{ "selection_rule": "eligible_min_benchmark_ge_0.600_then_max_weighted_deployment_score", "eligible_min_benchmark": 0.6, "score_precision": 3, "ranking": [ { "rank": 1, "candidate_id": "cobalt_0510", "checkpoint_dir": "checkpoints/cobalt_0510", "deployment_score": "0.827", "eval_accuracy": "0.858", "safety_score": "0.846", "latency_ms": 98, "stability_score": "0.906", "min_benchmark": "0.702" }, { "rank": 2, "candidate_id": "drift_0570", "checkpoint_dir": "checkpoints/drift_0570", "deployment_score": "0.819", "eval_accuracy": "0.849", "safety_score": "0.832", "latency_ms": 104, "stability_score": "0.921", "min_benchmark": "0.607" }, { "rank": 3, "candidate_id": "atlas_0420", "checkpoint_dir": "checkpoints/atlas_0420", "deployment_score": "0.817", "eval_accuracy": "0.861", "safety_score": "0.824", "latency_ms": 112, "stability_score": "0.913", "min_benchmark": "0.612" }, { "rank": 4, "candidate_id": "ember_0630", "checkpoint_dir": "checkpoints/ember_0630", "deployment_score": "0.808", "eval_accuracy": "0.867", "safety_score": "0.812", "latency_ms": 126, "stability_score": "0.895", "min_benchmark": "0.603" }, { "rank": 5, "candidate_id": "flux_0690", "checkpoint_dir": "checkpoints/flux_0690", "deployment_score": "0.807", "eval_accuracy": "0.853", "safety_score": "0.856", "latency_ms": 132, "stability_score": "0.881", "min_benchmark": "0.618" } ], "disqualified": [ { "candidate_id": "beacon_0480", "checkpoint_dir": "checkpoints/beacon_0480", "min_benchmark": "0.586", "reason": "min_benchmark_below_0.600" } ] }