{ "bench_version": 1, "track": "custom_tracks/rough_energy_regression", "model": "mlp_tiny", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.009, "weight_decay": 0.0001 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "mean": 0.17962444573640823 }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001 }, "mean": 0.17939040809869766 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "mean": 0.13639282248914242 }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001 }, "mean": 0.13660208880901337 }, { "cfg": { "lr": 0.009, "weight_decay": 0.0 }, "mean": 0.12427650578320026 }, { "cfg": { "lr": 0.009, "weight_decay": 0.0001 }, "mean": 0.12187139689922333 } ], "full": { "mean": 0.11977773066610098, "std": 0.010381994134392314, "per_seed": [ 0.11285003274679184, 0.12270589917898178, 0.1380033791065216, 0.11392627656459808, 0.12507213652133942, 0.10099826753139496, 0.12710516154766083, 0.11756069213151932 ], "n": 8 } }, "idea": { "mean": 0.777425967156887, "std": 0.1318602192538638, "per_seed": [ 0.9373617172241211, 0.9086369276046753, 0.8551380634307861, 0.555958092212677, 0.8983770608901978, 0.70047527551651, 0.715994656085968, 0.6474659442901611 ], "n": 8, "best_cfg": { "lr": 0.001, "weight_decay": 0.0 }, "sweep": [ { "cfg": { "lr": 0.001, "weight_decay": 0.0 }, "result": { "mean": 0.777425967156887, "std": 0.1318602192538638, "per_seed": [ 0.9373617172241211, 0.9086369276046753, 0.8551380634307861, 0.555958092212677, 0.8983770608901978, 0.70047527551651, 0.715994656085968, 0.6474659442901611 ], "n": 8 } }, { "cfg": { "lr": 0.001, "weight_decay": 0.0001 }, "result": { "mean": 0.7774515226483345, "std": 0.13189202326535374, "per_seed": [ 0.9375675916671753, 0.9086875915527344, 0.8551148772239685, 0.5559515357017517, 0.8983452916145325, 0.7004724144935608, 0.7159877419471741, 0.6474851369857788 ], "n": 8 } }, { "cfg": { "lr": 0.003, "weight_decay": 0.0 }, "result": { "mean": 1.001797802746296, "std": 0.14249134156458224, "per_seed": [ 1.1306720972061157, 1.1415878534317017, 1.0970056056976318, 0.7530442476272583, 1.1628235578536987, 0.9271580576896667, 0.9430878758430481, 0.8590031266212463 ], "n": 8 } }, { "cfg": { "lr": 0.003, "weight_decay": 0.0001 }, "result": { "mean": 1.002461701631546, "std": 0.14312791455365667, "per_seed": [ 1.1407548189163208, 1.1356585025787354, 1.0970054864883423, 0.7530419826507568, 1.163993239402771, 0.9271581768989563, 0.9430776238441467, 0.8590037822723389 ], "n": 8 } }, { "cfg": { "lr": 0.009, "weight_decay": 0.0 }, "result": { "mean": 1.1230522990226746, "std": 0.04363725894180169, "per_seed": [ 1.1245875358581543, 1.1070117950439453, 1.18475341796875, 1.0596675872802734, 1.1676586866378784, 1.1612745523452759, 1.0625452995300293, 1.1169195175170898 ], "n": 8 } }, { "cfg": { "lr": 0.009, "weight_decay": 0.0001 }, "result": { "mean": 1.1208522766828537, "std": 0.040913691981246045, "per_seed": [ 1.1206907033920288, 1.1047009229660034, 1.1829783916473389, 1.0658692121505737, 1.1569230556488037, 1.1598163843154907, 1.06282639503479, 1.1130131483078003 ], "n": 8 } } ] }, "comparison": { "delta_mean": 0.6576482364907861, "idea_wins": 0, "n_pairs": 8, "per_seed_diffs": [ 0.8245116844773293, 0.7859310284256935, 0.7171346843242645, 0.4420318156480789, 0.7733049243688583, 0.599477007985115, 0.5888894945383072, 0.5299052521586418 ], "p_value": 0.0081, "mde": 0.11488058979741761, "mde_rel_pct": 95.9114763308257, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "custom_track": { "name": "rough_energy_regression", "file": "rough_track.py", "domain": "optimization" }, "mechanism_signature": { "quantity": "prediction-vs-observed NN output roughness", "predicted_bound": 10.0, "observed_idea": 0.019673509523272514, "observed_baseline_target_roughness": 0.7095075249671936, "confirmed": true } } }