{ "bench_version": 1, "track": "two_view_gauge_localization_v2", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01, "epochs": 18 }, "sweep": [ { "cfg": { "lr": 0.001, "epochs": 18 }, "mean": 1.3287881910800934 }, { "cfg": { "lr": 0.003, "epochs": 18 }, "mean": 1.2643743455410004 }, { "cfg": { "lr": 0.01, "epochs": 18 }, "mean": 1.1665648221969604 } ], "full": { "mean": 1.1336221471428871, "std": 0.09147791521994385, "per_seed": [ 1.1263655424118042, 1.207707166671753, 1.2102880477905273, 1.1218985319137573, 1.037619948387146, 0.9893431067466736, 1.28654146194458, 1.0892133712768555 ], "n": 8 } }, "idea": { "config": { "lr": 0.01, "epochs": 18 }, "mean": 1.0666468143463135, "std": 0.06930290941504633, "per_seed": [ 0.9820091128349304, 1.1590790748596191, 1.1329891681671143, 1.1253324747085571, 0.984858512878418, 0.9815046191215515, 1.096936583518982, 1.0704649686813354 ], "n": 8 }, "comparison": { "delta_mean": -0.06697533279657364, "idea_wins": 7, "n_pairs": 8, "per_seed_diffs": [ -0.14435642957687378, -0.04862809181213379, -0.07729887962341309, 0.0034339427947998047, -0.05276143550872803, -0.00783848762512207, -0.18960487842559814, -0.01874840259552002 ], "p_value": 0.0152, "mde": 0.056931783847403286, "mde_rel_pct": 5.022112878695138, "verdict": "idea better (significant)", "system_worked": true }, "mechanism_signature": { "values": { "prediction": "two-view analytic gauge initialization reduces target prediction error", "analytic_test_mse_mean": 0.011936143389903009, "trained_baseline_test_mse_mean": 1.1336221620440483, "trained_idea_test_mse_mean": 1.0666468441486359, "confirmed": true }, "confirmed": true }, "custom_track": { "name": "two_view_gauge_localization_v2", "file": "two_view_registered_track_v2.py", "domain": "geometry/localization" } }