FAILURE MAP
← Case archive

FA-6261 / Statistics / Open access

Mean absolute error · case 01

Opposite errors cancel before absolute value is applied.

Verified by executionVariant 1 · 4 checks per implementationDownload source bundle ↓JSON ↗

ROOT CAUSE

Opposite errors cancel before absolute value is applied.

VERIFIED REPAIR

Apply the specified mathematical contract directly, preserving all terms and boundary cases: return str(Fraction(sum(abs(a-p) for a,p in zip(actual,predicted)),len(actual)))

Unsuccessful approach: Squared error changes the loss function.

Case contract

Integer finite observations and equal lengths for paired samples. Counts and weights are nonnegative. Rational results use reduced Fraction strings. Empty or undefined statistics return None where shown. Paired arrays are nonempty; average absolute prediction residuals. Exact operational definition: str(Fraction(sum(abs(a-p) for a,p in zip(actual,predicted)),len(actual)))

Why this case matters

Small exact fixtures expose this error without platform timing, external services, or probabilistic observations. Statistical estimators results depend on the stated convention.

1 / The failure

Exit 1
"""Failure Map reference implementation. Python standard library only."""
import json
import math
import calendar
import statistics
import itertools
from fractions import Fraction
from datetime import date, datetime, timedelta, timezone
from decimal import Decimal, ROUND_HALF_UP, ROUND_DOWN, ROUND_CEILING, ROUND_FLOOR

N = 1
observations = []
def solve(actual, predicted):
    return str(abs(Fraction(sum(a-p for a,p in zip(actual,predicted)),len(actual))))
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('fixture 1: ([1, 3], [2, 2])', solve(*([1, 3], [2, 2])), '1')
check('fixture 2: ([0, 0], [2, -2])', solve(*([0, 0], [2, -2])), '2')
check('fixture 3: ([1], [1])', solve(*([1], [1])), '0')
check('fixture 4: ([1, 2, 3], [1, 2, 6])', solve(*([1, 2, 3], [1, 2, 6])), '1')
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)
Boundary fixtureActualExpectedOutcome
fixture 1: ([1, 3], [2, 2])01Failed
fixture 2: ([0, 0], [2, -2])02Failed
fixture 3: ([1], [1])00Passed
fixture 4: ([1, 2, 3], [1, 2, 6])11Passed

SHA-256 / e83d452320eba9e0a810be3236686a01b371ac709c374aa69d173e24559ca3b4

2 / The unsuccessful fix

Exit 1
"""Failure Map reference implementation. Python standard library only."""
import json
import math
import calendar
import statistics
import itertools
from fractions import Fraction
from datetime import date, datetime, timedelta, timezone
from decimal import Decimal, ROUND_HALF_UP, ROUND_DOWN, ROUND_CEILING, ROUND_FLOOR

N = 1
observations = []
def solve(actual, predicted):
    return str(Fraction(sum((a-p)**2 for a,p in zip(actual,predicted)),len(actual)))
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('fixture 1: ([1, 3], [2, 2])', solve(*([1, 3], [2, 2])), '1')
check('fixture 2: ([0, 0], [2, -2])', solve(*([0, 0], [2, -2])), '2')
check('fixture 3: ([1], [1])', solve(*([1], [1])), '0')
check('fixture 4: ([1, 2, 3], [1, 2, 6])', solve(*([1, 2, 3], [1, 2, 6])), '1')
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)
Boundary fixtureActualExpectedOutcome
fixture 1: ([1, 3], [2, 2])11Passed
fixture 2: ([0, 0], [2, -2])42Failed
fixture 3: ([1], [1])00Passed
fixture 4: ([1, 2, 3], [1, 2, 6])31Failed

SHA-256 / fdb76c95cb8a76742855a980dd82aa9c93daa5d8daf7b9bb0f1301a1af452afd

3 / The verified repair

Exit 0
"""Failure Map reference implementation. Python standard library only."""
import json
import math
import calendar
import statistics
import itertools
from fractions import Fraction
from datetime import date, datetime, timedelta, timezone
from decimal import Decimal, ROUND_HALF_UP, ROUND_DOWN, ROUND_CEILING, ROUND_FLOOR

N = 1
observations = []
def solve(actual, predicted):
    return str(Fraction(sum(abs(a-p) for a,p in zip(actual,predicted)),len(actual)))
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('fixture 1: ([1, 3], [2, 2])', solve(*([1, 3], [2, 2])), '1')
check('fixture 2: ([0, 0], [2, -2])', solve(*([0, 0], [2, -2])), '2')
check('fixture 3: ([1], [1])', solve(*([1], [1])), '0')
check('fixture 4: ([1, 2, 3], [1, 2, 6])', solve(*([1, 2, 3], [1, 2, 6])), '1')
print(json.dumps({"observations": observations, "passed": all(x["passed"] for x in observations)}, ensure_ascii=False))
raise SystemExit(0 if all(x["passed"] for x in observations) else 1)
Boundary fixtureActualExpectedOutcome
fixture 1: ([1, 3], [2, 2])11Passed
fixture 2: ([0, 0], [2, -2])22Passed
fixture 3: ([1], [1])00Passed
fixture 4: ([1, 2, 3], [1, 2, 6])11Passed

SHA-256 / e2c709ab4022d95f80e019e03340f4d9006c9ed0e14e782b05b560f9bea9f552

Verification & scope

This reproducer isolates one failure mechanism. Results cover the supplied fixtures. Variants within a family share a test contract and should remain grouped when constructing evaluation splits. Related mechanisms with a shared evaluation_group must also remain together; these controlled models are not independent production incidents.

Observations recorded using Python 3.12.14 at 2026-09-29T14:37:59.555715+00:00.

Case digest / 348c8f16899bf50ee877e39b8622f01d2624d2e6e30d779b0209500e1f83b2de