{ "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.003 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 1.596962183713913 }, { "cfg": { "lr": 0.003 }, "mean": 1.552410066127777 }, { "cfg": { "lr": 0.01 }, "mean": 1.5703844726085663 } ], "full": { "mean": 1.5021538734436035, "std": 0.09324438560832148, "per_seed": [ 1.4778438806533813, 1.4308412075042725, 1.5888422727584839, 1.7121129035949707, 1.4590684175491333, 1.4697362184524536, 1.4667506217956543, 1.4120354652404785 ], "n": 8 } }, "idea": { "mean": 1.5022293776273727, "std": 0.09287950268012642, "per_seed": [ 1.4786245822906494, 1.4313784837722778, 1.5867565870285034, 1.7121129035949707, 1.459558367729187, 1.4695805311203003, 1.4680730104446411, 1.4117505550384521 ], "n": 8 }, "comparison": { "delta_mean": 7.550418376922607e-05, "idea_wins": 3, "n_pairs": 8, "per_seed_diffs": [ 0.0007807016372680664, 0.0005372762680053711, -0.0020856857299804688, 0.0, 0.0004899501800537109, -0.0001556873321533203, 0.0013223886489868164, -0.0002849102020263672 ], "p_value": 0.82525, "mde": 0.0008536970299377886, "mde_rel_pct": 0.05683153004696756, "verdict": "no measurable effect", "system_worked": false }, "idea_sweep": [ { "cfg": { "lr": 0.003 }, "result": { "mean": 1.5022293776273727, "std": 0.09287950268012642, "per_seed": [ 1.4786245822906494, 1.4313784837722778, 1.5867565870285034, 1.7121129035949707, 1.459558367729187, 1.4695805311203003, 1.4680730104446411, 1.4117505550384521 ], "n": 8 } }, { "cfg": { "lr": 0.001 }, "result": { "mean": 1.5371521562337875, "std": 0.10299458835449656, "per_seed": [ 1.533307433128357, 1.483575701713562, 1.607698917388916, 1.7639100551605225, 1.5047532320022583, 1.5342274904251099, 1.4773060083389282, 1.3924384117126465 ], "n": 8 } }, { "cfg": { "lr": 0.01 }, "result": { "mean": 1.5104802548885345, "std": 0.10079049945434744, "per_seed": [ 1.4905154705047607, 1.4462878704071045, 1.600508213043213, 1.7361385822296143, 1.4536124467849731, 1.5005030632019043, 1.448508620262146, 1.4077677726745605 ], "n": 8 } } ], "track_justification": "dynamics matches stability/control structure of the finite-horizon collapse monitor", "mechanism_signature": { "probe": "trained RNN predictions under three fixed phase perturbations", "per_seed": [ { "seed": 0, "baseline_metric": 1.4778438806533813, "idea_metric": 1.4786245822906494, "baseline_gap": 0.0034411137457937002, "idea_gap": 0.005794507451355457, "baseline_chern": 1.7380369271595016e-08, "idea_chern": -4.784160125544356e-10 }, { "seed": 1, "baseline_metric": 1.4308412075042725, "idea_metric": 1.4313784837722778, "baseline_gap": 0.08322877436876297, "idea_gap": 0.08180162310600281, "baseline_chern": -5.830075504012453e-10, "idea_chern": 2.12119036466648e-09 }, { "seed": 2, "baseline_metric": 1.5888422727584839, "idea_metric": 1.5867565870285034, "baseline_gap": 0.003892321139574051, "idea_gap": 0.004510408267378807, "baseline_chern": -1.4004964258741766e-09, "idea_chern": -8.674661327411772e-09 }, { "seed": 3, "baseline_metric": 1.7121129035949707, "idea_metric": 1.7121129035949707, "baseline_gap": 0.08939465880393982, "idea_gap": 0.08939465880393982, "baseline_chern": -6.488612319724056e-11, "idea_chern": -6.488612319724056e-11 }, { "seed": 4, "baseline_metric": 1.4590684175491333, "idea_metric": 1.459558367729187, "baseline_gap": 0.03839415684342384, "idea_gap": 0.049591924995183945, "baseline_chern": -2.129452757791829e-09, "idea_chern": 5.6372739935792205e-09 }, { "seed": 5, "baseline_metric": 1.4697362184524536, "idea_metric": 1.4695805311203003, "baseline_gap": 0.10124503821134567, "idea_gap": 0.10104020684957504, "baseline_chern": -4.887011095528017e-09, "idea_chern": -2.0993884286090966e-09 }, { "seed": 6, "baseline_metric": 1.4667506217956543, "idea_metric": 1.4680730104446411, "baseline_gap": 0.079883873462677, "idea_gap": 0.07974080741405487, "baseline_chern": -9.885893837729884e-09, "idea_chern": 1.0790899473853646e-09 }, { "seed": 7, "baseline_metric": 1.4120354652404785, "idea_metric": 1.4117505550384521, "baseline_gap": 0.2863689661026001, "idea_gap": 0.28592658042907715, "baseline_chern": 2.0020123666392965e-09, "idea_chern": 6.683505491112086e-11 } ], "training_checkpoints_seed0": [ { "epoch": 1, "gap": 0.0251762717962265, "chern": 2.9378251026121728e-09, "rounded_chern": 0 }, { "epoch": 3, "gap": 0.058473870158195496, "chern": 2.4474322762181137e-10, "rounded_chern": 0 }, { "epoch": 5, "gap": 0.054124489426612854, "chern": -3.3403893006553517e-09, "rounded_chern": 0 }, { "epoch": 7, "gap": 0.01788416877388954, "chern": -3.5472674164821973e-09, "rounded_chern": 0 }, { "epoch": 9, "gap": 0.015780657529830933, "chern": -4.577209723398702e-09, "rounded_chern": 0 }, { "epoch": 10, "gap": 0.005794507451355457, "chern": -4.784160125544356e-10, "rounded_chern": 0 } ], "predicted": "Chern stays constant while gap is nonzero; sector changes require gap closing", "observed_transition_count": 0, "min_checkpoint_gap": 0.005794507451355457, "confirmed": true } }