Upload env_clip nonlinear dominance diagnostics
Browse files- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/command.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/config.yaml +13 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/data_hash.txt +6 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/eval.log +3 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/git_hash.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/metrics.json +0 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/metrics_by_seed.json +2762 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/metrics_by_task.json +117 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/report.md +21 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/split_hash.txt +14 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/table.tex +8 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/train.log +5 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/command.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/config.yaml +13 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/data_hash.txt +6 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/eval.log +3 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/git_hash.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/metrics.json +0 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/metrics_by_seed.json +2762 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/metrics_by_task.json +117 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/report.md +21 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/split_hash.txt +14 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/table.tex +8 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/train.log +5 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/command.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/config.yaml +13 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/data_hash.txt +6 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/eval.log +3 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/git_hash.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/metrics.json +0 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/metrics_by_seed.json +2762 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/metrics_by_task.json +117 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/report.md +21 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/split_hash.txt +14 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/table.tex +8 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/train.log +5 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/command.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/config.yaml +13 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/data_hash.txt +6 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/eval.log +3 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/git_hash.txt +1 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/metrics.json +0 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/metrics_by_seed.json +2762 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/metrics_by_task.json +117 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/report.md +21 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/split_hash.txt +14 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/table.tex +8 -0
- workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/train.log +5 -0
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/command.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
python scripts/eval_nonlinear_dominance_selector.py --calibration-input runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json --calibration-target-index data/cil_charts_rgb_refs/train/index.json --eval-input runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json --eval-target-index data/cil_charts_rgb_refs/test/index.json --checkpoint-template runs/ctt_residual_base_context_obs_seed{seed}/model.pt --out-dir runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test --feature-set basic --target positive_margin --k 8 --bootstrap-samples 1000
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/config.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bootstrap_samples: 1000
|
| 2 |
+
calibration_input: runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
calibration_target_index: data/cil_charts_rgb_refs/train/index.json
|
| 4 |
+
checkpoint_template: runs/ctt_residual_base_context_obs_seed{seed}/model.pt
|
| 5 |
+
eval_input: runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 6 |
+
eval_target_index: data/cil_charts_rgb_refs/test/index.json
|
| 7 |
+
feature_set: basic
|
| 8 |
+
k: 8
|
| 9 |
+
model_types: hgb_classifier,hgb_regressor,rf_regressor
|
| 10 |
+
out_dir: runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test
|
| 11 |
+
seed: 0
|
| 12 |
+
selection_frac: 0.35
|
| 13 |
+
target: positive_margin
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/data_hash.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_input": "06375099001e740a377c402e34b77bf6974be3dc2a468974340ce41eb1b487f0",
|
| 3 |
+
"calibration_target_index": "67973c50072aa87a3b97533b6292b08a8b4d88a95571dc22e91b6e8fd19e0d85",
|
| 4 |
+
"eval_input": "57df43ff4802379dfd60b5209d5a04028d721256406685decededccdbec0d49c",
|
| 5 |
+
"eval_target_index": "dee1b5225485df6624747dd4c5074bcf514685b54017d05e698d2051638fbf36"
|
| 6 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/eval.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
selected model/tau on held-out calibration-selection rows; evaluated on held-out measured rollout rows
|
| 2 |
+
eval_input=runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
num_eval_rows=144
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/git_hash.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
14e81292e2004925f81e0bb4810f6f144bfd87b7
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/metrics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/metrics_by_seed.json
ADDED
|
@@ -0,0 +1,2762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"1073161778/train0": {
|
| 3 |
+
"base_success": 1.0,
|
| 4 |
+
"base_utility": 2.0,
|
| 5 |
+
"coverage": 0.0,
|
| 6 |
+
"execute_generated": 0.0,
|
| 7 |
+
"fallback_rate": 1.0,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.0,
|
| 11 |
+
"predicted_margin": 0.292771638695511,
|
| 12 |
+
"proposal_oracle_success": 1.0,
|
| 13 |
+
"proposal_oracle_utility": 2.0,
|
| 14 |
+
"selected_candidate_index": 4.0,
|
| 15 |
+
"selected_success": 1.0,
|
| 16 |
+
"selected_success_gain_over_base": 0.0,
|
| 17 |
+
"selected_utility": 2.0,
|
| 18 |
+
"selected_utility_gain_over_base": 0.0,
|
| 19 |
+
"selector_regret": 0.0,
|
| 20 |
+
"success_selector_gap": 0.0,
|
| 21 |
+
"success_support_gap": 0.0,
|
| 22 |
+
"support_gap": 0.0,
|
| 23 |
+
"tau": 0.3741559563273496
|
| 24 |
+
},
|
| 25 |
+
"1073161778/train1": {
|
| 26 |
+
"base_success": 1.0,
|
| 27 |
+
"base_utility": 2.0,
|
| 28 |
+
"coverage": 0.0,
|
| 29 |
+
"execute_generated": 0.0,
|
| 30 |
+
"fallback_rate": 1.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.36117233126140574,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.7071996331214905,
|
| 37 |
+
"selected_candidate_index": 3.0,
|
| 38 |
+
"selected_success": 1.0,
|
| 39 |
+
"selected_success_gain_over_base": 0.0,
|
| 40 |
+
"selected_utility": 2.0,
|
| 41 |
+
"selected_utility_gain_over_base": 0.0,
|
| 42 |
+
"selector_regret": 0.0,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.2928003668785095,
|
| 46 |
+
"tau": 0.3741559563273496
|
| 47 |
+
},
|
| 48 |
+
"1073161778/train2": {
|
| 49 |
+
"base_success": 1.0,
|
| 50 |
+
"base_utility": 2.0,
|
| 51 |
+
"coverage": 0.0,
|
| 52 |
+
"execute_generated": 0.0,
|
| 53 |
+
"fallback_rate": 1.0,
|
| 54 |
+
"hidden_chart_oracle_success": 1.0,
|
| 55 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 56 |
+
"outcome_ptr": 0.0,
|
| 57 |
+
"predicted_margin": 0.3457649211345198,
|
| 58 |
+
"proposal_oracle_success": 1.0,
|
| 59 |
+
"proposal_oracle_utility": 2.0,
|
| 60 |
+
"selected_candidate_index": 2.0,
|
| 61 |
+
"selected_success": 1.0,
|
| 62 |
+
"selected_success_gain_over_base": 0.0,
|
| 63 |
+
"selected_utility": 2.0,
|
| 64 |
+
"selected_utility_gain_over_base": 0.0,
|
| 65 |
+
"selector_regret": 0.0,
|
| 66 |
+
"success_selector_gap": 0.0,
|
| 67 |
+
"success_support_gap": 0.0,
|
| 68 |
+
"support_gap": 0.0,
|
| 69 |
+
"tau": 0.3741559563273496
|
| 70 |
+
},
|
| 71 |
+
"1113371261/train0": {
|
| 72 |
+
"base_success": 0.0,
|
| 73 |
+
"base_utility": 0.15842342376708984,
|
| 74 |
+
"coverage": 0.0,
|
| 75 |
+
"execute_generated": 0.0,
|
| 76 |
+
"fallback_rate": 1.0,
|
| 77 |
+
"hidden_chart_oracle_success": 1.0,
|
| 78 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 79 |
+
"outcome_ptr": 0.0,
|
| 80 |
+
"predicted_margin": 0.2748700135153204,
|
| 81 |
+
"proposal_oracle_success": 0.0,
|
| 82 |
+
"proposal_oracle_utility": 0.10274861752986908,
|
| 83 |
+
"selected_candidate_index": 1.0,
|
| 84 |
+
"selected_success": 0.0,
|
| 85 |
+
"selected_success_gain_over_base": 0.0,
|
| 86 |
+
"selected_utility": 0.15842342376708984,
|
| 87 |
+
"selected_utility_gain_over_base": 0.0,
|
| 88 |
+
"selector_regret": 0.0,
|
| 89 |
+
"success_selector_gap": 0.0,
|
| 90 |
+
"success_support_gap": 1.0,
|
| 91 |
+
"support_gap": 1.897251382470131,
|
| 92 |
+
"tau": 0.3741559563273496
|
| 93 |
+
},
|
| 94 |
+
"1113371261/train1": {
|
| 95 |
+
"base_success": 0.0,
|
| 96 |
+
"base_utility": 0.15842342376708984,
|
| 97 |
+
"coverage": 0.0,
|
| 98 |
+
"execute_generated": 0.0,
|
| 99 |
+
