{ "bench_version": 1, "track": "relational_graph_classification", "model": "local_relational_gnn", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.006, "tau": 0.5 }, "sweep": [ { "cfg": { "lr": 0.0015, "tau": 0.5 }, "mean": 0.012500000186264515 }, { "cfg": { "lr": 0.0015, "tau": 1.0 }, "mean": 0.012500000186264515 }, { "cfg": { "lr": 0.0015, "tau": 2.0 }, "mean": 0.012500000186264515 }, { "cfg": { "lr": 0.003, "tau": 0.5 }, "mean": 0.009375000256113708 }, { "cfg": { "lr": 0.003, "tau": 1.0 }, "mean": 0.009375000256113708 }, { "cfg": { "lr": 0.003, "tau": 2.0 }, "mean": 0.009375000256113708 }, { "cfg": { "lr": 0.006, "tau": 0.5 }, "mean": 0.004687500069849193 }, { "cfg": { "lr": 0.006, "tau": 1.0 }, "mean": 0.004687500069849193 }, { "cfg": { "lr": 0.006, "tau": 2.0 }, "mean": 0.0062500000931322575 } ], "full": { "mean": 0.003906250058207661, "std": 0.004349815973278263, "per_seed": [ 0.0062500000931322575, 0.0, 0.0062500000931322575, 0.0062500000931322575, 0.0, 0.012500000186264515, 0.0, 0.0 ], "n": 8 } }, "idea": { "mean": 0.0031250000465661287, "std": 0.004419417448270373, "per_seed": [ 0.0062500000931322575, 0.0, 0.0062500000931322575, 0.0, 0.0, 0.012500000186264515, 0.0, 0.0 ], "n": 8 }, "comparison": { "delta_mean": -0.0007812500116415322, "idea_wins": 1, "n_pairs": 8, "per_seed_diffs": [ 0.0, 0.0, 0.0, -0.0062500000931322575, 0.0, 0.0, 0.0, 0.0 ], "p_value": 1.0, "mde": 0.0018476562775322238, "mde_rel_pct": 47.300000000000004, "verdict": "no significant win", "system_worked": false }, "idea_sweep": [ { "cfg": { "lr": 0.006, "tau": 0.5, "beta4": 0.75 }, "result": { "mean": 0.003906250058207661, "std": 0.004349815973278263, "per_seed": [ 0.0062500000931322575, 0.0, 0.0062500000931322575, 0.0062500000931322575, 0.0, 0.012500000186264515, 0.0, 0.0 ], "n": 8 } }, { "cfg": { "lr": 0.006, "tau": 0.5, "beta4": 1.5 }, "result": { "mean": 0.003906250058207661, "std": 0.004349815973278263, "per_seed": [ 0.0062500000931322575, 0.0, 0.0062500000931322575, 0.0062500000931322575, 0.0, 0.012500000186264515, 0.0, 0.0 ], "n": 8 } }, { "cfg": { "lr": 0.006, "tau": 0.5, "beta4": 3.0 }, "result": { "mean": 0.0031250000465661287, "std": 0.004419417448270373, "per_seed": [ 0.0062500000931322575, 0.0, 0.0062500000931322575, 0.0, 0.0, 0.012500000186264515, 0.0, 0.0 ], "n": 8 } } ], "protocol_note": "Built-in relational custom track used; no structurally matching built-in track exists.", "mechanism_signature": { "prediction": "trained positive beta4 increases rainbow density while beta4=0 is unary", "observed_mean_density_change": 0.15861905947260094, "per_seed": [ { "seed": 0, "density0": 0.0045055123046040535, "density_beta4": 0.08666115999221802, "delta_density": 0.08215564768761396, "entropy_beta4": 0.8868252635002136 }, { "seed": 1, "density0": 0.0016223047859966755, "density_beta4": 0.22191891074180603, "delta_density": 0.22029660595580935, "entropy_beta4": 1.0981340408325195 }, { "seed": 2, "density0": 0.0005412318860180676, "density_beta4": 0.2031792253255844, "delta_density": 0.20263799343956634, "entropy_beta4": 1.0696096420288086 }, { "seed": 3, "density0": 0.006103047169744968, "density_beta4": 0.18493475019931793, "delta_density": 0.17883170302957296, "entropy_beta4": 1.0392907857894897 }, { "seed": 4, "density0": 2.5453034124822693e-10, "density_beta4": 0.22103427350521088, "delta_density": 0.22103427325068054, "entropy_beta4": 1.096804141998291 }, { "seed": 5, "density0": 0.06863658130168915, "density_beta4": 0.19528405368328094, "delta_density": 0.1266474723815918, "entropy_beta4": 1.0535038709640503 }, { "seed": 6, "density0": 0.05335409194231033, "density_beta4": 0.1256251484155655, "delta_density": 0.07227105647325516, "entropy_beta4": 0.914698600769043 }, { "seed": 7, "density0": 0.04267265647649765, "density_beta4": 0.2077503800392151, "delta_density": 0.16507772356271744, "entropy_beta4": 1.0758920907974243 } ], "beta4_zero_max_change": 0.0, "confirmed": true }, "wall_clock_note": "canonical train_model; equal 18 epochs, batch 64; timing not primary metric" }