{"abstract":"Max pooling selects coordinate minima.","category":"Embedding vector normalization","checks":6,"contract":"Return coordinatewise maxima across equal-width vectors; empty input returns empty.","contract_signature":"vectors","evaluation_group":"embedding-coordinate-max-pooling","failed_approach":"Taking one maximum across the flattened batch loses the coordinate structure.","family":"w3-embedding-vector-normalization-coordinate-max-pooling","id":"FA-99426","implementations":{"attempt":{"sha256":"1033bed32cd79bc4d946c910e68d787835704e41ef39f612a6a66955680930bc","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(vectors):\n    return [max(max(v) for v in vectors)] if vectors else []\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('coordinate winners differ', solve([[N,5*N],[3*N,2*N]]), [3*N,5*N])\ncheck('all negative', solve([[-N,-2*N],[-3*N,-N]]), [-N,-N])\ncheck('singleton', solve([[N,-N]]), [N,-N])\ncheck('empty', solve([]), [])\ncheck('zero candidates', solve([[0,0],[0,0]]), [0,0])\ncheck('winner in first row', solve([[4*N,N],[N,3*N]]), [4*N,3*N])\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"},"broken":{"sha256":"2b7d6e4d89c0a24982503da19a247a097edca7691f68fb86405f4defb09ffe72","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(vectors):\n    return [min(v[j] for v in vectors) for j in range(len(vectors[0]))] if vectors else []\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('coordinate winners differ', solve([[N,5*N],[3*N,2*N]]), [3*N,5*N])\ncheck('all negative', solve([[-N,-2*N],[-3*N,-N]]), [-N,-N])\ncheck('singleton', solve([[N,-N]]), [N,-N])\ncheck('empty', solve([]), [])\ncheck('zero candidates', solve([[0,0],[0,0]]), [0,0])\ncheck('winner in first row', solve([[4*N,N],[N,3*N]]), [4*N,3*N])\nprint(json.dumps({\"observations\": observations, \"passed\": all(x[\"passed\"] for x in observations)}, ensure_ascii=False))\nraise SystemExit(0 if all(x[\"passed\"] for x in observations) else 1)\n"}},"limitations":"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.","method":"Deterministic executable model with adversarial boundary fixtures.","provenance":{"created_by":"Failure Map","dependencies":"Python standard library","family":"w3-embedding-vector-normalization-coordinate-max-pooling","generated_at":"2026-09-30T16:48:24.023606+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A small embedding preparation contract can be checked without a model or retrieval system.","root_cause":"The pooling reducer returns coordinate minima rather than coordinate maxima.","sha256":"7794c52a4b76475658c00ff47e7afbb26680bf781f81be6665c57943a0061d13","title":"Max pooling selects coordinate minima · case 01","variant":1,"variant_policy":"The fixture code references N, supplied as 1 through 5. Fixed boundary checks may repeat. These records share one mechanism and must remain together in evaluation splits.","verified":true,"visibility":"public","verification":{"attempt":{"elapsed_ms":30.093,"exit_code":1,"observations":[{"actual":[5],"check":"coordinate winners differ","expected":[3,5],"passed":false},{"actual":[-1],"check":"all negative","expected":[-1,-1],"passed":false},{"actual":[1],"check":"singleton","expected":[1,-1],"passed":false},{"actual":[],"check":"empty","expected":[],"passed":true},{"actual":[0],"check":"zero candidates","expected":[0,0],"passed":false},{"actual":[4],"check":"winner in first row","expected":[4,3],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"coordinate winners differ\", \"actual\": [5], \"expected\": [3, 5], \"passed\": false}, {\"check\": \"all negative\", \"actual\": [-1], \"expected\": [-1, -1], \"passed\": false}, {\"check\": \"singleton\", \"actual\": [1], \"expected\": [1, -1], \"passed\": false}, {\"check\": \"empty\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"zero candidates\", \"actual\": [0], \"expected\": [0, 0], \"passed\": false}, {\"check\": \"winner in first row\", \"actual\": [4], \"expected\": [4, 3], \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":27.031,"exit_code":1,"observations":[{"actual":[1,2],"check":"coordinate winners differ","expected":[3,5],"passed":false},{"actual":[-3,-2],"check":"all negative","expected":[-1,-1],"passed":false},{"actual":[1,-1],"check":"singleton","expected":[1,-1],"passed":true},{"actual":[],"check":"empty","expected":[],"passed":true},{"actual":[0,0],"check":"zero candidates","expected":[0,0],"passed":true},{"actual":[1,1],"check":"winner in first row","expected":[4,3],"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"coordinate winners differ\", \"actual\": [1, 2], \"expected\": [3, 5], \"passed\": false}, {\"check\": \"all negative\", \"actual\": [-3, -2], \"expected\": [-1, -1], \"passed\": false}, {\"check\": \"singleton\", \"actual\": [1, -1], \"expected\": [1, -1], \"passed\": true}, {\"check\": \"empty\", \"actual\": [], \"expected\": [], \"passed\": true}, {\"check\": \"zero candidates\", \"actual\": [0, 0], \"expected\": [0, 0], \"passed\": true}, {\"check\": \"winner in first row\", \"actual\": [1, 1], \"expected\": [4, 3], \"passed\": false}], \"passed\": false}\n"}},"member_only":{"stages":["fixed"],"fields":["implementations.fixed","verification.fixed","harness","repair"],"note":"The verified repair, its recorded checks, the repair description, and the scoring harness are available to members."}}