", "employee_contribution": "225.00", "allowed_deduction": "0.00", "taxable_pay": "4275.00", "income_tax": "444.00", "net_pay": "3831.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4500.00", "employee_contribution": "225.00", "allowed_deduction": "0.00", "taxable_pay": "4275.00", "income_tax": "444.00", "net_pay": "3831.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00328 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3792.25", "employee_contribution": "227.54", "allowed_deduction": "77.07", "taxable_pay": "3487.64", "income_tax": "248.76", "net_pay": "3238.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3792.25", "employee_contribution": "227.54", "allowed_deduction": "77.07", "taxable_pay": "3487.64", "income_tax": "248.76", "net_pay": "3238.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3792.25", "employee_contribution": "227.54", "allowed_deduction": "77.07", "taxable_pay": "3487.64", "income_tax": "248.76", "net_pay": "3238.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3792.25", "employee_contribution": "227.54", "allowed_deduction": "77.07", "taxable_pay": "3487.64", "income_tax": "248.76", "net_pay": "3238.88", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00148 · 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."}
case4-4001-00370 · 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
case4-4001-00207 · Calculation
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9932.71", "employee_contribution": "250.00", "allowed_deduction": "372.81", "taxable_pay": "9309.90", "income_tax": "1481.98", "net_pay": "7827.92", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9932.71", "employee_contribution": "250.00", "allowed_deduction": "372.81", "taxable_pay": "9309.90", "income_tax": "1481.98", "net_pay": "7827.92", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9932.71", "employee_contribution": "270.00", "allowed_deduction": "372.81", "taxable_pay": "9289.90", "income_tax": "1296.18", "net_pay": "7993.72", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9932.71", "employee_contribution": "250.00", "allowed_deduction": "372.81", "taxable_pay": "9309.90", "income_tax": "1481.98", "net_pay": "7827.92", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00264 · Calculation
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3713.50", "employee_contribution": "259.95", "allowed_deduction": "0.00", "taxable_pay": "3453.55", "income_tax": "351.78", "net_pay": "3101.77", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3713.50", "employee_contribution": "259.95", "allowed_deduction": "0.00", "taxable_pay": "3453.55", "income_tax": "351.78", "net_pay": "3101.77", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3713.50", "employee_contribution": "259.95", "allowed_deduction": "0.00", "taxable_pay": "3453.55", "income_tax": "351.78", "net_pay": "3101.77", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100% calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3713.50", "employee_contribution": "259.95", "allowed_deduction": "0.00", "taxable_pay": "3453.55", "income_tax": "351.78", "net_pay": "3101.77", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00150 · 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."}
case4-4001-00340 · 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."}