← Training / β 0.04, rubric 7
β 0.04, rubric 7
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
7
Steps
60 / 60
LR
1e-05
Group size
4-16
Epochs
2
Prompt
decision examples, thinking disabled
GPU time
5.1h
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
generated-1001-00064 · Calculation
-50%
retrieve · wrong decision
{"decision": "retrieve", "field": "contribution_rate", "value": "0.04", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"], "explanation": "The task requires retrieving information from the rulebook based on the provided month, and R1 and R2 are needed for the calculation. These are the required tools and sources for the task."}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "6717.67", "employee_contribution": "1075.95", "allowed_deduction": "326.05", "taxable_pay": "1075.45", "income_tax": "65.25", "net_pay": "1061.30", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "6717.67", "employee_contribution": "1103.67", "allowed_deduction": "326.05", "taxable_pay": "1824.98", "income_tax": "39.30", "net_pay": "1794.38", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "6717.67", "employee_contribution": "1001.63", "allowed_deduction": "1001.63", "taxable_pay": "1822.25", "income_tax": "42.25", "net_pay": "4794.49", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7", "R9"]}
generated-1001-00055 · Calculation
-50%
retrieve · wrong decision
{"decision": "retrieve", "field": "2026-11", "value": "2891.48", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "2891.48", "employee_contribution": "144.48", "allowed_deduction": "0.00", "taxable_pay": "2314.00", "income_tax": "38.50", "net_pay": "2063.98", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "2891.48",
"employee_contribution": "1727.00",
"allowed_deduction": "0.00",
"taxable_pay": "2058.48",
"income_tax": "107.00",
"net_pay": "2174.48",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7", "R9"]
}
-50%
retrieve · wrong decision
{"decision": "retrieve", "field": "2026-11-05", "value": "2891.48", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
generated-1001-00092 · Trap
CONFLICTING_GROSS_PAY
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "6265.40", "employee_contribution": "217.00", "allowed_deduction": "217.79", "taxable_pay": "2178.79", "income_tax": "43.40", "net_pay": "6040.10", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
clarify · wrong clarification
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
0%
clarify · wrong clarification
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "6265.40", "employee_contribution": "1308.26", "allowed_deduction": "217.79", "taxable_pay": "2100.51", "income_tax": "210.21", "net_pay": "4062.20", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
generated-1001-00096 · Trap
MISSING_GROSS_PAY
-50%
retrieve · invalid format
{"decision": "retrieve", "field": "contribution_rate", "value": "0.08", "clauses": ["R1", "R3", "R4"], "clauses": ["R1", "R3", "R4", "R5"]}
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "2400.00", "employee_contribution": "120.00", "allowed_deduction": "100.00", "taxable_pay": "2180.00", "income_tax": "118.00", "net_pay": "2062.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
-50%
calculate · wrong decision
{
"decision": "calculate",
"currency": "LCR",
"gross_pay": "2400.00",
"employee_contribution": "120.00",
"allowed_deduction": "100.00",
"taxable_pay": "2180.00",
"income_tax": "118.00",
"net_pay": "2062.00",
"clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]
}
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "1800.00", "employee_contribution": "102.33", "allowed_deduction": "102.33", "taxable_pay": "2142.00", "income_tax": "429.33", "net_pay": "1789.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
Step 30
generated-1001-00028 · Calculation
-50%
clarify · wrong decision
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Provide the monthly gross pay before calculation."}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "6216.27", "employee_contribution": "1001.90", "allowed_deduction": "1001.90", "taxable_pay": "1117.68", "income_tax": "45.28", "net_pay": "5210.99", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "6216.27", "employee_contribution": "206.27", "allowed_deduction": "206.66", "taxable_pay": "2060.00", "income_tax": "205.66", "net_pay": "2070.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "6216.27", "employee_contribution": "1043.00", "allowed_deduction": "206.66", "taxable_pay": "2263.00", "income_tax": "173.20", "net_pay": "2062.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
generated-1001-00088 · Calculation
