{"bank_hash":"fce29b4d66cfddeab39632d451935271a37df595374b40eacd300201e3726291","tasks":[{"artifact_contract":"strict-v2","category":"coding","group":"Data correctness","id":"coding-reconcile","ordered_mapping":true,"prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input has invoices and payments lists of {id, cents}. Sum amounts by id; payments subtract from invoices. Return a dict of nonzero outstanding amounts with dictionary iteration keys sorted lexicographically by id, including negative overpayments. IDs are strings. Empty lists are valid. Amounts in cents are integers.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Reconcile invoices and payments"},{"artifact_contract":"strict-v2","category":"coding","group":"Data correctness","id":"coding-dedup","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is a list of {id, version, value}. Keep the highest version for each id; on equal version keep the last occurrence. Return the retained objects sorted lexicographically by id. Do not mutate the input. IDs are strings, versions are integers, and values are arbitrary JSON.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Resolve duplicate event deliveries"},{"artifact_contract":"strict-v2","category":"coding","group":"Algorithms","id":"coding-intervals","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is a list of [start,end] integer half-open intervals, with start<=end. Drop empty intervals; merge overlapping or touching intervals. Return sorted merged intervals without mutating input.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Merge maintenance windows"},{"artifact_contract":"strict-v2","category":"coding","group":"Safety and edge cases","id":"coding-redact","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is arbitrary JSON. Recursively remove dictionary keys whose lowercase spelling equals password, token or secret. Preserve other values and list order; never mutate the original.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Redact nested customer records"},{"artifact_contract":"strict-v2","category":"coding","group":"Algorithms","id":"coding-rolling","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is {events:[[day,count],...], query_days:[integer,...]}. Return totals for each query day covering inclusive days q-6 through q. Events can be unsorted, repeated or negative-day; count is nonnegative. Query order must be preserved. Days, query days and counts are integers.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Calculate seven-day activity totals"},{"artifact_contract":"strict-v2","category":"coding","group":"Data correctness","id":"coding-allocate","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is {total:nonnegative integer,weights:[nonnegative integer,...]}. Allocate proportionally using largest remainders: floor each share, then give leftover cents to largest fractional remainders, ties to lower index. If weights empty return []; if all zero return zeros.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Allocate cents without rounding loss"},{"artifact_contract":"strict-v2","category":"coding","group":"Data correctness","id":"coding-csv","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is CSV text with header customer,cents, including quoted fields. Treat a customer containing only whitespace as blank. Trim surrounding whitespace from cents, then accept only an optional ASCII + or - followed by one or more ASCII digits 0-9. Ignore blank customers and invalid cents. Sum by customer and return a dictionary, including zero totals. Preserve customer spelling. CSV quoting is valid and the header is exactly customer,cents. Ignore rows missing either field or containing extra fields. Ignore empty lines. Whitespace means Python str.strip() whitespace. No dictionary key order is required.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Parse and aggregate CSV purchases"},{"artifact_contract":"strict-v2","category":"coding","group":"Algorithms","id":"coding-dependencies","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is a dict mapping each named job to prerequisite names. Include names referenced only as prerequisites. Return the lexicographically smallest valid topological order, choosing the smallest ready name at every step. Return null for any cycle. Job and prerequisite names are strings; prerequisites are lists. Repeated names in a prerequisite list denote the same dependency. Referenced-only names have no prerequisites. A self-dependency is a cycle. Return Python None for a cycle.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Order deployment dependencies"},{"artifact_contract":"strict-v2","category":"coding","group":"Data correctness","id":"coding-fifo","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is {lots:[[quantity,unit_cents],...], sold:nonnegative integer}. Sell in lot order. Return {remaining_units,remaining_value_cents,unfilled_units}. All quantities/prices nonnegative; unfilled is sales beyond available inventory. Quantities and unit prices are integers.