ISS-Certified Sampled Optimizer Wrapper / results.json

Failed on benchmark

Raw ⬇ ZIP
 1{
 2  "seed": 7,
 3  "predictions": {
 4    "fixed_stability_boundary": {
 5      "prediction": [
 6        0.19999999999999996,
 7        2.2
 8      ],
 9      "observed_grid": [
10        0.24999999999999997,
11        2.1999999999999997
12      ],
13      "grid_resolution": 0.049999999999999996,
14      "agreement": true
15    },
16    "sampling_interval_certificate": {
17      "prediction_min_M": 2,
18      "observed_min_M": 2,
19      "lambda": 0.2,
20      "q": 0.9,
21      "results": [
22        {
23          "M": 1,
24          "certificate": 0.010000000000000064,
25          "passes": false
26        },
27        {
28          "M": 2,
29          "certificate": -0.14389999999999986,
30          "passes": true
31        },
32        {
33          "M": 3,
34          "certificate": -0.2685589999999998,
35          "passes": true
36        },
37        {
38          "M": 4,
39          "certificate": -0.36953279,
40          "passes": true
41        },
42        {
43          "M": 5,
44          "certificate": -0.45132155989999995,
45          "passes": true
46        },
47        {
48          "M": 6,
49          "certificate": -0.5175704635189999,
50          "passes": true
51        },
52        {
53          "M": 7,
54          "certificate": -0.5712320754503899,
55          "passes": true
56        }
57      ],
58      "agreement": true
59    },
60    "disturbance_scaling": {
61      "prediction": "V_plateau proportional to d^2; bound coefficient c/lambda=8",
62      "c_over_lambda": 8.0,
63      "observed_V_over_d2": [
64        4.0,
65        4.0,
66        4.0,
67        4.0
68      ],
69      "observed_mean_ratio": 4.0,
70      "scaling_relative_spread": 0.0,
71      "agreement": true
72    }
73  },
74  "wrapper_comparison": {
75    "baseline": {
76      "diverged": false,
77      "max_abs": 2.221542239632625e+22,
78      "final_abs": 2.221542239632625e+22,
79      "u": 3.0
80    },
81    "idea": {
82      "diverged": false,
83      "accepted": 92,
84      "rejected": 8,
85      "max_abs": 1.0,
86      "final_abs": 0.0020936161099304974,
87      "u": 3.0,
88      "mean_eta": 0.32025000000000015
89    }
90  },
91  "certificate_sanity": {
92    "all_rollouts_finite": true,
93    "checks": [
94      true,
95      true,
96      true
97    ]
98  }
99}