{ "bench_version": 1, "track": "sequence", "model": "shared_transformer_token_attention", "metric_direction": "lower is better", "n_seeds": 8, "baseline": { "best_cfg": { "lr": 0.003, "tau": 0.25 }, "sweep": [ { "cfg": { "lr": 0.001, "tau": 0.25 }, "mean": 1.0073408037424088 }, { "cfg": { "lr": 0.001, "tau": 0.5 }, "mean": 1.0072430819272995 }, { "cfg": { "lr": 0.003, "tau": 0.25 }, "mean": 0.9897160083055496 }, { "cfg": { "lr": 0.003, "tau": 0.5 }, "mean": 0.9971326589584351 }, { "cfg": { "lr": 0.01, "tau": 0.25 }, "mean": 1.041932761669159 }, { "cfg": { "lr": 0.01, "tau": 0.5 }, "mean": 1.0047774612903595 } ], "full": { "mean": 1.0231029689311981, "std": 0.11072729156070826, "per_seed": [ 0.9939484000205994, 0.8335484266281128, 1.1223986148834229, 1.0089685916900635, 0.9049072861671448, 1.0517245531082153, 1.2106995582580566, 1.0586283206939697 ], "n": 8 } }, "idea": { "mean": 1.0160572454333305, "std": 0.10683002426665564, "per_seed": [ 0.9757922291755676, 0.856389582157135, 1.1297253370285034, 1.0210782289505005, 0.8922733664512634, 1.0258088111877441, 1.2052284479141235, 1.0221619606018066 ], "n": 8 }, "comparison": { "delta_mean": -0.007045723497867584, "idea_wins": 5, "n_pairs": 8, "per_seed_diffs": [ -0.01815617084503174, 0.022841155529022217, 0.007326722145080566, 0.012109637260437012, -0.012633919715881348, -0.02591574192047119, -0.0054711103439331055, -0.036466360092163086 ], "p_value": 0.34205, "mde": 0.016858466245238783, "mde_rel_pct": 1.6477780592162945, "verdict": "no measurable effect", "system_worked": false }, "idea_best_cfg": { "lr": 0.003, "tau": 0.25 }, "idea_configs": [ { "cfg": { "lr": 0.001, "tau": 0.25 }, "mean": 1.0335221663117409 }, { "cfg": { "lr": 0.003, "tau": 0.25 }, "mean": 1.0160572454333305 }, { "cfg": { "lr": 0.01, "tau": 0.25 }, "mean": 1.0669345706701279 } ], "runtime_sec": 50.11480712890625, "mechanism_signature": { "prediction": "two-factor contraction equals product of trained token-query similarities", "predicted_max_abs_error": 0.0, "observed_max_abs_error": 0.0, "predicted_correlation": 1.0, "observed_correlation": 0.9999999403953552, "confirmed": true }, "track_justification": "Sequence forecast has multi-token correlations; conjunction attention operates over token roles/factors.", "custom_track": null }