Стенд-проверка (stage-2) · промт оператора:

(универсальный)

Ответ агента:

{ "worked": false, "confidence": 10, "verdict": "Implemented the certified-tube idea as a Jacobian-aware training intervention on the structurally matched dynamics track, using the shared rnn_small architecture and paired eight-seed protocol. The idea was significantly worse than the tuned baseline: MSE increased from 0.0002974 to 0.0003114, paired delta was +1.398e-05, and permutation p=0.0081. The measured NN sensitivity signature was finite but did not confirm the quantitative prediction, so there is no observed training win.", "metrics": { "baseline": "mean MSE 0.0002974229, best lr 0.01, 8 seeds", "idea": "mean MSE 0.0003114019, lr 0.01 and lambda 0.02, 8 seeds; delta +0.0000139789, p=0.0081, 0/8 paired wins" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 stage2_tube_bench.py", "files": [ "stage2_tube_bench.py", "bench_report.json" ], "limitations": "This MVP uses a differentiable Jacobian/tube sensitivity penalty rather than a full online MPC/QP wrapper with explicit state/action tightening, residual calibration, and fallback execution. It used 800 training samples, 200 test samples, and 12 epochs; no physical hardware or larger cart-pole evaluation was performed.", "bench_report": { "bench_version": 1, "track": "dynamics", "model": "rnn_small", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.01 }, "sweep": [ { "cfg": { "lr": 0.001 }, "mean": 0.001600443793 }, { "cfg": { "lr": 0.003 }, "mean": 0.0008657508879 }, { "cfg": { "lr": 0.01 }, "mean": 0.0003360401788 } ], "full_mean": 0.0002974229255, "full_std": 0.0001259086355 }, "idea": { "best_cfg": { "lr": 0.01, "lambda": 0.02 }, "mean": 0.0003114018746, "std": 0.0001252840425, "settings": { "0.001": 0.0016261089622, "0.003": 0.0008687566078, "0.01": 0.0003114018746 } }, "comparison": { "delta_mean": 1.3978949e-05, "idea_wins": 0, "n_pairs": 8, "p_value": 0.0081, "verdict": "idea worse (significant)", "system_worked": false }, "mechanism_signature": { "predicted_vs_observed_ratio": 0.8521462103, "confirmed": false }, "protocol_notes": { "paired_seeds": [ 0, 1, 2, 3, 4, 5, 6, 7 ], "epochs": 12, "n_train": 800, "n_test": 200, "structural_match": "dynamics/control", "baseline_grid_equals_idea_union": true } }, "system_verdict": "failed", "practical_verdict": "harms", "mechanism_ok": 0, "system_judged": true }