"fallback_rate": 1.0,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 1.0,
|
| 103 |
+
"predicted_margin": 0.34929520973604355,
|
| 104 |
+
"proposal_oracle_success": 0.0,
|
| 105 |
+
"proposal_oracle_utility": 0.18093222379684448,
|
| 106 |
+
"selected_candidate_index": 2.0,
|
| 107 |
+
"selected_success": 0.0,
|
| 108 |
+
"selected_success_gain_over_base": 0.0,
|
| 109 |
+
"selected_utility": 0.15842342376708984,
|
| 110 |
+
"selected_utility_gain_over_base": 0.0,
|
| 111 |
+
"selector_regret": 0.02250880002975464,
|
| 112 |
+
"success_selector_gap": 0.0,
|
| 113 |
+
"success_support_gap": 1.0,
|
| 114 |
+
"support_gap": 1.8190677762031555,
|
| 115 |
+
"tau": 0.3741559563273496
|
| 116 |
+
},
|
| 117 |
+
"1113371261/train2": {
|
| 118 |
+
"base_success": 0.0,
|
| 119 |
+
"base_utility": 0.15842342376708984,
|
| 120 |
+
"coverage": 0.0,
|
| 121 |
+
"execute_generated": 0.0,
|
| 122 |
+
"fallback_rate": 1.0,
|
| 123 |
+
"hidden_chart_oracle_success": 1.0,
|
| 124 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 125 |
+
"outcome_ptr": 1.0,
|
| 126 |
+
"predicted_margin": 0.28994114758485556,
|
| 127 |
+
"proposal_oracle_success": 0.0,
|
| 128 |
+
"proposal_oracle_utility": 0.19527167081832886,
|
| 129 |
+
"selected_candidate_index": 4.0,
|
| 130 |
+
"selected_success": 0.0,
|
| 131 |
+
"selected_success_gain_over_base": 0.0,
|
| 132 |
+
"selected_utility": 0.15842342376708984,
|
| 133 |
+
"selected_utility_gain_over_base": 0.0,
|
| 134 |
+
"selector_regret": 0.036848247051239014,
|
| 135 |
+
"success_selector_gap": 0.0,
|
| 136 |
+
"success_support_gap": 1.0,
|
| 137 |
+
"support_gap": 1.8047283291816711,
|
| 138 |
+
"tau": 0.3741559563273496
|
| 139 |
+
},
|
| 140 |
+
"1151410346/train0": {
|
| 141 |
+
"base_success": 0.0,
|
| 142 |
+
"base_utility": 0.2260012924671173,
|
| 143 |
+
"coverage": 0.0,
|
| 144 |
+
"execute_generated": 0.0,
|
| 145 |
+
"fallback_rate": 1.0,
|
| 146 |
+
"hidden_chart_oracle_success": 1.0,
|
| 147 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 148 |
+
"outcome_ptr": 1.0,
|
| 149 |
+
"predicted_margin": 0.32375809904022324,
|
| 150 |
+
"proposal_oracle_success": 0.0,
|
| 151 |
+
"proposal_oracle_utility": 0.8663521409034729,
|
| 152 |
+
"selected_candidate_index": 6.0,
|
| 153 |
+
"selected_success": 0.0,
|
| 154 |
+
"selected_success_gain_over_base": 0.0,
|
| 155 |
+
"selected_utility": 0.2260012924671173,
|
| 156 |
+
"selected_utility_gain_over_base": 0.0,
|
| 157 |
+
"selector_regret": 0.6403508484363556,
|
| 158 |
+
"success_selector_gap": 0.0,
|
| 159 |
+
"success_support_gap": 1.0,
|
| 160 |
+
"support_gap": 1.133647859096527,
|
| 161 |
+
"tau": 0.3741559563273496
|
| 162 |
+
},
|
| 163 |
+
"1151410346/train1": {
|
| 164 |
+
"base_success": 0.0,
|
| 165 |
+
"base_utility": 0.2260012924671173,
|
| 166 |
+
"coverage": 0.0,
|
| 167 |
+
"execute_generated": 0.0,
|
| 168 |
+
"fallback_rate": 1.0,
|
| 169 |
+
"hidden_chart_oracle_success": 1.0,
|
| 170 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 171 |
+
"outcome_ptr": 1.0,
|
| 172 |
+
"predicted_margin": 0.34860626835972375,
|
| 173 |
+
"proposal_oracle_success": 0.0,
|
| 174 |
+
"proposal_oracle_utility": 0.8138919472694397,
|
| 175 |
+
"selected_candidate_index": 7.0,
|
| 176 |
+
"selected_success": 0.0,
|
| 177 |
+
"selected_success_gain_over_base": 0.0,
|
| 178 |
+
"selected_utility": 0.2260012924671173,
|
| 179 |
+
"selected_utility_gain_over_base": 0.0,
|
| 180 |
+
"selector_regret": 0.5878906548023224,
|
| 181 |
+
"success_selector_gap": 0.0,
|
| 182 |
+
"success_support_gap": 1.0,
|
| 183 |
+
"support_gap": 1.1861080527305603,
|
| 184 |
+
"tau": 0.3741559563273496
|
| 185 |
+
},
|
| 186 |
+
"1151410346/train2": {
|
| 187 |
+
"base_success": 0.0,
|
| 188 |
+
"base_utility": 0.2260012924671173,
|
| 189 |
+
"coverage": 0.0,
|
| 190 |
+
"execute_generated": 0.0,
|
| 191 |
+
"fallback_rate": 1.0,
|
| 192 |
+
"hidden_chart_oracle_success": 1.0,
|
| 193 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 194 |
+
"outcome_ptr": 0.0,
|
| 195 |
+
"predicted_margin": 0.3657069596994634,
|
| 196 |
+
"proposal_oracle_success": 0.0,
|
| 197 |
+
"proposal_oracle_utility": 0.21912741661071777,
|
| 198 |
+
"selected_candidate_index": 6.0,
|
| 199 |
+
"selected_success": 0.0,
|
| 200 |
+
"selected_success_gain_over_base": 0.0,
|
| 201 |
+
"selected_utility": 0.2260012924671173,
|
| 202 |
+
"selected_utility_gain_over_base": 0.0,
|
| 203 |
+
"selector_regret": 0.0,
|
| 204 |
+
"success_selector_gap": 0.0,
|
| 205 |
+
"success_support_gap": 1.0,
|
| 206 |
+
"support_gap": 1.7808725833892822,
|
| 207 |
+
"tau": 0.3741559563273496
|
| 208 |
+
},
|
| 209 |
+
"1261930456/train0": {
|
| 210 |
+
"base_success": 1.0,
|
| 211 |
+
"base_utility": 2.0,
|
| 212 |
+
"coverage": 1.0,
|
| 213 |
+
"execute_generated": 1.0,
|
| 214 |
+
"fallback_rate": 0.0,
|
| 215 |
+
"hidden_chart_oracle_success": 1.0,
|
| 216 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 217 |
+
"outcome_ptr": 0.0,
|
| 218 |
+
"predicted_margin": 0.49362379866268385,
|
| 219 |
+
"proposal_oracle_success": 1.0,
|
| 220 |
+
"proposal_oracle_utility": 2.0,
|
| 221 |
+
"selected_candidate_index": 3.0,
|
| 222 |
+
"selected_success": 0.0,
|
| 223 |
+
"selected_success_gain_over_base": -1.0,
|
| 224 |
+
"selected_utility": 0.06716175377368927,
|
| 225 |
+
"selected_utility_gain_over_base": -1.9328382462263107,
|
| 226 |
+
"selector_regret": 1.9328382462263107,
|
| 227 |
+
"success_selector_gap": 1.0,
|
| 228 |
+
"success_support_gap": 0.0,
|
| 229 |
+
"support_gap": 0.0,
|
| 230 |
+
"tau": 0.3741559563273496
|
| 231 |
+
},
|
| 232 |
+
"1261930456/train1": {
|
| 233 |
+
"base_success": 1.0,
|
| 234 |
+
"base_utility": 2.0,
|
| 235 |
+
"coverage": 1.0,
|
| 236 |
+
"execute_generated": 1.0,
|
| 237 |
+
"fallback_rate": 0.0,
|
| 238 |
+
"hidden_chart_oracle_success": 1.0,
|
| 239 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 240 |
+
"outcome_ptr": 0.0,
|
| 241 |
+
"predicted_margin": 0.5844950408029461,
|
| 242 |
+
"proposal_oracle_success": 1.0,
|
| 243 |
+
"proposal_oracle_utility": 2.0,
|
| 244 |
+
"selected_candidate_index": 2.0,
|
| 245 |
+
"selected_success": 1.0,
|
| 246 |
+
"selected_success_gain_over_base": 0.0,
|
| 247 |
+
"selected_utility": 2.0,
|
| 248 |
+
"selected_utility_gain_over_base": 0.0,
|
| 249 |
+
"selector_regret": 0.0,
|
| 250 |
+
"success_selector_gap": 0.0,
|
| 251 |
+
"success_support_gap": 0.0,
|
| 252 |
+
"support_gap": 0.0,
|
| 253 |
+
"tau": 0.3741559563273496
|
| 254 |
+
},
|
| 255 |
+
"1261930456/train2": {
|
| 256 |
+
"base_success": 1.0,
|
| 257 |
+
"base_utility": 2.0,
|
| 258 |
+
"coverage": 1.0,
|
| 259 |
+
"execute_generated": 1.0,
|
| 260 |
+
"fallback_rate": 0.0,
|
| 261 |
+
"hidden_chart_oracle_success": 1.0,
|
| 262 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 263 |
+
"outcome_ptr": 0.0,
|
| 264 |
+
"predicted_margin": 0.5690133983051641,
|
| 265 |
+
"proposal_oracle_success": 1.0,
|
| 266 |
+
"proposal_oracle_utility": 2.0,
|
| 267 |
+
"selected_candidate_index": 4.0,
|
| 268 |
+
"selected_success": 0.0,
|
| 269 |
+
"selected_success_gain_over_base": -1.0,
|
| 270 |
+
"selected_utility": 0.08501242101192474,
|
| 271 |
+
"selected_utility_gain_over_base": -1.9149875789880753,
|
| 272 |
+
"selector_regret": 1.9149875789880753,
|
| 273 |
+
"success_selector_gap": 1.0,
|
| 274 |
+
"success_support_gap": 0.0,
|
| 275 |
+
"support_gap": 0.0,
|
| 276 |
+
"tau": 0.3741559563273496
|
| 277 |
+
},
|
| 278 |
+
"1324133122/train0": {
|
| 279 |
+
"base_success": 0.0,
|
| 280 |
+
"base_utility": 0.09220491349697113,
|
| 281 |
+
"coverage": 0.0,
|
| 282 |
+
"execute_generated": 0.0,
|
| 283 |
+
"fallback_rate": 1.0,
|
| 284 |
+
"hidden_chart_oracle_success": 1.0,
|
| 285 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 286 |
+
"outcome_ptr": 0.0,
|
| 287 |
+
"predicted_margin": 0.30291602696952474,
|
| 288 |
+
"proposal_oracle_success": 0.0,
|
| 289 |
+
"proposal_oracle_utility": 0.054989203810691833,
|
| 290 |
+
"selected_candidate_index": 2.0,
|
| 291 |
+
"selected_success": 0.0,
|
| 292 |
+
"selected_success_gain_over_base": 0.0,
|
| 293 |
+
"selected_utility": 0.09220491349697113,
|
| 294 |
+
"selected_utility_gain_over_base": 0.0,
|
| 295 |
+
"selector_regret": 0.0,
|
| 296 |
+
"success_selector_gap": 0.0,
|
| 297 |
+
"success_support_gap": 1.0,
|
| 298 |
+
"support_gap": 1.9450107961893082,
|
| 299 |
+
"tau": 0.3741559563273496
|
| 300 |
+
},
|
| 301 |
+
"1324133122/train1": {
|
| 302 |
+
"base_success": 0.0,
|
| 303 |
+
"base_utility": 0.09220491349697113,
|
| 304 |
+
"coverage": 0.0,
|
| 305 |
+
"execute_generated": 0.0,
|
| 306 |
+
"fallback_rate": 1.0,
|
| 307 |
+
"hidden_chart_oracle_success": 1.0,
|
| 308 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 309 |
+
"outcome_ptr": 1.0,
|
| 310 |
+
"predicted_margin": 0.3015169653629154,
|
| 311 |
+
"proposal_oracle_success": 0.0,
|
| 312 |
+
"proposal_oracle_utility": 0.1324586570262909,
|
| 313 |
+
"selected_candidate_index": 6.0,
|
| 314 |
+
"selected_success": 0.0,
|
| 315 |
+
"selected_success_gain_over_base": 0.0,
|
| 316 |
+
"selected_utility": 0.09220491349697113,
|
| 317 |
+
"selected_utility_gain_over_base": 0.0,
|
| 318 |
+
"selector_regret": 0.04025374352931976,
|
| 319 |
+
"success_selector_gap": 0.0,
|
| 320 |
+
"success_support_gap": 1.0,
|
| 321 |
+
"support_gap": 1.867541342973709,
|
| 322 |
+
"tau": 0.3741559563273496
|
| 323 |
+
},
|
| 324 |
+
"1324133122/train2": {
|
| 325 |
+
"base_success": 0.0,
|
| 326 |
+
"base_utility": 0.09220491349697113,
|
| 327 |
+
"coverage": 0.0,
|
| 328 |
+
"execute_generated": 0.0,
|
| 329 |
+
"fallback_rate": 1.0,
|
| 330 |
+
"hidden_chart_oracle_success": 1.0,
|
