{"abstract":"Mean reduction trusts declared world size after dropout.","category":"Distributed training aggregation","checks":7,"contract":"Given received scalar contributions and configured world size, return their mean; empty set returns None.","contract_signature":"values, world","evaluation_group":"w3-dta-worker-count-mean","failed_approach":"Assuming exactly one dropout and dividing by world size minus one fails when the actual number of missing workers differs.","family":"w3-distributed-training-aggregation-worker-count-mean","id":"FA-99286","implementations":{"attempt":{"sha256":"215cdac921ae08b8f43c8b95323d4d9ca033c8b4e23a55aaff5f07925e5e3efb","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(values, world):\n    return sum(values)/max(1,world-1) if values else None\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('partial round',solve([N,3*N],4),2*N)\ncheck('exactly one missing',solve([N,3*N],3),2*N)\ncheck('full round',solve([N,3*N],2),2*N)\ncheck('empty round',solve([],N),None)\ncheck('single received',solve([5*N],4),5*N)\ncheck('configured zero with values',solve([N,3*N],0),2*N)\ncheck('negative values',solve([-N,N,4*N],9),4*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":"f96b458a3ea03450170a3f11d86b4b5878dbf17a2984b13a3a388f02053a32c9","source":"\"\"\"Failure Map reference implementation. Python standard library only.\"\"\"\nimport json\n\nN = 1\nobservations = []\ndef solve(values, world):\n    return sum(values)/world if world else None\ndef check(label, actual, expected):\n    observations.append({\"check\": label, \"actual\": actual, \"expected\": expected, \"passed\": actual == expected})\ncheck('partial round',solve([N,3*N],4),2*N)\ncheck('exactly one missing',solve([N,3*N],3),2*N)\ncheck('full round',solve([N,3*N],2),2*N)\ncheck('empty round',solve([],N),None)\ncheck('single received',solve([5*N],4),5*N)\ncheck('configured zero with values',solve([N,3*N],0),2*N)\ncheck('negative values',solve([-N,N,4*N],9),4*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-worker-count-mean","generated_at":"2026-09-30T16:48:22.632883+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 divisor is the configured world size even when fewer worker contributions arrived.","sha256":"8c608c121a0c186dfb5fd4d02360c1b327255c46acd93e87b018ced0a745f874","title":"Mean reduction trusts declared world size after dropout · 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":27.837,"exit_code":1,"observations":[{"actual":1.3333333333333333,"check":"partial round","expected":2,"passed":false},{"actual":2.0,"check":"exactly one missing","expected":2,"passed":true},{"actual":4.0,"check":"full round","expected":2,"passed":false},{"actual":null,"check":"empty round","expected":null,"passed":true},{"actual":1.6666666666666667,"check":"single received","expected":5,"passed":false},{"actual":4.0,"check":"configured zero with values","expected":2,"passed":false},{"actual":0.5,"check":"negative values","expected":1.3333333333333333,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"partial round\", \"actual\": 1.3333333333333333, \"expected\": 2, \"passed\": false}, {\"check\": \"exactly one missing\", \"actual\": 2.0, \"expected\": 2, \"passed\": true}, {\"check\": \"full round\", \"actual\": 4.0, \"expected\": 2, \"passed\": false}, {\"check\": \"empty round\", \"actual\": null, \"expected\": null, \"passed\": true}, {\"check\": \"single received\", \"actual\": 1.6666666666666667, \"expected\": 5, \"passed\": false}, {\"check\": \"configured zero with values\", \"actual\": 4.0, \"expected\": 2, \"passed\": false}, {\"check\": \"negative values\", \"actual\": 0.5, \"expected\": 1.3333333333333333, \"passed\": false}], \"passed\": false}\n"},"broken":{"elapsed_ms":28.661,"exit_code":1,"observations":[{"actual":1.0,"check":"partial round","expected":2,"passed":false},{"actual":1.3333333333333333,"check":"exactly one missing","expected":2,"passed":false},{"actual":2.0,"check":"full round","expected":2,"passed":true},{"actual":0.0,"check":"empty round","expected":null,"passed":false},{"actual":1.25,"check":"single received","expected":5,"passed":false},{"actual":null,"check":"configured zero with values","expected":2,"passed":false},{"actual":0.4444444444444444,"check":"negative values","expected":1.3333333333333333,"passed":false}],"passed":false,"stderr":"","stdout":"{\"observations\": [{\"check\": \"partial round\", \"actual\": 1.0, \"expected\": 2, \"passed\": false}, {\"check\": \"exactly one missing\", \"actual\": 1.3333333333333333, \"expected\": 2, \"passed\": false}, {\"check\": \"full round\", \"actual\": 2.0, \"expected\": 2, \"passed\": true}, {\"check\": \"empty round\", \"actual\": 0.0, \"expected\": null, \"passed\": false}, {\"check\": \"single received\", \"actual\": 1.25, \"expected\": 5, \"passed\": false}, {\"check\": \"configured zero with values\", \"actual\": null, \"expected\": 2, \"passed\": false}, {\"check\": \"negative values\", \"actual\": 0.4444444444444444, \"expected\": 1.3333333333333333, \"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."}}