{ "checks": { "accuracy_at_least_0.70": true, "early_alignment_at_least_0.50": true, "epoch11_to20_feedback_cosine_at_least_0.70": true, "final_feedback_cosine_at_least_0.80": true, "macs_at_most_1.40x_bp": true, "record_and_trajectory_finite": true, "within_15_points_of_bp_epoch20": true, "zero_task_loss_queries": true }, "confirmation_test_seeds_touched": false, "full_validation_opened": true, "metrics": { "accuracy": 0.8266, "bp_epoch20_accuracy": 0.8102, "bp_epoch20_total_macs": 109487808000000, "early_third_alignment": 0.8855825364589691, "epoch11_to20_mean_feedback_forward_cosine": 0.8545936173514315, "final_mean_feedback_forward_cosine": 0.9010338814635026, "final_mean_feedback_forward_relative_error": 0.44480918269408376, "logical_batch_loss_queries": 0, "loss": 0.5224007934570313, "mac_ratio_to_bp": 1.3260607208430002, "peak_memory_allocated_bytes": 2162790400, "source_commit": "8f420f256aef160d79e3a9620a92ae156f06ef74", "total_macs": 145187481600000, "wall_s": 558.1345100402832 }, "protocol": "kolen_pollack_short_v1", "review_score_after": 5, "review_score_before": 5, "score_change_rule": "inherited KP baseline cannot raise score", "status": "passed" }