| 331 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 332 |
+
"outcome_ptr": 1.0,
|
| 333 |
+
"predicted_margin": 0.2829121416380268,
|
| 334 |
+
"proposal_oracle_success": 0.0,
|
| 335 |
+
"proposal_oracle_utility": 0.19291165471076965,
|
| 336 |
+
"selected_candidate_index": 2.0,
|
| 337 |
+
"selected_success": 0.0,
|
| 338 |
+
"selected_success_gain_over_base": 0.0,
|
| 339 |
+
"selected_utility": 0.09220491349697113,
|
| 340 |
+
"selected_utility_gain_over_base": 0.0,
|
| 341 |
+
"selector_regret": 0.10070674121379852,
|
| 342 |
+
"success_selector_gap": 0.0,
|
| 343 |
+
"success_support_gap": 1.0,
|
| 344 |
+
"support_gap": 1.8070883452892303,
|
| 345 |
+
"tau": 0.3741559563273496
|
| 346 |
+
},
|
| 347 |
+
"1324642411/train0": {
|
| 348 |
+
"base_success": 0.0,
|
| 349 |
+
"base_utility": 0.10647052526473999,
|
| 350 |
+
"coverage": 1.0,
|
| 351 |
+
"execute_generated": 1.0,
|
| 352 |
+
"fallback_rate": 0.0,
|
| 353 |
+
"hidden_chart_oracle_success": 1.0,
|
| 354 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 355 |
+
"outcome_ptr": 1.0,
|
| 356 |
+
"predicted_margin": 0.42792806960140634,
|
| 357 |
+
"proposal_oracle_success": 0.0,
|
| 358 |
+
"proposal_oracle_utility": 0.17193320393562317,
|
| 359 |
+
"selected_candidate_index": 3.0,
|
| 360 |
+
"selected_success": 0.0,
|
| 361 |
+
"selected_success_gain_over_base": 0.0,
|
| 362 |
+
"selected_utility": 0.08104583621025085,
|
| 363 |
+
"selected_utility_gain_over_base": -0.025424689054489136,
|
| 364 |
+
"selector_regret": 0.09088736772537231,
|
| 365 |
+
"success_selector_gap": 0.0,
|
| 366 |
+
"success_support_gap": 1.0,
|
| 367 |
+
"support_gap": 1.8280667960643768,
|
| 368 |
+
"tau": 0.3741559563273496
|
| 369 |
+
},
|
| 370 |
+
"1324642411/train1": {
|
| 371 |
+
"base_success": 0.0,
|
| 372 |
+
"base_utility": 0.10647052526473999,
|
| 373 |
+
"coverage": 1.0,
|
| 374 |
+
"execute_generated": 1.0,
|
| 375 |
+
"fallback_rate": 0.0,
|
| 376 |
+
"hidden_chart_oracle_success": 1.0,
|
| 377 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 378 |
+
"outcome_ptr": 1.0,
|
| 379 |
+
"predicted_margin": 0.3921674767850758,
|
| 380 |
+
"proposal_oracle_success": 0.0,
|
| 381 |
+
"proposal_oracle_utility": 0.1836909055709839,
|
| 382 |
+
"selected_candidate_index": 1.0,
|
| 383 |
+
"selected_success": 0.0,
|
| 384 |
+
"selected_success_gain_over_base": 0.0,
|
| 385 |
+
"selected_utility": 0.10393516719341278,
|
| 386 |
+
"selected_utility_gain_over_base": -0.0025353580713272095,
|
| 387 |
+
"selector_regret": 0.0797557383775711,
|
| 388 |
+
"success_selector_gap": 0.0,
|
| 389 |
+
"success_support_gap": 1.0,
|
| 390 |
+
"support_gap": 1.8163090944290161,
|
| 391 |
+
"tau": 0.3741559563273496
|
| 392 |
+
},
|
| 393 |
+
"1324642411/train2": {
|
| 394 |
+
"base_success": 0.0,
|
| 395 |
+
"base_utility": 0.10647052526473999,
|
| 396 |
+
"coverage": 0.0,
|
| 397 |
+
"execute_generated": 0.0,
|
| 398 |
+
"fallback_rate": 1.0,
|
| 399 |
+
"hidden_chart_oracle_success": 1.0,
|
| 400 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 401 |
+
"outcome_ptr": 1.0,
|
| 402 |
+
"predicted_margin": 0.31840010979467775,
|
| 403 |
+
"proposal_oracle_success": 1.0,
|
| 404 |
+
"proposal_oracle_utility": 2.0,
|
| 405 |
+
"selected_candidate_index": 7.0,
|
| 406 |
+
"selected_success": 0.0,
|
| 407 |
+
"selected_success_gain_over_base": 0.0,
|
| 408 |
+
"selected_utility": 0.10647052526473999,
|
| 409 |
+
"selected_utility_gain_over_base": 0.0,
|
| 410 |
+
"selector_regret": 1.89352947473526,
|
| 411 |
+
"success_selector_gap": 1.0,
|
| 412 |
+
"success_support_gap": 0.0,
|
| 413 |
+
"support_gap": 0.0,
|
| 414 |
+
"tau": 0.3741559563273496
|
| 415 |
+
},
|
| 416 |
+
"1375492786/train0": {
|
| 417 |
+
"base_success": 1.0,
|
| 418 |
+
"base_utility": 2.0,
|
| 419 |
+
"coverage": 0.0,
|
| 420 |
+
"execute_generated": 0.0,
|
| 421 |
+
"fallback_rate": 1.0,
|
| 422 |
+
"hidden_chart_oracle_success": 1.0,
|
| 423 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 424 |
+
"outcome_ptr": 0.0,
|
| 425 |
+
"predicted_margin": 0.27576249231752253,
|
| 426 |
+
"proposal_oracle_success": 1.0,
|
| 427 |
+
"proposal_oracle_utility": 2.0,
|
| 428 |
+
"selected_candidate_index": 7.0,
|
| 429 |
+
"selected_success": 1.0,
|
| 430 |
+
"selected_success_gain_over_base": 0.0,
|
| 431 |
+
"selected_utility": 2.0,
|
| 432 |
+
"selected_utility_gain_over_base": 0.0,
|
| 433 |
+
"selector_regret": 0.0,
|
| 434 |
+
"success_selector_gap": 0.0,
|
| 435 |
+
"success_support_gap": 0.0,
|
| 436 |
+
"support_gap": 0.0,
|
| 437 |
+
"tau": 0.3741559563273496
|
| 438 |
+
},
|
| 439 |
+
"1375492786/train1": {
|
| 440 |
+
"base_success": 1.0,
|
| 441 |
+
"base_utility": 2.0,
|
| 442 |
+
"coverage": 0.0,
|
| 443 |
+
"execute_generated": 0.0,
|
| 444 |
+
"fallback_rate": 1.0,
|
| 445 |
+
"hidden_chart_oracle_success": 1.0,
|
| 446 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 447 |
+
"outcome_ptr": 0.0,
|
| 448 |
+
"predicted_margin": 0.30671589390658466,
|
| 449 |
+
"proposal_oracle_success": 0.0,
|
| 450 |
+
"proposal_oracle_utility": 0.08251869678497314,
|
| 451 |
+
"selected_candidate_index": 2.0,
|
| 452 |
+
"selected_success": 1.0,
|
| 453 |
+
"selected_success_gain_over_base": 0.0,
|
| 454 |
+
"selected_utility": 2.0,
|
| 455 |
+
"selected_utility_gain_over_base": 0.0,
|
| 456 |
+
"selector_regret": 0.0,
|
| 457 |
+
"success_selector_gap": 0.0,
|
| 458 |
+
"success_support_gap": 1.0,
|
| 459 |
+
"support_gap": 1.9174813032150269,
|
| 460 |
+
"tau": 0.3741559563273496
|
| 461 |
+
},
|
| 462 |
+
"1375492786/train2": {
|
| 463 |
+
"base_success": 1.0,
|
| 464 |
+
"base_utility": 2.0,
|
| 465 |
+
"coverage": 0.0,
|
| 466 |
+
"execute_generated": 0.0,
|
| 467 |
+
"fallback_rate": 1.0,
|
| 468 |
+
"hidden_chart_oracle_success": 1.0,
|
| 469 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 470 |
+
"outcome_ptr": 0.0,
|
| 471 |
+
"predicted_margin": 0.2818032504385155,
|
| 472 |
+
"proposal_oracle_success": 1.0,
|
| 473 |
+
"proposal_oracle_utility": 2.0,
|
| 474 |
+
"selected_candidate_index": 7.0,
|
| 475 |
+
"selected_success": 1.0,
|
| 476 |
+
"selected_success_gain_over_base": 0.0,
|
| 477 |
+
"selected_utility": 2.0,
|
| 478 |
+
"selected_utility_gain_over_base": 0.0,
|
| 479 |
+
"selector_regret": 0.0,
|
| 480 |
+
"success_selector_gap": 0.0,
|
| 481 |
+
"success_support_gap": 0.0,
|
| 482 |
+
"support_gap": 0.0,
|
| 483 |
+
"tau": 0.3741559563273496
|
| 484 |
+
},
|
| 485 |
+
"141984615/train0": {
|
| 486 |
+
"base_success": 0.0,
|
| 487 |
+
"base_utility": 0.10283424705266953,
|
| 488 |
+
"coverage": 0.0,
|
| 489 |
+
"execute_generated": 0.0,
|
| 490 |
+
"fallback_rate": 1.0,
|
| 491 |
+
"hidden_chart_oracle_success": 0.0,
|
| 492 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 493 |
+
"outcome_ptr": 0.0,
|
| 494 |
+
"predicted_margin": 0.37348877935876434,
|
| 495 |
+
"proposal_oracle_success": 0.0,
|
| 496 |
+
"proposal_oracle_utility": 0.007291515823453665,
|
| 497 |
+
"selected_candidate_index": 2.0,
|
| 498 |
+
"selected_success": 0.0,
|
| 499 |
+
"selected_success_gain_over_base": 0.0,
|
| 500 |
+
"selected_utility": 0.10283424705266953,
|
| 501 |
+
"selected_utility_gain_over_base": 0.0,
|
| 502 |
+
"selector_regret": 0.0,
|
| 503 |
+
"success_selector_gap": 0.0,
|
| 504 |
+
"success_support_gap": 0.0,
|
| 505 |
+
"support_gap": 0.27848575497046113,
|
| 506 |
+
"tau": 0.3741559563273496
|
| 507 |
+
},
|
| 508 |
+
"141984615/train1": {
|
| 509 |
+
"base_success": 0.0,
|
| 510 |
+
"base_utility": 0.10283424705266953,
|
| 511 |
+
"coverage": 1.0,
|
| 512 |
+
"execute_generated": 1.0,
|
| 513 |
+
"fallback_rate": 0.0,
|
| 514 |
+
"hidden_chart_oracle_success": 0.0,
|
| 515 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 516 |
+
"outcome_ptr": 0.0,
|
| 517 |
+
"predicted_margin": 0.40137543246827484,
|
| 518 |
+
"proposal_oracle_success": 0.0,
|
| 519 |
+
"proposal_oracle_utility": 0.037011127918958664,
|
| 520 |
+
"selected_candidate_index": 0.0,
|
| 521 |
+
"selected_success": 0.0,
|
| 522 |
+
"selected_success_gain_over_base": 0.0,
|
| 523 |
+
"selected_utility": 0.037011127918958664,
|
| 524 |
+
"selected_utility_gain_over_base": -0.06582311913371086,
|
| 525 |
+
"selector_regret": 0.0,
|
| 526 |
+
"success_selector_gap": 0.0,
|
| 527 |
+
"success_support_gap": 0.0,
|
| 528 |
+
"support_gap": 0.24876614287495613,
|
| 529 |
+
"tau": 0.3741559563273496
|
| 530 |
+
},
|
| 531 |
+
"141984615/train2": {
|
| 532 |
+
"base_success": 0.0,
|
| 533 |
+
"base_utility": 0.10283424705266953,
|
| 534 |
+
"coverage": 0.0,
|
| 535 |
+
"execute_generated": 0.0,
|
| 536 |
+
"fallback_rate": 1.0,
|
| 537 |
+
"hidden_chart_oracle_success": 0.0,
|
| 538 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 539 |
+
"outcome_ptr": 0.0,
|
| 540 |
+
"predicted_margin": 0.3033646357953552,
|
| 541 |
+
"proposal_oracle_success": 0.0,
|
| 542 |
+
"proposal_oracle_utility": 0.030228236690163612,
|
| 543 |
+
"selected_candidate_index": 4.0,
|
| 544 |
+
"selected_success": 0.0,
|
| 545 |
+
"selected_success_gain_over_base": 0.0,
|
| 546 |
+
"selected_utility": 0.10283424705266953,
|
| 547 |
+
"selected_utility_gain_over_base": 0.0,
|
| 548 |
+
"selector_regret": 0.0,
|
| 549 |
+
"success_selector_gap": 0.0,
|
| 550 |
+
"success_support_gap": 0.0,
|
| 551 |
+
"support_gap": 0.2555490341037512,
|
| 552 |
+
"tau": 0.3741559563273496
|
| 553 |
+
},
|
| 554 |
+
"1461069713/train0": {
|
| 555 |
+
"base_success": 0.0,
|
| 556 |
+
"base_utility": 0.0939030647277832,
|
| 557 |
+
"coverage": 0.0,
|
| 558 |
+
"execute_generated": 0.0,
|
| 559 |
+
"fallback_rate": 1.0,
|
| 560 |
+
"hidden_chart_oracle_success": 0.0,
|
| 561 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 562 |
