{ "status": "uncertain", "issues": [], "criteria": [ { "id": "primary", "metric": "accuracy", "margin": -0.03, "status": "uncertain", "n_items": 1319, "seed_effects": [ 0.032600454890068235 ], "bounds": [ 0, 1 ], "estimate": 0.032600454890068235, "lower": -0.042188907691052054, "upper": 0.10738981747118853, "n_units": 1319 } ], "outcome_reason": "insufficient_evidence", "unit": "fixed_checkpoint_items", "n_seeds": 1, "alpha": 0.05, "method": "paired_hoeffding" }