FA-99431 / Embedding vector normalization / Open access

Min pooling selects coordinate maxima · case 01

Min pooling selects coordinate maxima.

Verified by executionVariant 1 · 6 checks per implementationDownload source bundle ↓JSON ↗

ROOT CAUSE

The reducer chooses the largest value in each dimension.

THE FAILURE

The reducer chooses the largest value in each dimension.

Unsuccessful approach: Returning one flattened minimum destroys the per-coordinate output shape.

Case contract

Return coordinatewise minima across equal-width vectors; empty input returns empty.

Why this case matters

A small embedding preparation contract can be checked without a model or retrieval system.

1 / The failure

Exit 1

"""Failure Map reference implementation. Python standard library only."""
import json

N = 1
observations = []
def solve(vectors):
    return [max(v[j] for v in vectors) for j in range(len(vectors[0]))] if vectors else []
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('coordinate winners differ', solve([[N,5*N],[3*N,2*N]]), [N,2*N])
check('all negative', solve([[-N,-2*N],[-3*N,-N]]), [-3*N,-2*N])
check('singleton', solve([[N,-N]]), [N,-N])
check('empty', solve([]), [])
check('zero candidates', solve([[0,0],[0,0]]), [0,0])
check('winner in last row', solve([[4*N,3*N],[N,2*N]]), [N,2*N])
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 fixture	Actual	Expected	Outcome
coordinate winners differ	`[3, 5]`	`[1, 2]`	Failed
all negative	`[-1, -1]`	`[-3, -2]`	Failed
singleton	`[1, -1]`	`[1, -1]`	Passed
empty	`[]`	`[]`	Passed
zero candidates	`[0, 0]`	`[0, 0]`	Passed
winner in last row	`[4, 3]`	`[1, 2]`	Failed

SHA-256 / 05217994e60909c74f0d2d99bbe3837e978fb2f0587d2b972e63d5fbcd7eb72b

2 / The unsuccessful fix

Exit 1

"""Failure Map reference implementation. Python standard library only."""
import json

N = 1
observations = []
def solve(vectors):
    return [min(min(v) for v in vectors)] if vectors else []
def check(label, actual, expected):
    observations.append({"check": label, "actual": actual, "expected": expected, "passed": actual == expected})
check('coordinate winners differ', solve([[N,5*N],[3*N,2*N]]), [N,2*N])
check('all negative', solve([[-N,-2*N],[-3*N,-N]]), [-3*N,-2*N])
check('singleton', solve([[N,-N]]), [N,-N])
check('empty', solve([]), [])
check('zero candidates', solve([[0,0],[0,0]]), [0,0])
check('winner in last row', solve([[4*N,3*N],[N,2*N]]), [N,2*N])
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 fixture	Actual	Expected	Outcome
coordinate winners differ	`[1]`	`[1, 2]`	Failed
all negative	`[-3]`	`[-3, -2]`	Failed
singleton	`[-1]`	`[1, -1]`	Failed
empty	`[]`	`[]`	Passed
zero candidates	`[0]`	`[0, 0]`	Failed
winner in last row	`[1]`	`[1, 2]`	Failed

SHA-256 / f9075da3bb268b2af957274227c42da6a6a35aff6ae530b06a12755217df80e0

HELD IN THE MEMBER ARCHIVE

The verified repair and its recorded checks are member-only.

This mechanism has 6 recorded checks per implementation. The open-access tier publishes the failure and the unsuccessful fix; the repaired source that passes every check, and the observations that prove it, are available to members.

Every case sharing this mechanism uses the same contract and the same repair, so this one record is held back for all of them.

Member access is invitation-based. Sign in with your invited account to inspect the repair.

Verification & scope

Inputs are finite toy vectors or token rows; this contract makes no claim about model quality or production embedding behavior. 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 2026-09-30T16:48:24.023490+00:00.

Case digest / 0a322af1cac6720ffe0fe3949afe592ebab993518861fbc22435a3489b366107