+
"outcome_ptr": 0.0,
|
| 563 |
+
"predicted_margin": 0.3556138453891751,
|
| 564 |
+
"proposal_oracle_success": 0.0,
|
| 565 |
+
"proposal_oracle_utility": 0.06019836664199829,
|
| 566 |
+
"selected_candidate_index": 4.0,
|
| 567 |
+
"selected_success": 0.0,
|
| 568 |
+
"selected_success_gain_over_base": 0.0,
|
| 569 |
+
"selected_utility": 0.0939030647277832,
|
| 570 |
+
"selected_utility_gain_over_base": 0.0,
|
| 571 |
+
"selector_regret": 0.0,
|
| 572 |
+
"success_selector_gap": 0.0,
|
| 573 |
+
"success_support_gap": 0.0,
|
| 574 |
+
"support_gap": 0.0991440862417221,
|
| 575 |
+
"tau": 0.3741559563273496
|
| 576 |
+
},
|
| 577 |
+
"1461069713/train1": {
|
| 578 |
+
"base_success": 0.0,
|
| 579 |
+
"base_utility": 0.0939030647277832,
|
| 580 |
+
"coverage": 1.0,
|
| 581 |
+
"execute_generated": 1.0,
|
| 582 |
+
"fallback_rate": 0.0,
|
| 583 |
+
"hidden_chart_oracle_success": 0.0,
|
| 584 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 585 |
+
"outcome_ptr": 0.0,
|
| 586 |
+
"predicted_margin": 0.506786610273882,
|
| 587 |
+
"proposal_oracle_success": 0.0,
|
| 588 |
+
"proposal_oracle_utility": 0.016585012897849083,
|
| 589 |
+
"selected_candidate_index": 4.0,
|
| 590 |
+
"selected_success": 0.0,
|
| 591 |
+
"selected_success_gain_over_base": 0.0,
|
| 592 |
+
"selected_utility": 0.016585012897849083,
|
| 593 |
+
"selected_utility_gain_over_base": -0.07731805182993412,
|
| 594 |
+
"selector_regret": 0.0,
|
| 595 |
+
"success_selector_gap": 0.0,
|
| 596 |
+
"success_support_gap": 0.0,
|
| 597 |
+
"support_gap": 0.14275743998587132,
|
| 598 |
+
"tau": 0.3741559563273496
|
| 599 |
+
},
|
| 600 |
+
"1461069713/train2": {
|
| 601 |
+
"base_success": 0.0,
|
| 602 |
+
"base_utility": 0.0939030647277832,
|
| 603 |
+
"coverage": 1.0,
|
| 604 |
+
"execute_generated": 1.0,
|
| 605 |
+
"fallback_rate": 0.0,
|
| 606 |
+
"hidden_chart_oracle_success": 0.0,
|
| 607 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 608 |
+
"outcome_ptr": 1.0,
|
| 609 |
+
"predicted_margin": 0.3809741420013,
|
| 610 |
+
"proposal_oracle_success": 0.0,
|
| 611 |
+
"proposal_oracle_utility": 0.09970339387655258,
|
| 612 |
+
"selected_candidate_index": 3.0,
|
| 613 |
+
"selected_success": 0.0,
|
| 614 |
+
"selected_success_gain_over_base": 0.0,
|
| 615 |
+
"selected_utility": 0.06527054309844971,
|
| 616 |
+
"selected_utility_gain_over_base": -0.028632521629333496,
|
| 617 |
+
"selector_regret": 0.034432850778102875,
|
| 618 |
+
"success_selector_gap": 0.0,
|
| 619 |
+
"success_support_gap": 0.0,
|
| 620 |
+
"support_gap": 0.059639059007167816,
|
| 621 |
+
"tau": 0.3741559563273496
|
| 622 |
+
},
|
| 623 |
+
"1480856810/train0": {
|
| 624 |
+
"base_success": 0.0,
|
| 625 |
+
"base_utility": 0.08703407645225525,
|
| 626 |
+
"coverage": 1.0,
|
| 627 |
+
"execute_generated": 1.0,
|
| 628 |
+
"fallback_rate": 0.0,
|
| 629 |
+
"hidden_chart_oracle_success": 0.0,
|
| 630 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 631 |
+
"outcome_ptr": 1.0,
|
| 632 |
+
"predicted_margin": 0.39508824247975904,
|
| 633 |
+
"proposal_oracle_success": 1.0,
|
| 634 |
+
"proposal_oracle_utility": 2.0,
|
| 635 |
+
"selected_candidate_index": 2.0,
|
| 636 |
+
"selected_success": 1.0,
|
| 637 |
+
"selected_success_gain_over_base": 1.0,
|
| 638 |
+
"selected_utility": 2.0,
|
| 639 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 640 |
+
"selector_regret": 0.0,
|
| 641 |
+
"success_selector_gap": 0.0,
|
| 642 |
+
"success_support_gap": 0.0,
|
| 643 |
+
"support_gap": 0.0,
|
| 644 |
+
"tau": 0.3741559563273496
|
| 645 |
+
},
|
| 646 |
+
"1480856810/train1": {
|
| 647 |
+
"base_success": 0.0,
|
| 648 |
+
"base_utility": 0.08703407645225525,
|
| 649 |
+
"coverage": 1.0,
|
| 650 |
+
"execute_generated": 1.0,
|
| 651 |
+
"fallback_rate": 0.0,
|
| 652 |
+
"hidden_chart_oracle_success": 0.0,
|
| 653 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 654 |
+
"outcome_ptr": 1.0,
|
| 655 |
+
"predicted_margin": 0.5930611397299111,
|
| 656 |
+
"proposal_oracle_success": 1.0,
|
| 657 |
+
"proposal_oracle_utility": 2.0,
|
| 658 |
+
"selected_candidate_index": 4.0,
|
| 659 |
+
"selected_success": 1.0,
|
| 660 |
+
"selected_success_gain_over_base": 1.0,
|
| 661 |
+
"selected_utility": 2.0,
|
| 662 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 663 |
+
"selector_regret": 0.0,
|
| 664 |
+
"success_selector_gap": 0.0,
|
| 665 |
+
"success_support_gap": 0.0,
|
| 666 |
+
"support_gap": 0.0,
|
| 667 |
+
"tau": 0.3741559563273496
|
| 668 |
+
},
|
| 669 |
+
"1480856810/train2": {
|
| 670 |
+
"base_success": 0.0,
|
| 671 |
+
"base_utility": 0.08703407645225525,
|
| 672 |
+
"coverage": 1.0,
|
| 673 |
+
"execute_generated": 1.0,
|
| 674 |
+
"fallback_rate": 0.0,
|
| 675 |
+
"hidden_chart_oracle_success": 0.0,
|
| 676 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 677 |
+
"outcome_ptr": 1.0,
|
| 678 |
+
"predicted_margin": 0.41143741228233793,
|
| 679 |
+
"proposal_oracle_success": 1.0,
|
| 680 |
+
"proposal_oracle_utility": 2.0,
|
| 681 |
+
"selected_candidate_index": 1.0,
|
| 682 |
+
"selected_success": 0.0,
|
| 683 |
+
"selected_success_gain_over_base": 0.0,
|
| 684 |
+
"selected_utility": 2.0876526832580566e-05,
|
| 685 |
+
"selected_utility_gain_over_base": -0.08701319992542267,
|
| 686 |
+
"selector_regret": 1.9999791234731674,
|
| 687 |
+
"success_selector_gap": 1.0,
|
| 688 |
+
"success_support_gap": 0.0,
|
| 689 |
+
"support_gap": 0.0,
|
| 690 |
+
"tau": 0.3741559563273496
|
| 691 |
+
},
|
| 692 |
+
"1509980664/train0": {
|
| 693 |
+
"base_success": 0.0,
|
| 694 |
+
"base_utility": 0.8334100246429443,
|
| 695 |
+
"coverage": 0.0,
|
| 696 |
+
"execute_generated": 0.0,
|
| 697 |
+
"fallback_rate": 1.0,
|
| 698 |
+
"hidden_chart_oracle_success": 1.0,
|
| 699 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 700 |
+
"outcome_ptr": 1.0,
|
| 701 |
+
"predicted_margin": 0.29567751322199776,
|
| 702 |
+
"proposal_oracle_success": 1.0,
|
| 703 |
+
"proposal_oracle_utility": 2.0,
|
| 704 |
+
"selected_candidate_index": 6.0,
|
| 705 |
+
"selected_success": 0.0,
|
| 706 |
+
"selected_success_gain_over_base": 0.0,
|
| 707 |
+
"selected_utility": 0.8334100246429443,
|
| 708 |
+
"selected_utility_gain_over_base": 0.0,
|
| 709 |
+
"selector_regret": 1.1665899753570557,
|
| 710 |
+
"success_selector_gap": 1.0,
|
| 711 |
+
"success_support_gap": 0.0,
|
| 712 |
+
"support_gap": 0.0,
|
| 713 |
+
"tau": 0.3741559563273496
|
| 714 |
+
},
|
| 715 |
+
"1509980664/train1": {
|
| 716 |
+
"base_success": 0.0,
|
| 717 |
+
"base_utility": 0.8334100246429443,
|
| 718 |
+
"coverage": 0.0,
|
| 719 |
+
"execute_generated": 0.0,
|
| 720 |
+
"fallback_rate": 1.0,
|
| 721 |
+
"hidden_chart_oracle_success": 1.0,
|
| 722 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 723 |
+
"outcome_ptr": 1.0,
|
| 724 |
+
"predicted_margin": 0.32003263953794914,
|
| 725 |
+
"proposal_oracle_success": 1.0,
|
| 726 |
+
"proposal_oracle_utility": 2.0,
|
| 727 |
+
"selected_candidate_index": 7.0,
|
| 728 |
+
"selected_success": 0.0,
|
| 729 |
+
"selected_success_gain_over_base": 0.0,
|
| 730 |
+
"selected_utility": 0.8334100246429443,
|
| 731 |
+
"selected_utility_gain_over_base": 0.0,
|
| 732 |
+
"selector_regret": 1.1665899753570557,
|
| 733 |
+
"success_selector_gap": 1.0,
|
| 734 |
+
"success_support_gap": 0.0,
|
| 735 |
+
"support_gap": 0.0,
|
| 736 |
+
"tau": 0.3741559563273496
|
| 737 |
+
},
|
| 738 |
+
"1509980664/train2": {
|
| 739 |
+
"base_success": 0.0,
|
| 740 |
+
"base_utility": 0.8334100246429443,
|
| 741 |
+
"coverage": 0.0,
|
| 742 |
+
"execute_generated": 0.0,
|
| 743 |
+
"fallback_rate": 1.0,
|
| 744 |
+
"hidden_chart_oracle_success": 1.0,
|
| 745 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 746 |
+
"outcome_ptr": 0.0,
|
| 747 |
+
"predicted_margin": 0.2903038021197549,
|
| 748 |
+
"proposal_oracle_success": 0.0,
|
| 749 |
+
"proposal_oracle_utility": 0.8162217140197754,
|
| 750 |
+
"selected_candidate_index": 5.0,
|
| 751 |
+
"selected_success": 0.0,
|
| 752 |
+
"selected_success_gain_over_base": 0.0,
|
| 753 |
+
"selected_utility": 0.8334100246429443,
|
| 754 |
+
"selected_utility_gain_over_base": 0.0,
|
| 755 |
+
"selector_regret": 0.0,
|
| 756 |
+
"success_selector_gap": 0.0,
|
| 757 |
+
"success_support_gap": 1.0,
|
| 758 |
+
"support_gap": 1.1837782859802246,
|
| 759 |
+
"tau": 0.3741559563273496
|
| 760 |
+
},
|
| 761 |
+
"1522272686/train0": {
|
| 762 |
+
"base_success": 0.0,
|
| 763 |
+
"base_utility": 0.5839591026306152,
|
| 764 |
+
"coverage": 0.0,
|
| 765 |
+
"execute_generated": 0.0,
|
| 766 |
+
"fallback_rate": 1.0,
|
| 767 |
+
"hidden_chart_oracle_success": 1.0,
|
| 768 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 769 |
+
"outcome_ptr": 0.0,
|
| 770 |
+
"predicted_margin": 0.1923524089283563,
|
| 771 |
+
"proposal_oracle_success": 0.0,
|
| 772 |
+
"proposal_oracle_utility": 0.18325337767601013,
|
| 773 |
+
"selected_candidate_index": 3.0,
|
| 774 |
+
"selected_success": 0.0,
|
| 775 |
+
"selected_success_gain_over_base": 0.0,
|
| 776 |
+
"selected_utility": 0.5839591026306152,
|
| 777 |
+
"selected_utility_gain_over_base": 0.0,
|
| 778 |
+
"selector_regret": 0.0,
|
| 779 |
+
"success_selector_gap": 0.0,
|
| 780 |
+
"success_support_gap": 1.0,
|
| 781 |
+
"support_gap": 1.8167466223239899,
|
| 782 |
+
"tau": 0.3741559563273496
|
| 783 |
+
},
|
| 784 |
+
"1522272686/train1": {
|
| 785 |
+
"base_success": 0.0,
|
| 786 |
+
"base_utility": 0.5839591026306152,
|
| 787 |
+
"coverage": 0.0,
|
| 788 |
+
"execute_generated": 0.0,
|
| 789 |
+
"fallback_rate": 1.0,
|
| 790 |
+
"hidden_chart_oracle_success": 1.0,
|
| 791 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 792 |