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "8340.45", "employee_contribution": "2245.45", "allowed_deduction": "284.60", "taxable_pay": "2213.45", "income_tax": "1084.45", "net_pay": "1120.90", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "8340.45", "employee_contribution": "2249.40", "allowed_deduction": "284.60", "taxable_pay": "2249.40", "income_tax": "48.00", "net_pay": "999.45", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "8340.45", "employee_contribution": "2240.45", "allowed_deduction": "284.60", "taxable_pay": "2376.45", "income_tax": "84.45", "net_pay": "7474.40", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
clarify · wrong decision
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing."}
generated-1001-00005 · Trap
MISSING_PAYROLL_MONTH
0%
clarify · wrong clarification
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "explanation": "Gross pay is missing. Please provide the monthly gross pay before calculation."}
0%
clarify · wrong clarification
{
"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_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing, so no reference row can be chosen. Please provide an authoritative schedule that covers it."}
-50%
clarify · invalid format
{"decision": "clarify", "reason_code": "MISSING_GROSS_PAY", "clauses": ["R1", "R7"], "value": "None of the provided information includes the necessary 'gross_pay' or a reference row to calculate payroll."}
generated-1001-00002 · Trap
NO_APPLICABLE_REFERENCE
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "1170.19", "employee_contribution": "103.59", "allowed_deduction": "66.18", "taxable_pay": "1261.62", "income_tax": "55.62", "net_pay": "1104.05", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
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."}
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "1170.19", "employee_contribution": "70.89", "allowed_deduction": "66.18", "taxable_pay": "1728.40", "income_tax": "43.38", "net_pay": "1105.60", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · wrong decision
{"decision": "calculate", "currency": "LCR", "gross_pay": "1170.19", "employee_contribution": "77.59", "allowed_deduction": "66.18", "taxable_pay": "1258.01", "income_tax": "10.73", "net_pay": "1002.50", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
Step 60
generated-1001-00085 · Calculation
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9993.09", "employee_contribution": "127.09", "allowed_deduction": "127.12", "taxable_pay": "2188.00", "income_tax": "58.00", "net_pay": "2188.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · invalid format
{"decision": "calculate", "currency": "LCR", "gross_pay": "9993.09", "employee_contribution": "400.00", "allowed_deduction": "127.12", "taxable_pay": "4000.00", "net_pay": "1996.09", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
-50%
calculate · invalid format
{"decision": "calculate", "currency": "LCR", "gross_pay": "9993.09", "employee_contribution": "400.00", "allowed_deduction": "127.12", "taxable_pay": "2388.17", "income_tax": "63.81", "net_pay": "9993.09 - 400.00 + 127.12 = 9950.21", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "9993.09", "employee_contribution": "127.09", "allowed_deduction": "127.12", "taxable_pay": "2175.27", "income_tax": "45.27", "net_pay": "9795.09", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
generated-1001-00043 · Calculation
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4681.59", "employee_contribution": "1055.33", "allowed_deduction": "168.38", "taxable_pay": "1722.39", "income_tax": "56.00", "net_pay": "2525.20", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4681.59", "employee_contribution": "1049.01", "allowed_deduction": "168.38", "taxable_pay": "1457.00", "income_tax": "84.35", "net_pay": "1273.59", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6", "R7"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4681.59", "employee_contribution": "1257.83", "allowed_deduction": "168.38", "taxable_pay": "1900.00", "income_tax": "133.50", "net_pay": "1873.00", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
0%
calculate · scored
{"decision": "calculate", "currency": "LCR", "gross_pay": "4681.59", "employee_contribution": "1169.23", "allowed_deduction": "168.38", "taxable_pay": "1801.90", "income_tax": "42.00", "net_pay": "2959.50", "clauses": ["R1", "R2", "R3", "R4", "R5", "R6"]}
generated-1001-00101 · Trap
MISSING_PAYROLL_MONTH
0%
clarify · wrong clarification
{"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."}
97%
clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The provided record lacks a specified payroll month reference, so it is not applicable for the 2026 reference period."}
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 an authoritative schedule that covers it."}
100%
clarify · scored
{"decision": "clarify", "reason_code": "MISSING_PAYROLL_MONTH", "clauses": ["R1", "R7"], "explanation": "The payroll month is missing. Please provide the payroll month. The reference row cannot be applied for this month because no reference row exists for it."}
generated-1001-00041 · 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."}