← Training / SFT + RL, β 0.04, balanced
SFT + RL, β 0.04, balanced
β 0.001, rubric 5
β 0.04, rubric 5
β 0.04, rubric 3
β 0.04, rubric 4
β 0.04, rubric 6
β 0.001, rubric 7
β 0.04, rubric 7
β 0.04, rubric 7, answer-weighted
SFT + RL, β 0.001
SFT + RL, β 0.001, seed 8
SFT + RL, β 0.001, seed 9
SFT + RL, β 0.04
SFT + RL, β 0.04, balanced
SFT + RL, β 0.04, more signal
SFT + RL, β 10
SFT + RL, β 100
KL β
0.04
Rubric
8
Steps
60 / 60
LR
1e-05
Group size
4-16
Epochs
2
Prompt
v4 interleaved demonstrations, calculate tool
GPU time
3.5h
Training curves, 60 steps
Mean reward
KL divergence (k3)
Policy entropy
Completion length (tokens)
Trap pass rate
Payslip pass rate
Correct clarifications
Calculates through traps
Non-tied groups
Sampled completions
Step 1
case4-4001-00204 · Calculation
-50%
clarify · wrong decision
{"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%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1080.14", "employee_contribution": "64.81", "allowed_deduction": "0.00", "taxable_pay": "1015.33", "income_tax": "1.23", "net_pay": "1014.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"]}
-50%
clarify · wrong decision
{"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%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1080.14", "employee_contribution": "64.81", "allowed_deduction": "0.00", "taxable_pay": "1015.33", "income_tax": "1.23", "net_pay": "1014.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R9"]}
case4-4001-00344 · Calculation
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "513.69", "employee_contribution": "35.96", "allowed_deduction": "102.25", "taxable_pay": "375.48", "income_tax": "0.00", "net_pay": "375.48", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "513.69", "employee_contribution": "35.96", "allowed_deduction": "102.25", "taxable_pay": "375.48", "income_tax": "0.00", "net_pay": "375.48", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "513.69", "employee_contribution": "35.96", "allowed_deduction": "102.25", "taxable_pay": "375.48", "income_tax": "0.00", "net_pay": "375.48", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "513.69", "employee_contribution": "35.96", "allowed_deduction": "102.25", "taxable_pay": "375.48", "income_tax": "0.00", "net_pay": "375.48", "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
case4-4001-00116 · Calculation
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1220.25", "employee_contribution": "73.22", "allowed_deduction": "189.35", "taxable_pay": "957.68", "income_tax": "0.00", "net_pay": "957.68", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1220.25", "employee_contribution": "73.22", "allowed_deduction": "189.35", "taxable_pay": "957.68", "income_tax": "0.00", "net_pay": "957.68", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1220.25", "employee_contribution": "73.22", "allowed_deduction": "189.35", "taxable_pay": "957.68", "income_tax": "0.00", "net_pay": "957.68", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1220.25", "employee_contribution": "73.22", "allowed_deduction": "189.35", "taxable_pay": "957.68", "income_tax": "0.00", "net_pay": "957.68", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00078 · Calculation
-50%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3165.62", "employee_contribution": "253.25", "allowed_deduction": "39.00", "taxable_pay": "2873.37", "income_tax": "200.80", "net_pay": "2672.57", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3165.62", "employee_contribution": "253.25", "allowed_deduction": "39.00", "taxable_pay": "2873.37", "income_tax": "200.80", "net_pay": "2672.57", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3165.62", "employee_contribution": "253.25", "allowed_deduction": "39.00", "taxable_pay": "2873.37", "income_tax": "200.80", "net_pay": "2672.57", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "3165.62", "employee_contribution": "253.25", "allowed_deduction": "39.00", "taxable_pay": "2873.37", "income_tax": "200.80", "net_pay": "2672.57", "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
case4-4001-00082 · Calculation
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "2042.75", "employee_contribution": "122.57", "allowed_deduction": "0.00", "taxable_pay": "1920.18", "income_tax": "86.42", "net_pay": "1833.76", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "2042.75", "employee_contribution": "122.57", "allowed_deduction": "0.00", "taxable_pay": "1920.18", "income_tax": "86.42", "net_pay": "1833.76", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "2042.75", "employee_contribution": "122.57", "allowed_deduction": "0.00", "taxable_pay": "1920.18", "income_tax": "86.42", "net_pay": "1833.76", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "2042.75", "employee_contribution": "122.57", "allowed_deduction": "0.00", "taxable_pay": "1920.18", "income_tax": "86.42", "net_pay": "1833.76", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
case4-4001-00140 · Calculation
-50%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1276.57", "employee_contribution": "89.36", "allowed_deduction": "0.00", "taxable_pay": "1187.21", "income_tax": "8.72", "net_pay": "1178.49", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1276.57", "employee_contribution": "76.59", "allowed_deduction": "0.00", "taxable_pay": "1199.98", "income_tax": "0.00", "net_pay": "1199.98", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1276.57", "employee_contribution": "89.36", "allowed_deduction": "0.00", "taxable_pay": "1187.21", "income_tax": "8.72", "net_pay": "1178.49", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
100%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "1276.57", "employee_contribution": "76.59", "allowed_deduction": "0.00", "taxable_pay": "1199.98", "income_tax": "0.00", "net_pay": "1199.98", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
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."}