+
"outcome_ptr": 0.0,
|
| 793 |
+
"predicted_margin": 0.26480661258416843,
|
| 794 |
+
"proposal_oracle_success": 0.0,
|
| 795 |
+
"proposal_oracle_utility": 0.07014383375644684,
|
| 796 |
+
"selected_candidate_index": 4.0,
|
| 797 |
+
"selected_success": 0.0,
|
| 798 |
+
"selected_success_gain_over_base": 0.0,
|
| 799 |
+
"selected_utility": 0.5839591026306152,
|
| 800 |
+
"selected_utility_gain_over_base": 0.0,
|
| 801 |
+
"selector_regret": 0.0,
|
| 802 |
+
"success_selector_gap": 0.0,
|
| 803 |
+
"success_support_gap": 1.0,
|
| 804 |
+
"support_gap": 1.9298561662435532,
|
| 805 |
+
"tau": 0.3741559563273496
|
| 806 |
+
},
|
| 807 |
+
"1522272686/train2": {
|
| 808 |
+
"base_success": 0.0,
|
| 809 |
+
"base_utility": 0.5839591026306152,
|
| 810 |
+
"coverage": 0.0,
|
| 811 |
+
"execute_generated": 0.0,
|
| 812 |
+
"fallback_rate": 1.0,
|
| 813 |
+
"hidden_chart_oracle_success": 1.0,
|
| 814 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 815 |
+
"outcome_ptr": 0.0,
|
| 816 |
+
"predicted_margin": 0.25057469871698324,
|
| 817 |
+
"proposal_oracle_success": 0.0,
|
| 818 |
+
"proposal_oracle_utility": 0.14937306940555573,
|
| 819 |
+
"selected_candidate_index": 3.0,
|
| 820 |
+
"selected_success": 0.0,
|
| 821 |
+
"selected_success_gain_over_base": 0.0,
|
| 822 |
+
"selected_utility": 0.5839591026306152,
|
| 823 |
+
"selected_utility_gain_over_base": 0.0,
|
| 824 |
+
"selector_regret": 0.0,
|
| 825 |
+
"success_selector_gap": 0.0,
|
| 826 |
+
"success_support_gap": 1.0,
|
| 827 |
+
"support_gap": 1.8506269305944443,
|
| 828 |
+
"tau": 0.3741559563273496
|
| 829 |
+
},
|
| 830 |
+
"1549324805/train0": {
|
| 831 |
+
"base_success": 0.0,
|
| 832 |
+
"base_utility": 0.10451483726501465,
|
| 833 |
+
"coverage": 1.0,
|
| 834 |
+
"execute_generated": 1.0,
|
| 835 |
+
"fallback_rate": 0.0,
|
| 836 |
+
"hidden_chart_oracle_success": 0.0,
|
| 837 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 838 |
+
"outcome_ptr": 0.0,
|
| 839 |
+
"predicted_margin": 0.37672502201482544,
|
| 840 |
+
"proposal_oracle_success": 0.0,
|
| 841 |
+
"proposal_oracle_utility": 0.0415392704308033,
|
| 842 |
+
"selected_candidate_index": 0.0,
|
| 843 |
+
"selected_success": 0.0,
|
| 844 |
+
"selected_success_gain_over_base": 0.0,
|
| 845 |
+
"selected_utility": 0.0260902252048254,
|
| 846 |
+
"selected_utility_gain_over_base": -0.07842461206018925,
|
| 847 |
+
"selector_regret": 0.015449045225977898,
|
| 848 |
+
"success_selector_gap": 0.0,
|
| 849 |
+
"success_support_gap": 0.0,
|
| 850 |
+
"support_gap": 0.255916815251112,
|
| 851 |
+
"tau": 0.3741559563273496
|
| 852 |
+
},
|
| 853 |
+
"1549324805/train1": {
|
| 854 |
+
"base_success": 0.0,
|
| 855 |
+
"base_utility": 0.10451483726501465,
|
| 856 |
+
"coverage": 0.0,
|
| 857 |
+
"execute_generated": 0.0,
|
| 858 |
+
"fallback_rate": 1.0,
|
| 859 |
+
"hidden_chart_oracle_success": 0.0,
|
| 860 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 861 |
+
"outcome_ptr": 1.0,
|
| 862 |
+
"predicted_margin": 0.3606900164943357,
|
| 863 |
+
"proposal_oracle_success": 0.0,
|
| 864 |
+
"proposal_oracle_utility": 0.19892151653766632,
|
| 865 |
+
"selected_candidate_index": 0.0,
|
| 866 |
+
"selected_success": 0.0,
|
| 867 |
+
"selected_success_gain_over_base": 0.0,
|
| 868 |
+
"selected_utility": 0.10451483726501465,
|
| 869 |
+
"selected_utility_gain_over_base": 0.0,
|
| 870 |
+
"selector_regret": 0.09440667927265167,
|
| 871 |
+
"success_selector_gap": 0.0,
|
| 872 |
+
"success_support_gap": 0.0,
|
| 873 |
+
"support_gap": 0.09853456914424896,
|
| 874 |
+
"tau": 0.3741559563273496
|
| 875 |
+
},
|
| 876 |
+
"1549324805/train2": {
|
| 877 |
+
"base_success": 0.0,
|
| 878 |
+
"base_utility": 0.10451483726501465,
|
| 879 |
+
"coverage": 1.0,
|
| 880 |
+
"execute_generated": 1.0,
|
| 881 |
+
"fallback_rate": 0.0,
|
| 882 |
+
"hidden_chart_oracle_success": 0.0,
|
| 883 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 884 |
+
"outcome_ptr": 0.0,
|
| 885 |
+
"predicted_margin": 0.45827775488717093,
|
| 886 |
+
"proposal_oracle_success": 0.0,
|
| 887 |
+
"proposal_oracle_utility": 0.09092829376459122,
|
| 888 |
+
"selected_candidate_index": 0.0,
|
| 889 |
+
"selected_success": 0.0,
|
| 890 |
+
"selected_success_gain_over_base": 0.0,
|
| 891 |
+
"selected_utility": 0.03407943248748779,
|
| 892 |
+
"selected_utility_gain_over_base": -0.07043540477752686,
|
| 893 |
+
"selector_regret": 0.056848861277103424,
|
| 894 |
+
"success_selector_gap": 0.0,
|
| 895 |
+
"success_support_gap": 0.0,
|
| 896 |
+
"support_gap": 0.20652779191732407,
|
| 897 |
+
"tau": 0.3741559563273496
|
| 898 |
+
},
|
| 899 |
+
"1578990937/train0": {
|
| 900 |
+
"base_success": 0.0,
|
| 901 |
+
"base_utility": 0.82413649559021,
|
| 902 |
+
"coverage": 0.0,
|
| 903 |
+
"execute_generated": 0.0,
|
| 904 |
+
"fallback_rate": 1.0,
|
| 905 |
+
"hidden_chart_oracle_success": 1.0,
|
| 906 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 907 |
+
"outcome_ptr": 1.0,
|
| 908 |
+
"predicted_margin": 0.30129083453678585,
|
| 909 |
+
"proposal_oracle_success": 1.0,
|
| 910 |
+
"proposal_oracle_utility": 2.0,
|
| 911 |
+
"selected_candidate_index": 1.0,
|
| 912 |
+
"selected_success": 0.0,
|
| 913 |
+
"selected_success_gain_over_base": 0.0,
|
| 914 |
+
"selected_utility": 0.82413649559021,
|
| 915 |
+
"selected_utility_gain_over_base": 0.0,
|
| 916 |
+
"selector_regret": 1.17586350440979,
|
| 917 |
+
"success_selector_gap": 1.0,
|
| 918 |
+
"success_support_gap": 0.0,
|
| 919 |
+
"support_gap": 0.0,
|
| 920 |
+
"tau": 0.3741559563273496
|
| 921 |
+
},
|
| 922 |
+
"1578990937/train1": {
|
| 923 |
+
"base_success": 0.0,
|
| 924 |
+
"base_utility": 0.82413649559021,
|
| 925 |
+
"coverage": 1.0,
|
| 926 |
+
"execute_generated": 1.0,
|
| 927 |
+
"fallback_rate": 0.0,
|
| 928 |
+
"hidden_chart_oracle_success": 1.0,
|
| 929 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 930 |
+
"outcome_ptr": 1.0,
|
| 931 |
+
"predicted_margin": 0.3882270730285144,
|
| 932 |
+
"proposal_oracle_success": 1.0,
|
| 933 |
+
"proposal_oracle_utility": 2.0,
|
| 934 |
+
"selected_candidate_index": 7.0,
|
| 935 |
+
"selected_success": 0.0,
|
| 936 |
+
"selected_success_gain_over_base": 0.0,
|
| 937 |
+
"selected_utility": 0.18939486145973206,
|
| 938 |
+
"selected_utility_gain_over_base": -0.6347416341304779,
|
| 939 |
+
"selector_regret": 1.810605138540268,
|
| 940 |
+
"success_selector_gap": 1.0,
|
| 941 |
+
"success_support_gap": 0.0,
|
| 942 |
+
"support_gap": 0.0,
|
| 943 |
+
"tau": 0.3741559563273496
|
| 944 |
+
},
|
| 945 |
+
"1578990937/train2": {
|
| 946 |
+
"base_success": 0.0,
|
| 947 |
+
"base_utility": 0.82413649559021,
|
| 948 |
+
"coverage": 1.0,
|
| 949 |
+
"execute_generated": 1.0,
|
| 950 |
+
"fallback_rate": 0.0,
|
| 951 |
+
"hidden_chart_oracle_success": 1.0,
|
| 952 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 953 |
+
"outcome_ptr": 1.0,
|
| 954 |
+
"predicted_margin": 0.4763906292645175,
|
| 955 |
+
"proposal_oracle_success": 1.0,
|
| 956 |
+
"proposal_oracle_utility": 2.0,
|
| 957 |
+
"selected_candidate_index": 1.0,
|
| 958 |
+
"selected_success": 0.0,
|
| 959 |
+
"selected_success_gain_over_base": 0.0,
|
| 960 |
+
"selected_utility": 0.1460946798324585,
|
| 961 |
+
"selected_utility_gain_over_base": -0.6780418157577515,
|
| 962 |
+
"selector_regret": 1.8539053201675415,
|
| 963 |
+
"success_selector_gap": 1.0,
|
| 964 |
+
"success_support_gap": 0.0,
|
| 965 |
+
"support_gap": 0.0,
|
| 966 |
+
"tau": 0.3741559563273496
|
| 967 |
+
},
|
| 968 |
+
"1747178030/train0": {
|
| 969 |
+
"base_success": 1.0,
|
| 970 |
+
"base_utility": 2.0,
|
| 971 |
+
"coverage": 1.0,
|
| 972 |
+
"execute_generated": 1.0,
|
| 973 |
+
"fallback_rate": 0.0,
|
| 974 |
+
"hidden_chart_oracle_success": 1.0,
|
| 975 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 976 |
+
"outcome_ptr": 0.0,
|
| 977 |
+
"predicted_margin": 0.4720823674110989,
|
| 978 |
+
"proposal_oracle_success": 1.0,
|
| 979 |
+
"proposal_oracle_utility": 2.0,
|
| 980 |
+
"selected_candidate_index": 0.0,
|
| 981 |
+
"selected_success": 1.0,
|
| 982 |
+
"selected_success_gain_over_base": 0.0,
|
| 983 |
+
"selected_utility": 2.0,
|
| 984 |
+
"selected_utility_gain_over_base": 0.0,
|
| 985 |
+
"selector_regret": 0.0,
|
| 986 |
+
"success_selector_gap": 0.0,
|
| 987 |
+
"success_support_gap": 0.0,
|
| 988 |
+
"support_gap": 0.0,
|
| 989 |
+
"tau": 0.3741559563273496
|
| 990 |
+
},
|
| 991 |
+
"1747178030/train1": {
|
| 992 |
+
"base_success": 1.0,
|
| 993 |
+
"base_utility": 2.0,
|
| 994 |
+
"coverage": 1.0,
|
| 995 |
+
"execute_generated": 1.0,
|
| 996 |
+
"fallback_rate": 0.0,
|
| 997 |
+
"hidden_chart_oracle_success": 1.0,
|
| 998 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 999 |
+
"outcome_ptr": 0.0,
|
| 1000 |
+
"predicted_margin": 0.4339821423007203,
|
| 1001 |
+
"proposal_oracle_success": 1.0,
|
| 1002 |
+
"proposal_oracle_utility": 2.0,
|
| 1003 |
+
"selected_candidate_index": 6.0,
|
| 1004 |
+
"selected_success": 1.0,
|
| 1005 |
+
"selected_success_gain_over_base": 0.0,
|
| 1006 |
+
"selected_utility": 2.0,
|
| 1007 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1008 |
+
"selector_regret": 0.0,
|
| 1009 |
+
"success_selector_gap": 0.0,
|
| 1010 |
+
"success_support_gap": 0.0,
|
| 1011 |
+
"support_gap": 0.0,
|
| 1012 |
+
"tau": 0.3741559563273496
|
| 1013 |
+
},
|
| 1014 |
+
"1747178030/train2": {
|
| 1015 |
+
"base_success": 1.0,
|
| 1016 |
+
"base_utility": 2.0,
|
| 1017 |
+
"coverage": 1.0,
|
| 1018 |
+
"execute_generated": 1.0,
|
| 1019 |
+
"fallback_rate": 0.0,
|
| 1020 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1021 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1022 |
