Support-Scenario Attention Pruning / results.json

Mechanism failed

Raw ⬇ ZIP
  1{
  2  "seed": 376,
  3  "epsilon": 0.08,
  4  "math_support_order": {
  5    "passed": true,
  6    "trials": 5000
  7  },
  8  "trials": 10,
  9  "summary": {
 10    "dense_edges": {
 11      "mean": 90.0,
 12      "std": 0.0,
 13      "values": [
 14        90,
 15        90,
 16        90,
 17        90,
 18        90,
 19        90,
 20        90,
 21        90,
 22        90,
 23        90
 24      ]
 25    },
 26    "dense_error": {
 27      "mean": 0.0,
 28      "std": 0.0,
 29      "values": [
 30        0.0,
 31        0.0,
 32        0.0,
 33        0.0,
 34        0.0,
 35        0.0,
 36        0.0,
 37        0.0,
 38        0.0,
 39        0.0
 40      ]
 41    },
 42    "independent_edges": {
 43      "mean": 54.4,
 44      "std": 6.6513156593263565,
 45      "values": [
 46        49,
 47        58,
 48        52,
 49        54,
 50        69,
 51        58,
 52        51,
 53        56,
 54        42,
 55        55
 56      ]
 57    },
 58    "independent_error": {
 59      "mean": 0.017553432796253553,
 60      "std": 0.008624784794916214,
 61      "values": [
 62        0.022506316689627826,
 63        0.013834360410346809,
 64        0.008911446350441858,
 65        0.018737568361245835,
 66        0.0030744667863884544,
 67        0.015134302956108023,
 68        0.02023265130592163,
 69        0.017978617342751205,
 70        0.0377164611389749,
 71        0.017408136620728994
 72      ]
 73    },
 74    "independent_violations": {
 75      "mean": 0.1,
 76      "std": 0.30000000000000004,
 77      "values": [
 78        0,
 79        0,
 80        0,
 81        0,
 82        0,
 83        0,
 84        1,
 85        0,
 86        0,
 87        0
 88      ]
 89    },
 90    "structured_edges": {
 91      "mean": 12.0,
 92      "std": 0.0,
 93      "values": [
 94        12,
 95        12,
 96        12,
 97        12,
 98        12,
 99        12,
100        12,
101        12,
102        12,
103        12
104      ]
105    },
106    "structured_error": {
107      "mean": 0.6287995143998892,
108      "std": 0.09071147238479488,
109      "values": [
110        0.5417966494168902,
111        0.6696979843073828,
112        0.555076020448288,
113        0.48412888594648007,
114        0.5198361517819278,
115        0.6579590820419866,
116        0.753156640398068,
117        0.7070106656669161,
118        0.733795276886691,
119        0.6655377871042615
120      ]
121    },
122    "structured_violations": {
123      "mean": 0.0,
124      "std": 0.0,
125      "values": [
126        0,
127        0,
128        0,
129        0,
130        0,
131        0,
132        0,
133        0,
134        0,
135        0
136      ]
137    },
138    "checks": {
139      "mean": 6.0,
140      "std": 0.0,
141      "values": [
142        6,
143        6,
144        6,
145        6,
146        6,
147        6,
148        6,
149        6,
150        6,
151        6
152      ]
153    },
154    "independent_components": {
155      "mean": 2.8,
156      "std": 0.39999999999999997,
157      "values": [
158        3,
159        3,
160        3,
161        2,
162        3,
163        3,
164        3,
165        3,
166        2,
167        3
168      ]
169    },
170    "structured_components": {
171      "mean": 1.0,
172      "std": 0.0,
173      "values": [
174        1,
175        1,
176        1,
177        1,
178        1,
179        1,
180        1,
181        1,
182        1,
183        1
184      ]
185    }
186  }
187}