Critical stochastic min-plus tree layer / results.json

Failed on benchmark

Raw ⬇ ZIP
  1{
  2  "seed": 2176,
  3  "mechanism": {
  4    "q": 0.37,
  5    "depth": 8,
  6    "rows": [
  7      {
  8        "p": 0.1,
  9        "pred_z_depth8": 0.9999503690324584,
 10        "mc_z_depth8": 0.99996,
 11        "delta_pred": 0.6299503690324584,
 12        "delta_mc": 0.62996
 13      },
 14      {
 15        "p": 0.25,
 16        "pred_z_depth8": 0.9850209989877895,
 17        "mc_z_depth8": 0.98434,
 18        "delta_pred": 0.6150209989877895,
 19        "delta_mc": 0.61434
 20      },
 21      {
 22        "p": 0.4,
 23        "pred_z_depth8": 0.7477691817745206,
 24        "mc_z_depth8": 0.74652,
 25        "delta_pred": 0.37776918177452057,
 26        "delta_mc": 0.37651999999999997
 27      },
 28      {
 29        "p": 0.49,
 30        "pred_z_depth8": 0.4079192088912235,
 31        "mc_z_depth8": 0.4062,
 32        "delta_pred": 0.03791920889122352,
 33        "delta_mc": 0.03620000000000001
 34      },
 35      {
 36        "p": 0.5,
 37        "pred_z_depth8": 0.37,
 38        "mc_z_depth8": 0.36814,
 39        "delta_pred": 0.0,
 40        "delta_mc": -0.0018599999999999728
 41      },
 42      {
 43        "p": 0.51,
 44        "pred_z_depth8": 0.3334346669504791,
 45        "mc_z_depth8": 0.33446,
 46        "delta_pred": -0.03656533304952092,
 47        "delta_mc": -0.035540000000000016
 48      },
 49      {
 50        "p": 0.6,
 51        "pred_z_depth8": 0.09707514744005027,
 52        "mc_z_depth8": 0.09618,
 53        "delta_pred": -0.2729248525599497,
 54        "delta_mc": -0.27382
 55      },
 56      {
 57        "p": 0.75,
 58        "pred_z_depth8": 0.0034551828510631815,
 59        "mc_z_depth8": 0.00364,
 60        "delta_pred": -0.36654481714893683,
 61        "delta_mc": -0.36636
 62      },
 63      {
 64        "p": 0.9,
 65        "pred_z_depth8": 5.529732590653404e-06,
 66        "mc_z_depth8": 0.0,
 67        "delta_pred": -0.36999447026740934,
 68        "delta_mc": -0.37
 69      }
 70    ],
 71    "transition_fit_p": 0.49999999999999983,
 72    "transition_pred_p": 0.5,
 73    "max_mc_abs_error": 0.0018599999999999728
 74  },
 75  "depth_sweep": {
 76    "depths": {
 77      "0.25": {
 78        "depths": [
 79          0,
 80          1,
 81          2,
 82          4,
 83          8
 84        ],
 85        "predicted": [
 86          0.37,
 87          0.4865499999999999,
 88          0.61145954875,
 89          0.8287408778641445,
 90          0.9850209989877895
 91        ],
 92        "observed": [
 93          0.37,
 94          0.48583333333333334,
 95          0.6082333333333333,
 96          0.8300333333333333,
 97          0.9853333333333333
 98        ]
 99      },
100      "0.5": {
101        "depths": [
102          0,
103          1,
104          2,
105          4,
106          8
107        ],
108        "predicted": [
109          0.37,
110          0.37,
111          0.37,
112          0.37,
113          0.37
114        ],
115        "observed": [
116          0.37,
117          0.3767666666666667,
118          0.37123333333333336,
119          0.374,
120          0.37206666666666666
121        ]
122      },
123      "0.75": {
124        "depths": [
125          0,
126          1,
127          2,
128          4,
129          8
130        ],
131        "predicted": [
132          0.37,
133          0.25345,
134          0.15884345125,
135          0.05025410990086858,
136          0.0034551828510631815
137        ],
138        "observed": [
139          0.37,
140          0.254,
141          0.15423333333333333,
142          0.0488,
143          0.0038
144        ]
145      }
146    },
147    "critical_q_sweep": [
148      {
149        "q": 0.1,
150        "predicted_depth8": 0.1,
151        "observed_depth8": 0.098
152      },
153      {
154        "q": 0.3,
155        "predicted_depth8": 0.3,
156        "observed_depth8": 0.30133333333333334
157      },
158      {
159        "q": 0.6,
160        "predicted_depth8": 0.6,
161        "observed_depth8": 0.5968333333333333
162      },
163      {
164        "q": 0.9,
165        "predicted_depth8": 0.9,
166        "observed_depth8": 0.9010666666666667
167      }
168    ]
169  },
170  "toy_task": {
171    "sum_accuracy": 0.498,
172    "min_accuracy": 0.604,
173    "critical_stochastic_accuracy": 0.542
174  }
175}