+
"outcome_ptr": 0.0,
|
| 1023 |
+
"predicted_margin": 0.47673474284532225,
|
| 1024 |
+
"proposal_oracle_success": 1.0,
|
| 1025 |
+
"proposal_oracle_utility": 2.0,
|
| 1026 |
+
"selected_candidate_index": 4.0,
|
| 1027 |
+
"selected_success": 1.0,
|
| 1028 |
+
"selected_success_gain_over_base": 0.0,
|
| 1029 |
+
"selected_utility": 2.0,
|
| 1030 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1031 |
+
"selector_regret": 0.0,
|
| 1032 |
+
"success_selector_gap": 0.0,
|
| 1033 |
+
"success_support_gap": 0.0,
|
| 1034 |
+
"support_gap": 0.0,
|
| 1035 |
+
"tau": 0.3741559563273496
|
| 1036 |
+
},
|
| 1037 |
+
"1790188787/train0": {
|
| 1038 |
+
"base_success": 0.0,
|
| 1039 |
+
"base_utility": 0.12476746737957001,
|
| 1040 |
+
"coverage": 1.0,
|
| 1041 |
+
"execute_generated": 1.0,
|
| 1042 |
+
"fallback_rate": 0.0,
|
| 1043 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1044 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1045 |
+
"outcome_ptr": 0.0,
|
| 1046 |
+
"predicted_margin": 0.48888892485386093,
|
| 1047 |
+
"proposal_oracle_success": 0.0,
|
| 1048 |
+
"proposal_oracle_utility": 0.09791924059391022,
|
| 1049 |
+
"selected_candidate_index": 0.0,
|
| 1050 |
+
"selected_success": 0.0,
|
| 1051 |
+
"selected_success_gain_over_base": 0.0,
|
| 1052 |
+
"selected_utility": 0.06870591640472412,
|
| 1053 |
+
"selected_utility_gain_over_base": -0.056061550974845886,
|
| 1054 |
+
"selector_regret": 0.029213324189186096,
|
| 1055 |
+
"success_selector_gap": 0.0,
|
| 1056 |
+
"success_support_gap": 1.0,
|
| 1057 |
+
"support_gap": 1.9020807594060898,
|
| 1058 |
+
"tau": 0.3741559563273496
|
| 1059 |
+
},
|
| 1060 |
+
"1790188787/train1": {
|
| 1061 |
+
"base_success": 0.0,
|
| 1062 |
+
"base_utility": 0.12476746737957001,
|
| 1063 |
+
"coverage": 1.0,
|
| 1064 |
+
"execute_generated": 1.0,
|
| 1065 |
+
"fallback_rate": 0.0,
|
| 1066 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1067 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1068 |
+
"outcome_ptr": 1.0,
|
| 1069 |
+
"predicted_margin": 0.3755843205364714,
|
| 1070 |
+
"proposal_oracle_success": 0.0,
|
| 1071 |
+
"proposal_oracle_utility": 0.13031470775604248,
|
| 1072 |
+
"selected_candidate_index": 5.0,
|
| 1073 |
+
"selected_success": 0.0,
|
| 1074 |
+
"selected_success_gain_over_base": 0.0,
|
| 1075 |
+
"selected_utility": 0.11081808805465698,
|
| 1076 |
+
"selected_utility_gain_over_base": -0.013949379324913025,
|
| 1077 |
+
"selector_regret": 0.019496619701385498,
|
| 1078 |
+
"success_selector_gap": 0.0,
|
| 1079 |
+
"success_support_gap": 1.0,
|
| 1080 |
+
"support_gap": 1.8696852922439575,
|
| 1081 |
+
"tau": 0.3741559563273496
|
| 1082 |
+
},
|
| 1083 |
+
"1790188787/train2": {
|
| 1084 |
+
"base_success": 0.0,
|
| 1085 |
+
"base_utility": 0.12476746737957001,
|
| 1086 |
+
"coverage": 1.0,
|
| 1087 |
+
"execute_generated": 1.0,
|
| 1088 |
+
"fallback_rate": 0.0,
|
| 1089 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1090 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1091 |
+
"outcome_ptr": 1.0,
|
| 1092 |
+
"predicted_margin": 0.3785435132544391,
|
| 1093 |
+
"proposal_oracle_success": 1.0,
|
| 1094 |
+
"proposal_oracle_utility": 2.0,
|
| 1095 |
+
"selected_candidate_index": 7.0,
|
| 1096 |
+
"selected_success": 0.0,
|
| 1097 |
+
"selected_success_gain_over_base": 0.0,
|
| 1098 |
+
"selected_utility": 0.09652663767337799,
|
| 1099 |
+
"selected_utility_gain_over_base": -0.028240829706192017,
|
| 1100 |
+
"selector_regret": 1.903473362326622,
|
| 1101 |
+
"success_selector_gap": 1.0,
|
| 1102 |
+
"success_support_gap": 0.0,
|
| 1103 |
+
"support_gap": 0.0,
|
| 1104 |
+
"tau": 0.3741559563273496
|
| 1105 |
+
},
|
| 1106 |
+
"1822210471/train0": {
|
| 1107 |
+
"base_success": 0.0,
|
| 1108 |
+
"base_utility": 0.07191530615091324,
|
| 1109 |
+
"coverage": 0.0,
|
| 1110 |
+
"execute_generated": 0.0,
|
| 1111 |
+
"fallback_rate": 1.0,
|
| 1112 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1113 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1114 |
+
"outcome_ptr": 1.0,
|
| 1115 |
+
"predicted_margin": 0.3460545899296898,
|
| 1116 |
+
"proposal_oracle_success": 1.0,
|
| 1117 |
+
"proposal_oracle_utility": 2.0,
|
| 1118 |
+
"selected_candidate_index": 3.0,
|
| 1119 |
+
"selected_success": 0.0,
|
| 1120 |
+
"selected_success_gain_over_base": 0.0,
|
| 1121 |
+
"selected_utility": 0.07191530615091324,
|
| 1122 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1123 |
+
"selector_regret": 1.9280846938490868,
|
| 1124 |
+
"success_selector_gap": 1.0,
|
| 1125 |
+
"success_support_gap": 0.0,
|
| 1126 |
+
"support_gap": 0.0,
|
| 1127 |
+
"tau": 0.3741559563273496
|
| 1128 |
+
},
|
| 1129 |
+
"1822210471/train1": {
|
| 1130 |
+
"base_success": 0.0,
|
| 1131 |
+
"base_utility": 0.07191530615091324,
|
| 1132 |
+
"coverage": 0.0,
|
| 1133 |
+
"execute_generated": 0.0,
|
| 1134 |
+
"fallback_rate": 1.0,
|
| 1135 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1136 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1137 |
+
"outcome_ptr": 1.0,
|
| 1138 |
+
"predicted_margin": 0.2999793737204269,
|
| 1139 |
+
"proposal_oracle_success": 1.0,
|
| 1140 |
+
"proposal_oracle_utility": 2.0,
|
| 1141 |
+
"selected_candidate_index": 3.0,
|
| 1142 |
+
"selected_success": 0.0,
|
| 1143 |
+
"selected_success_gain_over_base": 0.0,
|
| 1144 |
+
"selected_utility": 0.07191530615091324,
|
| 1145 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1146 |
+
"selector_regret": 1.9280846938490868,
|
| 1147 |
+
"success_selector_gap": 1.0,
|
| 1148 |
+
"success_support_gap": 0.0,
|
| 1149 |
+
"support_gap": 0.0,
|
| 1150 |
+
"tau": 0.3741559563273496
|
| 1151 |
+
},
|
| 1152 |
+
"1822210471/train2": {
|
| 1153 |
+
"base_success": 0.0,
|
| 1154 |
+
"base_utility": 0.07191530615091324,
|
| 1155 |
+
"coverage": 0.0,
|
| 1156 |
+
"execute_generated": 0.0,
|
| 1157 |
+
"fallback_rate": 1.0,
|
| 1158 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1159 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1160 |
+
"outcome_ptr": 1.0,
|
| 1161 |
+
"predicted_margin": 0.35054441428919914,
|
| 1162 |
+
"proposal_oracle_success": 1.0,
|
| 1163 |
+
"proposal_oracle_utility": 2.0,
|
| 1164 |
+
"selected_candidate_index": 7.0,
|
| 1165 |
+
"selected_success": 0.0,
|
| 1166 |
+
"selected_success_gain_over_base": 0.0,
|
| 1167 |
+
"selected_utility": 0.07191530615091324,
|
| 1168 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1169 |
+
"selector_regret": 1.9280846938490868,
|
| 1170 |
+
"success_selector_gap": 1.0,
|
| 1171 |
+
"success_support_gap": 0.0,
|
| 1172 |
+
"support_gap": 0.0,
|
| 1173 |
+
"tau": 0.3741559563273496
|
| 1174 |
+
},
|
| 1175 |
+
"1845489013/train0": {
|
| 1176 |
+
"base_success": 1.0,
|
| 1177 |
+
"base_utility": 2.0,
|
| 1178 |
+
"coverage": 0.0,
|
| 1179 |
+
"execute_generated": 0.0,
|
| 1180 |
+
"fallback_rate": 1.0,
|
| 1181 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1182 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1183 |
+
"outcome_ptr": 0.0,
|
| 1184 |
+
"predicted_margin": 0.2989164896631082,
|
| 1185 |
+
"proposal_oracle_success": 1.0,
|
| 1186 |
+
"proposal_oracle_utility": 2.0,
|
| 1187 |
+
"selected_candidate_index": 7.0,
|
| 1188 |
+
"selected_success": 1.0,
|
| 1189 |
+
"selected_success_gain_over_base": 0.0,
|
| 1190 |
+
"selected_utility": 2.0,
|
| 1191 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1192 |
+
"selector_regret": 0.0,
|
| 1193 |
+
"success_selector_gap": 0.0,
|
| 1194 |
+
"success_support_gap": 0.0,
|
| 1195 |
+
"support_gap": 0.0,
|
| 1196 |
+
"tau": 0.3741559563273496
|
| 1197 |
+
},
|
| 1198 |
+
"1845489013/train1": {
|
| 1199 |
+
"base_success": 1.0,
|
| 1200 |
+
"base_utility": 2.0,
|
| 1201 |
+
"coverage": 0.0,
|
| 1202 |
+
"execute_generated": 0.0,
|
| 1203 |
+
"fallback_rate": 1.0,
|
| 1204 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1205 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1206 |
+
"outcome_ptr": 0.0,
|
| 1207 |
+
"predicted_margin": 0.35433654964210193,
|
| 1208 |
+
"proposal_oracle_success": 1.0,
|
| 1209 |
+
"proposal_oracle_utility": 2.0,
|
| 1210 |
+
"selected_candidate_index": 4.0,
|
| 1211 |
+
"selected_success": 1.0,
|
| 1212 |
+
"selected_success_gain_over_base": 0.0,
|
| 1213 |
+
"selected_utility": 2.0,
|
| 1214 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1215 |
+
"selector_regret": 0.0,
|
| 1216 |
+
"success_selector_gap": 0.0,
|
| 1217 |
+
"success_support_gap": 0.0,
|
| 1218 |
+
"support_gap": 0.0,
|
| 1219 |
+
"tau": 0.3741559563273496
|
| 1220 |
+
},
|
| 1221 |
+
"1845489013/train2": {
|
| 1222 |
+
"base_success": 1.0,
|
| 1223 |
+
"base_utility": 2.0,
|
| 1224 |
+
"coverage": 0.0,
|
| 1225 |
+
"execute_generated": 0.0,
|
| 1226 |
+
"fallback_rate": 1.0,
|
| 1227 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1228 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1229 |
+
"outcome_ptr": 0.0,
|
| 1230 |
+
"predicted_margin": 0.3440215189574023,
|
| 1231 |
+
"proposal_oracle_success": 1.0,
|
| 1232 |
+
"proposal_oracle_utility": 2.0,
|
| 1233 |
+
"selected_candidate_index": 7.0,
|
| 1234 |
+
"selected_success": 1.0,
|
| 1235 |
+
"selected_success_gain_over_base": 0.0,
|
| 1236 |
+
"selected_utility": 2.0,
|
| 1237 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1238 |
+
"selector_regret": 0.0,
|
| 1239 |
+
"success_selector_gap": 0.0,
|
| 1240 |
+
"success_support_gap": 0.0,
|
| 1241 |
+
"support_gap": 0.0,
|
| 1242 |
+
"tau": 0.3741559563273496
|
| 1243 |
+
},
|
| 1244 |
+
"1999022574/train0": {
|
| 1245 |
+
"base_success": 1.0,
|
| 1246 |
+
"base_utility": 2.0,
|
| 1247 |
+
"coverage": 0.0,
|
| 1248 |
+
"execute_generated": 0.0,
