{"abstract":"Replica mean omits one received contribution from its denominator.","category":"Distributed training aggregation","checks":6,"contract":"Given a list of scalar replica gradients, return their arithmetic mean; empty input returns None.","contract_signature":"values","evaluation_group":"w3-dta-replica-mean","failed_approach":"Filtering zero-valued replicas removes valid contributions and biases the mean.","family":"w3-distributed-training-aggregation-replica-mean","id":"FA-99251","implementations":{"attempt":{"sha256":"6aa293dbfa8d22c1b6c4b9b63e191c76d9e6db82141bde2122cab7de01f5a2b5","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(values):\n    v=[x for x in values if x]; return sum(v)/len(v) if v else None\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('two replicas',solve([N,3*N]),2*N)\ncheck('zero is a participant',solve([0,N]),N/2)\ncheck('empty round',solve([]),None)\ncheck('one replica',solve([N]),N)\ncheck('three uneven values',solve([N,2*N,6*N]),3*N)\ncheck('negative mean',solve([-N,N,2*N]),2*N/3)\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":"41cfbf575fe876e97ac98273f50864ef22d3b8b9752cc1ca85587d6639d989a6","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(values):\n    return sum(values)/max(1,len(values)-1) if values else None\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('two replicas',solve([N,3*N]),2*N)\ncheck('zero is a participant',solve([0,N]),N/2)\ncheck('empty round',solve([]),None)\ncheck('one replica',solve([N]),N)\ncheck('three uneven values',solve([N,2*N,6*N]),3*N)\ncheck('negative mean',solve([-N,N,2*N]),2*N/3)\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 already materialized Python values from a fixed toy collective; no transport, failure recovery, optimizer state, or real model behavior is represented. 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-distributed-training-aggregation-replica-mean","generated_at":"2026-09-30T16:48:22.178504+00:00","license":"CC0-1.0","python":"3.12.14","seed":1,"split":"open-access"},"relevance":"A toy distributed-training contract makes replica and shard contribution rules explicit without claiming framework compatibility or performance.","root_cause":"The denominator is computed as one fewer than the number of received replicas.","sha256":"3af444c1a9ae9daf17b7295d029bf60f0f540f285e158d6bd708857732f44dc7","title":"Replica mean omits one received contribution from its denominator · 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":30.203,"exit_code":1,"observations":[{"actual":2.0,"check":"two replicas","expected":2,"passed":true},{"actual":1.0,"check":"zero is a participant","expected":0.5,"passed":false},{"actual":null,"check":"empty round","expected":null,"passed":true},{"actual":1.0,"check":"one replica","expected":1,"passed":true},{"actual":3.0,"check":"three uneven values","expected":3,"passed":true},{"actual":0.6666666666666666,"check":"negative mean","expected":0.6666666666666666,"passed":true}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"two replicas\", \"actual\": 2.0, \"expected\": 2, \"passed\": true}, {\"check\": \"zero is a participant\", \"actual\": 1.0, \"expected\": 0.5, \"passed\": false}, {\"check\": \"empty round\", \"actual\": null, \"expected\": null, \"passed\": true}, {\"check\": \"one replica\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}, {\"check\": \"three uneven values\", \"actual\": 3.0, \"expected\": 3, \"passed\": true}, {\"check\": \"negative mean\", \"actual\": 0.6666666666666666, \"expected\": 0.6666666666666666, \"passed\": true}], \"passed\": false}\n"},"broken":{"elapsed_ms":31.187,"exit_code":1,"observations":[{"actual":4.0,"check":"two replicas","expected":2,"passed":false},{"actual":1.0,"check":"zero is a participant","expected":0.5,"passed":false},{"actual":null,"check":"empty round","expected":null,"passed":true},{"actual":1.0,"check":"one replica","expected":1,"passed":true},{"actual":4.5,"check":"three uneven values","expected":3,"passed":false},{"actual":1.0,"check":"negative mean","expected":0.6666666666666666,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"two replicas\", \"actual\": 4.0, \"expected\": 2, \"passed\": false}, {\"check\": \"zero is a participant\", \"actual\": 1.0, \"expected\": 0.5, \"passed\": false}, {\"check\": \"empty round\", \"actual\": null, \"expected\": null, \"passed\": true}, {\"check\": \"one replica\", \"actual\": 1.0, \"expected\": 1, \"passed\": true}, {\"check\": \"three uneven values\", \"actual\": 4.5, \"expected\": 3, \"passed\": false}, {\"check\": \"negative mean\", \"actual\": 1.0, \"expected\": 0.6666666666666666, \"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."}}