{ "bench_version": 1, "track": "unordered_pointset_denoising", "model": "mlp_med", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 0.04259627405554056 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001 }, "mean": 0.04272811021655798 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.03448029048740864 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001 }, "mean": 0.034148878417909145 }, { "cfg": { "lr": 0.006, "weight_decay": 0.0 }, "mean": 0.03395335283130407 }, { "cfg": { "lr": 0.006, "weight_decay": 0.0001 }, "mean": 0.034376708790659904 } ], "full": { "mean": 0.034991197753697634, "std": 0.002117625587373799, "per_seed": [ 0.036085259169340134, 0.03398258239030838, 0.03428776562213898, 0.0314578041434288, 0.034709829837083817, 0.03937392309308052, 0.035850487649440765, 0.034181930124759674 ], "n": 8 } }, "idea": { "mean": 0.0419774423353374, "std": 0.0049312628769484414, "per_seed": [ 0.039885085076093674, 0.03695981204509735, 0.038052886724472046, 0.04973628371953964, 0.04566482454538345, 0.036613475531339645, 0.04028519243001938, 0.04862197861075401 ], "n": 8 }, "comparison": { "delta_mean": 0.006986244581639767, "idea_wins": 1, "n_pairs": 8, "per_seed_diffs": [ 0.00379982590675354, 0.002977229654788971, 0.003765121102333069, 0.01827847957611084, 0.010954994708299637, -0.0027604475617408752, 0.004434704780578613, 0.014440048485994339 ], "p_value": 0.0163, "mde": 0.005801091064441157, "mde_rel_pct": 16.578715325136695, "verdict": "idea worse (significant)", "system_worked": false }, "custom_track": { "name": "unordered_pointset_denoising", "file": "bench/custom_tracks/unordered_pointset_denoising.py", "domain": "point-set-diffusion" }, "baseline_grid": [ { "lr": 0.001, "weight_decay": 0.0 }, { "lr": 0.001, "weight_decay": 0.0001 }, { "lr": 0.003, "weight_decay": 0.0 }, { "lr": 0.003, "weight_decay": 0.0001 }, { "lr": 0.006, "weight_decay": 0.0 }, { "lr": 0.006, "weight_decay": 0.0001 } ], "idea_grid": [ { "lr": 0.001, "weight_decay": 0.0, "tree_lambda": 0.02 }, { "lr": 0.003, "weight_decay": 0.0, "tree_lambda": 0.05 }, { "lr": 0.006, "weight_decay": 0.0001, "tree_lambda": 0.1 } ], "idea_trials": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0, "tree_lambda": 0.02 }, "mean": 0.04521314054727554 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0, "tree_lambda": 0.05 }, "mean": 0.04115851689130068 }, { "cfg": { "lr": 0.006, "weight_decay": 0.0001, "tree_lambda": 0.1 }, "mean": 0.04825861472636461 } ], "math_check": { "gram_tree_orthogonal_invariance_relative_error": 2.9398856327134126e-07 }, "mechanism_signature": { "claim": "tree aggregation preserves target set correspondence", "predicted": "tree-feature correlation is higher for the idea system", "observed_baseline_mean_tree_corr": 0.9266873237022839, "observed_idea_mean_tree_corr": 0.9220414828405017, "per_seed": [ { "seed": 0, "baseline_tree_corr": 0.9256211589939427, "idea_tree_corr": 0.917472849753899, "baseline_mse": 0.036085259169340134, "idea_mse": 0.039885085076093674 }, { "seed": 1, "baseline_tree_corr": 0.9170005706547195, "idea_tree_corr": 0.924394805959731, "baseline_mse": 0.03398258239030838, "idea_mse": 0.03695981204509735 }, { "seed": 2, "baseline_tree_corr": 0.9286817916553544, "idea_tree_corr": 0.9288227539982717, "baseline_mse": 0.03428776562213898, "idea_mse": 0.038052886724472046 }, { "seed": 3, "baseline_tree_corr": 0.9419077791531315, "idea_tree_corr": 0.9076383879566745, "baseline_mse": 0.0314578041434288, "idea_mse": 0.04973628371953964 }, { "seed": 4, "baseline_tree_corr": 0.9288199555878167, "idea_tree_corr": 0.922377819116332, "baseline_mse": 0.034709829837083817, "idea_mse": 0.04566482454538345 }, { "seed": 5, "baseline_tree_corr": 0.9205480277200384, "idea_tree_corr": 0.9233275703070802, "baseline_mse": 0.03937392309308052, "idea_mse": 0.036613475531339645 }, { "seed": 6, "baseline_tree_corr": 0.9299053733445586, "idea_tree_corr": 0.9330525084728803, "baseline_mse": 0.035850487649440765, "idea_mse": 0.04028519243001938 }, { "seed": 7, "baseline_tree_corr": 0.9210139325087091, "idea_tree_corr": 0.9192451671591447, "baseline_mse": 0.034181930124759674, "idea_mse": 0.04862197861075401 } ], "confirmed": false } }