|
| 1249 |
+
"fallback_rate": 1.0,
|
| 1250 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1251 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1252 |
+
"outcome_ptr": 0.0,
|
| 1253 |
+
"predicted_margin": 0.2864812386218567,
|
| 1254 |
+
"proposal_oracle_success": 1.0,
|
| 1255 |
+
"proposal_oracle_utility": 2.0,
|
| 1256 |
+
"selected_candidate_index": 2.0,
|
| 1257 |
+
"selected_success": 1.0,
|
| 1258 |
+
"selected_success_gain_over_base": 0.0,
|
| 1259 |
+
"selected_utility": 2.0,
|
| 1260 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1261 |
+
"selector_regret": 0.0,
|
| 1262 |
+
"success_selector_gap": 0.0,
|
| 1263 |
+
"success_support_gap": 0.0,
|
| 1264 |
+
"support_gap": 0.0,
|
| 1265 |
+
"tau": 0.3741559563273496
|
| 1266 |
+
},
|
| 1267 |
+
"1999022574/train1": {
|
| 1268 |
+
"base_success": 1.0,
|
| 1269 |
+
"base_utility": 2.0,
|
| 1270 |
+
"coverage": 0.0,
|
| 1271 |
+
"execute_generated": 0.0,
|
| 1272 |
+
"fallback_rate": 1.0,
|
| 1273 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1274 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1275 |
+
"outcome_ptr": 0.0,
|
| 1276 |
+
"predicted_margin": 0.3060895394094739,
|
| 1277 |
+
"proposal_oracle_success": 1.0,
|
| 1278 |
+
"proposal_oracle_utility": 2.0,
|
| 1279 |
+
"selected_candidate_index": 4.0,
|
| 1280 |
+
"selected_success": 1.0,
|
| 1281 |
+
"selected_success_gain_over_base": 0.0,
|
| 1282 |
+
"selected_utility": 2.0,
|
| 1283 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1284 |
+
"selector_regret": 0.0,
|
| 1285 |
+
"success_selector_gap": 0.0,
|
| 1286 |
+
"success_support_gap": 0.0,
|
| 1287 |
+
"support_gap": 0.0,
|
| 1288 |
+
"tau": 0.3741559563273496
|
| 1289 |
+
},
|
| 1290 |
+
"1999022574/train2": {
|
| 1291 |
+
"base_success": 1.0,
|
| 1292 |
+
"base_utility": 2.0,
|
| 1293 |
+
"coverage": 0.0,
|
| 1294 |
+
"execute_generated": 0.0,
|
| 1295 |
+
"fallback_rate": 1.0,
|
| 1296 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1297 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1298 |
+
"outcome_ptr": 0.0,
|
| 1299 |
+
"predicted_margin": 0.27674986209929975,
|
| 1300 |
+
"proposal_oracle_success": 1.0,
|
| 1301 |
+
"proposal_oracle_utility": 2.0,
|
| 1302 |
+
"selected_candidate_index": 4.0,
|
| 1303 |
+
"selected_success": 1.0,
|
| 1304 |
+
"selected_success_gain_over_base": 0.0,
|
| 1305 |
+
"selected_utility": 2.0,
|
| 1306 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1307 |
+
"selector_regret": 0.0,
|
| 1308 |
+
"success_selector_gap": 0.0,
|
| 1309 |
+
"success_support_gap": 0.0,
|
| 1310 |
+
"support_gap": 0.0,
|
| 1311 |
+
"tau": 0.3741559563273496
|
| 1312 |
+
},
|
| 1313 |
+
"2012211287/train0": {
|
| 1314 |
+
"base_success": 0.0,
|
| 1315 |
+
"base_utility": 0.7236053347587585,
|
| 1316 |
+
"coverage": 0.0,
|
| 1317 |
+
"execute_generated": 0.0,
|
| 1318 |
+
"fallback_rate": 1.0,
|
| 1319 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1320 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1321 |
+
"outcome_ptr": 1.0,
|
| 1322 |
+
"predicted_margin": 0.2781929266795631,
|
| 1323 |
+
"proposal_oracle_success": 1.0,
|
| 1324 |
+
"proposal_oracle_utility": 2.0,
|
| 1325 |
+
"selected_candidate_index": 5.0,
|
| 1326 |
+
"selected_success": 0.0,
|
| 1327 |
+
"selected_success_gain_over_base": 0.0,
|
| 1328 |
+
"selected_utility": 0.7236053347587585,
|
| 1329 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1330 |
+
"selector_regret": 1.2763946652412415,
|
| 1331 |
+
"success_selector_gap": 1.0,
|
| 1332 |
+
"success_support_gap": 0.0,
|
| 1333 |
+
"support_gap": 0.0,
|
| 1334 |
+
"tau": 0.3741559563273496
|
| 1335 |
+
},
|
| 1336 |
+
"2012211287/train1": {
|
| 1337 |
+
"base_success": 0.0,
|
| 1338 |
+
"base_utility": 0.7236053347587585,
|
| 1339 |
+
"coverage": 1.0,
|
| 1340 |
+
"execute_generated": 1.0,
|
| 1341 |
+
"fallback_rate": 0.0,
|
| 1342 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1343 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1344 |
+
"outcome_ptr": 1.0,
|
| 1345 |
+
"predicted_margin": 0.3755843205364714,
|
| 1346 |
+
"proposal_oracle_success": 1.0,
|
| 1347 |
+
"proposal_oracle_utility": 2.0,
|
| 1348 |
+
"selected_candidate_index": 7.0,
|
| 1349 |
+
"selected_success": 0.0,
|
| 1350 |
+
"selected_success_gain_over_base": 0.0,
|
| 1351 |
+
"selected_utility": 0.6900332570075989,
|
| 1352 |
+
"selected_utility_gain_over_base": -0.03357207775115967,
|
| 1353 |
+
"selector_regret": 1.3099667429924011,
|
| 1354 |
+
"success_selector_gap": 1.0,
|
| 1355 |
+
"success_support_gap": 0.0,
|
| 1356 |
+
"support_gap": 0.0,
|
| 1357 |
+
"tau": 0.3741559563273496
|
| 1358 |
+
},
|
| 1359 |
+
"2012211287/train2": {
|
| 1360 |
+
"base_success": 0.0,
|
| 1361 |
+
"base_utility": 0.7236053347587585,
|
| 1362 |
+
"coverage": 0.0,
|
| 1363 |
+
"execute_generated": 0.0,
|
| 1364 |
+
"fallback_rate": 1.0,
|
| 1365 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1366 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1367 |
+
"outcome_ptr": 1.0,
|
| 1368 |
+
"predicted_margin": 0.34895677424461957,
|
| 1369 |
+
"proposal_oracle_success": 1.0,
|
| 1370 |
+
"proposal_oracle_utility": 2.0,
|
| 1371 |
+
"selected_candidate_index": 6.0,
|
| 1372 |
+
"selected_success": 0.0,
|
| 1373 |
+
"selected_success_gain_over_base": 0.0,
|
| 1374 |
+
"selected_utility": 0.7236053347587585,
|
| 1375 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1376 |
+
"selector_regret": 1.2763946652412415,
|
| 1377 |
+
"success_selector_gap": 1.0,
|
| 1378 |
+
"success_support_gap": 0.0,
|
| 1379 |
+
"support_gap": 0.0,
|
| 1380 |
+
"tau": 0.3741559563273496
|
| 1381 |
+
},
|
| 1382 |
+
"2038594191/train0": {
|
| 1383 |
+
"base_success": 1.0,
|
| 1384 |
+
"base_utility": 2.0,
|
| 1385 |
+
"coverage": 0.0,
|
| 1386 |
+
"execute_generated": 0.0,
|
| 1387 |
+
"fallback_rate": 1.0,
|
| 1388 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1389 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1390 |
+
"outcome_ptr": 0.0,
|
| 1391 |
+
"predicted_margin": 0.27574476828623157,
|
| 1392 |
+
"proposal_oracle_success": 1.0,
|
| 1393 |
+
"proposal_oracle_utility": 2.0,
|
| 1394 |
+
"selected_candidate_index": 5.0,
|
| 1395 |
+
"selected_success": 1.0,
|
| 1396 |
+
"selected_success_gain_over_base": 0.0,
|
| 1397 |
+
"selected_utility": 2.0,
|
| 1398 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1399 |
+
"selector_regret": 0.0,
|
| 1400 |
+
"success_selector_gap": 0.0,
|
| 1401 |
+
"success_support_gap": 0.0,
|
| 1402 |
+
"support_gap": 0.0,
|
| 1403 |
+
"tau": 0.3741559563273496
|
| 1404 |
+
},
|
| 1405 |
+
"2038594191/train1": {
|
| 1406 |
+
"base_success": 1.0,
|
| 1407 |
+
"base_utility": 2.0,
|
| 1408 |
+
"coverage": 0.0,
|
| 1409 |
+
"execute_generated": 0.0,
|
| 1410 |
+
"fallback_rate": 1.0,
|
| 1411 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1412 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1413 |
+
"outcome_ptr": 0.0,
|
| 1414 |
+
"predicted_margin": 0.2963268387066977,
|
| 1415 |
+
"proposal_oracle_success": 1.0,
|
| 1416 |
+
"proposal_oracle_utility": 2.0,
|
| 1417 |
+
"selected_candidate_index": 0.0,
|
| 1418 |
+
"selected_success": 1.0,
|
| 1419 |
+
"selected_success_gain_over_base": 0.0,
|
| 1420 |
+
"selected_utility": 2.0,
|
| 1421 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1422 |
+
"selector_regret": 0.0,
|
| 1423 |
+
"success_selector_gap": 0.0,
|
| 1424 |
+
"success_support_gap": 0.0,
|
| 1425 |
+
"support_gap": 0.0,
|
| 1426 |
+
"tau": 0.3741559563273496
|
| 1427 |
+
},
|
| 1428 |
+
"2038594191/train2": {
|
| 1429 |
+
"base_success": 1.0,
|
| 1430 |
+
"base_utility": 2.0,
|
| 1431 |
+
"coverage": 0.0,
|
| 1432 |
+
"execute_generated": 0.0,
|
| 1433 |
+
"fallback_rate": 1.0,
|
| 1434 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1435 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1436 |
+
"outcome_ptr": 0.0,
|
| 1437 |
+
"predicted_margin": 0.2728649751609838,
|
| 1438 |
+
"proposal_oracle_success": 1.0,
|
| 1439 |
+
"proposal_oracle_utility": 2.0,
|
| 1440 |
+
"selected_candidate_index": 1.0,
|
| 1441 |
+
"selected_success": 1.0,
|
| 1442 |
+
"selected_success_gain_over_base": 0.0,
|
| 1443 |
+
"selected_utility": 2.0,
|
| 1444 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1445 |
+
"selector_regret": 0.0,
|
| 1446 |
+
"success_selector_gap": 0.0,
|
| 1447 |
+
"success_support_gap": 0.0,
|
| 1448 |
+
"support_gap": 0.0,
|
| 1449 |
+
"tau": 0.3741559563273496
|
| 1450 |
+
},
|
| 1451 |
+
"2054899126/train0": {
|
| 1452 |
+
"base_success": 1.0,
|
| 1453 |
+
"base_utility": 2.0,
|
| 1454 |
+
"coverage": 0.5,
|
| 1455 |
+
"execute_generated": 0.5,
|
| 1456 |
+
"fallback_rate": 0.5,
|
| 1457 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1458 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1459 |
+
"outcome_ptr": 0.0,
|
| 1460 |
+
"predicted_margin": 0.3470083918101673,
|
| 1461 |
+
"proposal_oracle_success": 0.5,
|
| 1462 |
+
"proposal_oracle_utility": 1.077283151447773,
|
| 1463 |
+
"selected_candidate_index": 0.0,
|
| 1464 |
+
"selected_success": 1.0,
|
| 1465 |
+
"selected_success_gain_over_base": 0.0,
|
| 1466 |
+
"selected_utility": 2.0,
|
| 1467 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1468 |
+
"selector_regret": 0.0,
|
| 1469 |
+
"success_selector_gap": 0.0,
|
| 1470 |
+
"success_support_gap": 0.5,
|
| 1471 |
+
"support_gap": 0.922716848552227,
|
| 1472 |
+
"tau": 0.3741559563273496
|
| 1473 |
+
},
|
| 1474 |
+
"2054899126/train1": {
|
| 1475 |
+
"base_success": 1.0,
|
| 1476 |
+
"base_utility": 2.0,
|
| 1477 |
+
"coverage": 0.5,
|
| 1478 |
+
"execute_generated": 0.5,
|
| 1479 |
+
"fallback_rate": 0.5,