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Value remaining FIFO inventory"},{"artifact_contract":"strict-v2","category":"coding","group":"Algorithms","id":"coding-percentile","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is {values:[finite numbers,...],p:number in [0,100]}. Return nearest-rank percentile: sorted values at 1-based rank max(1,ceil(p/100*n)). Return null for no values. Do not interpolate or mutate input.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Calculate service latency percentiles"},{"artifact_contract":"strict-v2","category":"coding","group":"Safety and edge cases","id":"coding-slug","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is a string. Apply Unicode NFKD normalization, drop combining marks, lowercase, retain only ASCII a-z and digits, replace each run of other characters with one hyphen, strip edge hyphens. Return the slug.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Normalize Unicode article slugs"},{"artifact_contract":"strict-v2","category":"coding","group":"Safety and edge cases","id":"coding-rate","prompt":"Implement solve(data) in Python 3.9. Allowed imports are restricted module facades: math (public members); json (loads, dumps); csv (reader, DictReader); io (StringIO); re (compile, match, search, fullmatch, findall, finditer, split, sub, escape, IGNORECASE, MULTILINE, DOTALL, ASCII); collections (deque, defaultdict, Counter); heapq (heappush, heappop, heapify); unicodedata (normalize, combining, category). Other module members are unavailable. Use functions and only these safe built-ins: abs, all, any, bool, bytes, dict, divmod, enumerate, filter, float, frozenset, int, isinstance, len, list, map, max, min, next, ord, chr, pow, range, reversed, round, set, sorted, str, sum, tuple, zip, Exception, ValueError, TypeError, KeyError, IndexError, StopIteration. Import listed modules before referencing them. No custom classes, private/dunder attributes, globals/nonlocals, with statements, or async. Return only Python code, with no Markdown. Do not read files, use the network, run processes or access system state. Do not mutate any input, including nested containers. Return JSON-serializable values; Python None represents JSON null. Numeric strings and booleans are not accepted as numeric answers. Integer results are compared exactly; floating results use absolute tolerance 0.000001 or relative tolerance 0.00000001. Inputs follow the declared schema; no unspecified input validation is required. Input is {limit:positive integer,window:positive integer,events:[{user,time},...]}. Times are nondecreasing integer seconds. Process in input order. Accept only when fewer than limit previously accepted events for that user have times strictly greater than time-window. Rejections do not consume allowance. Return a list of booleans. User IDs are strings.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Apply a per-user rolling rate limit"},{"artifact_contract":"strict-v2","category":"math","group":"Finance","id":"math-margin","integer_fields":[],"prompt":"A shop buys 240 items at $18 each. It sells 210 at $30 and 30 at $24. Platform fees are 3% of revenue plus $0.20 per sold item. Shipping costs $2.50 per sold item. Calculate revenue, profit after these costs, and profit margin as a percentage of revenue. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: margin_percent, profit, revenue. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Separate markup from margin"},{"artifact_contract":"strict-v2","category":"math","group":"Optimization","id":"math-mix","integer_fields":[],"prompt":"Make exactly 80 litres of a 35% concentrate from 20% and 60% stocks, with additive volumes. How many litres of each stock are needed? Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: litres_20, litres_60. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Solve a production mix"},{"artifact_contract":"strict-v2","category":"math","group":"Statistics","id":"math-weighted","integer_fields":[],"prompt":"Campaign A has 900 visits and 45 purchases. Campaign B has 100 visits and 20 purchases. Next week A has 100 visits and 8 purchases; B has 900 visits and 162 purchases. Return each week’s total conversion percentage and next-minus-first percentage-point change. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: change_points, week1_percent, week2_percent. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Aggregate conversion rates correctly"},{"artifact_contract":"strict-v2","category":"math","group":"Probability","id":"math-bayes","integer_fields":[],"prompt":"A defect affects 2% of units. A detector flags 95% of defective units and 4% of nondefective units. Given a flag, calculate the probability the unit is defective, as a decimal from 0 to 1. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: probability. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Interpret a screening result"},{"artifact_contract":"strict-v2","category":"math","group":"Finance","id":"math-loan","integer_fields":[],"prompt":"A $12000 loan charges a nominal annual rate of 12%, compounded monthly, repaid with 24 equal end-of-month payments. Calculate the monthly payment and total interest, without intermediate rounding. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: interest, payment. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Calculate an amortizing payment"},{"artifact_contract":"strict-v2","category":"math","group":"Finance","id":"math-break-even","integer_fields":["units"],"prompt":"A product sells for $40. Variable costs are $17 production, $3 shipping, and a payment fee of 2.5% of sale price plus $0.30. Fixed monthly costs are $1870. Return the minimum whole units needed to break even and profit at that unit count. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. These fields require exact integer-valued numbers (1 and 1.0 are equivalent): units. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: profit, units. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Calculate break-even with fees"},{"artifact_contract":"strict-v2","category":"math","group":"Probability","id":"math-queue","integer_fields":[],"prompt":"Each of three independent services succeeds with probability 0.98. A workflow requires all three. It retries the complete workflow once if the first attempt fails; attempts are independent. Calculate eventual success probability and expected number of complete attempts. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: expected_attempts, success_probability. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Calculate independent service reliability"},{"artifact_contract":"strict-v2","category":"math","group":"Finance","id":"math-discount","integer_fields":[],"prompt":"An item is $250 before discounts and tax. Apply 20% off, then a further 15% off the discounted price, then 8% tax. Return the final price and effective pretax discount percentage. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: discount_percent, final_price. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Compare sequential and additive discounts"},{"artifact_contract":"strict-v2","category":"math","group":"Optimization","id":"math-capacity","integer_fields":["a","b"],"prompt":"Product A uses 3 labour hours and 2 machine hours and earns $40 contribution. B uses 2 labour and 4 machine hours and earns $50. Weekly limits are 120 labour and 160 machine hours. Products must be whole units. Maximize contribution; if tied choose more A. Return A, B and contribution. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. These fields require exact integer-valued numbers (1 and 1.0 are equivalent): a, b. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: a, b, contribution. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Optimize a constrained production plan"},{"artifact_contract":"strict-v2","category":"math","group":"Finance","id":"math-npv","integer_fields":[],"prompt":"Pay $1000 now, then receive $400 at each year end for three years. Use a 10% annual discount rate. Return net present value without rounding intermediate values. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: npv. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Discount a project cash flow"},{"artifact_contract":"strict-v2","category":"math","group":"Finance","id":"math-allocation","integer_fields":["a_cents","b_cents","c_cents"],"prompt":"Allocate exactly $10.00 to three departments with weights 1, 1, 1. Work in cents: floor shares, then allocate remaining cents by descending fractional remainder, ties to lower index. Return integer cents for departments A, B and C. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. These fields require exact integer-valued numbers (1 and 1.0 are equivalent): a_cents, b_cents, c_cents. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: a_cents, b_cents, c_cents. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Allocate a shared expense"},{"artifact_contract":"strict-v2","category":"math","group":"Statistics","id":"math-variance","integer_fields":[],"prompt":"For observations 4, 7, 7, 10, 12 calculate the arithmetic mean, unbiased sample variance (denominator n-1), and standard error of the mean. Return exact values when representable as terminating decimals. For nonterminating values, provide at least 10 significant digits; do not round intermediate values or final answers to cents or two decimal places. All other numeric fields use absolute tolerance 0.000001 or relative tolerance 0.00000001. Return exactly one JSON object with these keys: mean, sample_variance, standard_error. Numeric fields must be finite numbers. Use each requested key once, no extra keys, no numeric strings, booleans, Markdown or explanation.","review_status":"reviewed_offline_2026-10-04_inactive","title":"Calculate sample uncertainty"}],"version":"tested-best-bank-v2-reviewed"}