|
| 1480 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1481 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1482 |
+
"outcome_ptr": 0.0,
|
| 1483 |
+
"predicted_margin": 0.3532533835187622,
|
| 1484 |
+
"proposal_oracle_success": 0.5,
|
| 1485 |
+
"proposal_oracle_utility": 1.0696808770298958,
|
| 1486 |
+
"selected_candidate_index": 3.0,
|
| 1487 |
+
"selected_success": 1.0,
|
| 1488 |
+
"selected_success_gain_over_base": 0.0,
|
| 1489 |
+
"selected_utility": 2.0,
|
| 1490 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1491 |
+
"selector_regret": 0.0,
|
| 1492 |
+
"success_selector_gap": 0.0,
|
| 1493 |
+
"success_support_gap": 0.5,
|
| 1494 |
+
"support_gap": 0.9303191229701042,
|
| 1495 |
+
"tau": 0.3741559563273496
|
| 1496 |
+
},
|
| 1497 |
+
"2054899126/train2": {
|
| 1498 |
+
"base_success": 1.0,
|
| 1499 |
+
"base_utility": 2.0,
|
| 1500 |
+
"coverage": 0.5,
|
| 1501 |
+
"execute_generated": 0.5,
|
| 1502 |
+
"fallback_rate": 0.5,
|
| 1503 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1504 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1505 |
+
"outcome_ptr": 0.0,
|
| 1506 |
+
"predicted_margin": 0.3744279152208737,
|
| 1507 |
+
"proposal_oracle_success": 0.5,
|
| 1508 |
+
"proposal_oracle_utility": 1.0455262660980225,
|
| 1509 |
+
"selected_candidate_index": 0.0,
|
| 1510 |
+
"selected_success": 1.0,
|
| 1511 |
+
"selected_success_gain_over_base": 0.0,
|
| 1512 |
+
"selected_utility": 2.0,
|
| 1513 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1514 |
+
"selector_regret": 0.0,
|
| 1515 |
+
"success_selector_gap": 0.0,
|
| 1516 |
+
"success_support_gap": 0.5,
|
| 1517 |
+
"support_gap": 0.9544737339019775,
|
| 1518 |
+
"tau": 0.3741559563273496
|
| 1519 |
+
},
|
| 1520 |
+
"2061635888/train0": {
|
| 1521 |
+
"base_success": 0.0,
|
| 1522 |
+
"base_utility": 0.05225050449371338,
|
| 1523 |
+
"coverage": 0.0,
|
| 1524 |
+
"execute_generated": 0.0,
|
| 1525 |
+
"fallback_rate": 1.0,
|
| 1526 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1527 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1528 |
+
"outcome_ptr": 1.0,
|
| 1529 |
+
"predicted_margin": 0.2680360950974473,
|
| 1530 |
+
"proposal_oracle_success": 0.0,
|
| 1531 |
+
"proposal_oracle_utility": 0.09799930453300476,
|
| 1532 |
+
"selected_candidate_index": 2.0,
|
| 1533 |
+
"selected_success": 0.0,
|
| 1534 |
+
"selected_success_gain_over_base": 0.0,
|
| 1535 |
+
"selected_utility": 0.05225050449371338,
|
| 1536 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1537 |
+
"selector_regret": 0.04574880003929138,
|
| 1538 |
+
"success_selector_gap": 0.0,
|
| 1539 |
+
"success_support_gap": 1.0,
|
| 1540 |
+
"support_gap": 1.9020006954669952,
|
| 1541 |
+
"tau": 0.3741559563273496
|
| 1542 |
+
},
|
| 1543 |
+
"2061635888/train1": {
|
| 1544 |
+
"base_success": 0.0,
|
| 1545 |
+
"base_utility": 0.05225050449371338,
|
| 1546 |
+
"coverage": 0.0,
|
| 1547 |
+
"execute_generated": 0.0,
|
| 1548 |
+
"fallback_rate": 1.0,
|
| 1549 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1550 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1551 |
+
"outcome_ptr": 1.0,
|
| 1552 |
+
"predicted_margin": 0.29770620738185305,
|
| 1553 |
+
"proposal_oracle_success": 0.0,
|
| 1554 |
+
"proposal_oracle_utility": 0.07580336928367615,
|
| 1555 |
+
"selected_candidate_index": 7.0,
|
| 1556 |
+
"selected_success": 0.0,
|
| 1557 |
+
"selected_success_gain_over_base": 0.0,
|
| 1558 |
+
"selected_utility": 0.05225050449371338,
|
| 1559 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1560 |
+
"selector_regret": 0.02355286478996277,
|
| 1561 |
+
"success_selector_gap": 0.0,
|
| 1562 |
+
"success_support_gap": 1.0,
|
| 1563 |
+
"support_gap": 1.9241966307163239,
|
| 1564 |
+
"tau": 0.3741559563273496
|
| 1565 |
+
},
|
| 1566 |
+
"2061635888/train2": {
|
| 1567 |
+
"base_success": 0.0,
|
| 1568 |
+
"base_utility": 0.05225050449371338,
|
| 1569 |
+
"coverage": 0.0,
|
| 1570 |
+
"execute_generated": 0.0,
|
| 1571 |
+
"fallback_rate": 1.0,
|
| 1572 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1573 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1574 |
+
"outcome_ptr": 1.0,
|
| 1575 |
+
"predicted_margin": 0.27387772560678275,
|
| 1576 |
+
"proposal_oracle_success": 0.0,
|
| 1577 |
+
"proposal_oracle_utility": 0.11105132102966309,
|
| 1578 |
+
"selected_candidate_index": 6.0,
|
| 1579 |
+
"selected_success": 0.0,
|
| 1580 |
+
"selected_success_gain_over_base": 0.0,
|
| 1581 |
+
"selected_utility": 0.05225050449371338,
|
| 1582 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1583 |
+
"selector_regret": 0.05880081653594971,
|
| 1584 |
+
"success_selector_gap": 0.0,
|
| 1585 |
+
"success_support_gap": 1.0,
|
| 1586 |
+
"support_gap": 1.888948678970337,
|
| 1587 |
+
"tau": 0.3741559563273496
|
| 1588 |
+
},
|
| 1589 |
+
"211245842/train0": {
|
| 1590 |
+
"base_success": 0.0,
|
| 1591 |
+
"base_utility": 0.19090841710567474,
|
| 1592 |
+
"coverage": 0.0,
|
| 1593 |
+
"execute_generated": 0.0,
|
| 1594 |
+
"fallback_rate": 1.0,
|
| 1595 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1596 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1597 |
+
"outcome_ptr": 1.0,
|
| 1598 |
+
"predicted_margin": 0.2838401268071768,
|
| 1599 |
+
"proposal_oracle_success": 1.0,
|
| 1600 |
+
"proposal_oracle_utility": 2.0,
|
| 1601 |
+
"selected_candidate_index": 3.0,
|
| 1602 |
+
"selected_success": 0.0,
|
| 1603 |
+
"selected_success_gain_over_base": 0.0,
|
| 1604 |
+
"selected_utility": 0.19090841710567474,
|
| 1605 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1606 |
+
"selector_regret": 1.8090915828943253,
|
| 1607 |
+
"success_selector_gap": 1.0,
|
| 1608 |
+
"success_support_gap": 0.0,
|
| 1609 |
+
"support_gap": 0.0,
|
| 1610 |
+
"tau": 0.3741559563273496
|
| 1611 |
+
},
|
| 1612 |
+
"211245842/train1": {
|
| 1613 |
+
"base_success": 0.0,
|
| 1614 |
+
"base_utility": 0.19090841710567474,
|
| 1615 |
+
"coverage": 0.0,
|
| 1616 |
+
"execute_generated": 0.0,
|
| 1617 |
+
"fallback_rate": 1.0,
|
| 1618 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1619 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1620 |
+
"outcome_ptr": 1.0,
|
| 1621 |
+
"predicted_margin": 0.36516876704401185,
|
| 1622 |
+
"proposal_oracle_success": 0.0,
|
| 1623 |
+
"proposal_oracle_utility": 0.21295717358589172,
|
| 1624 |
+
"selected_candidate_index": 6.0,
|
| 1625 |
+
"selected_success": 0.0,
|
| 1626 |
+
"selected_success_gain_over_base": 0.0,
|
| 1627 |
+
"selected_utility": 0.19090841710567474,
|
| 1628 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1629 |
+
"selector_regret": 0.02204875648021698,
|
| 1630 |
+
"success_selector_gap": 0.0,
|
| 1631 |
+
"success_support_gap": 1.0,
|
| 1632 |
+
"support_gap": 1.7870428264141083,
|
| 1633 |
+
"tau": 0.3741559563273496
|
| 1634 |
+
},
|
| 1635 |
+
"211245842/train2": {
|
| 1636 |
+
"base_success": 0.0,
|
| 1637 |
+
"base_utility": 0.19090841710567474,
|
| 1638 |
+
"coverage": 0.0,
|
| 1639 |
+
"execute_generated": 0.0,
|
| 1640 |
+
"fallback_rate": 1.0,
|
| 1641 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1642 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1643 |
+
"outcome_ptr": 1.0,
|
| 1644 |
+
"predicted_margin": 0.344497387758629,
|
| 1645 |
+
"proposal_oracle_success": 0.0,
|
| 1646 |
+
"proposal_oracle_utility": 0.21523693203926086,
|
| 1647 |
+
"selected_candidate_index": 0.0,
|
| 1648 |
+
"selected_success": 0.0,
|
| 1649 |
+
"selected_success_gain_over_base": 0.0,
|
| 1650 |
+
"selected_utility": 0.19090841710567474,
|
| 1651 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1652 |
+
"selector_regret": 0.02432851493358612,
|
| 1653 |
+
"success_selector_gap": 0.0,
|
| 1654 |
+
"success_support_gap": 1.0,
|
| 1655 |
+
"support_gap": 1.7847630679607391,
|
| 1656 |
+
"tau": 0.3741559563273496
|
| 1657 |
+
},
|
| 1658 |
+
"278008524/train0": {
|
| 1659 |
+
"base_success": 0.0,
|
| 1660 |
+
"base_utility": 0.042734989896416664,
|
| 1661 |
+
"coverage": 0.0,
|
| 1662 |
+
"execute_generated": 0.0,
|
| 1663 |
+
"fallback_rate": 1.0,
|
| 1664 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1665 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1666 |
+
"outcome_ptr": 1.0,
|
| 1667 |
+
"predicted_margin": 0.3018022542600298,
|
| 1668 |
+
"proposal_oracle_success": 0.5,
|
| 1669 |
+
"proposal_oracle_utility": 1.0287093725055456,
|
| 1670 |
+
"selected_candidate_index": 5.0,
|
| 1671 |
+
"selected_success": 0.0,
|
| 1672 |
+
"selected_success_gain_over_base": 0.0,
|
| 1673 |
+
"selected_utility": 0.042734989896416664,
|
| 1674 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1675 |
+
"selector_regret": 0.985974382609129,
|
| 1676 |
+
"success_selector_gap": 0.5,
|
| 1677 |
+
"success_support_gap": 0.0,
|
| 1678 |
+
"support_gap": 0.08519926853477955,
|
| 1679 |
+
"tau": 0.3741559563273496
|
| 1680 |
+
},
|
| 1681 |
+
"278008524/train1": {
|
| 1682 |
+
"base_success": 0.0,
|
| 1683 |
+
"base_utility": 0.042734989896416664,
|
| 1684 |
+
"coverage": 0.5,
|
| 1685 |
+
"execute_generated": 0.5,
|
| 1686 |
+
"fallback_rate": 0.5,
|
| 1687 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1688 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1689 |
+
"outcome_ptr": 1.0,
|
| 1690 |
+
"predicted_margin": 0.4103646234410795,
|
| 1691 |
+
"proposal_oracle_success": 0.5,
|
| 1692 |
+
"proposal_oracle_utility": 1.0376745946705341,
|
| 1693 |
+
"selected_candidate_index": 0.5,
|
| 1694 |
+
"selected_success": 0.0,
|
| 1695 |
+
"selected_success_gain_over_base": 0.0,
|
| 1696 |
+
"selected_utility": 0.048898130655288696,
|
| 1697 |
+
"selected_utility_gain_over_base": 0.006163140758872032,
|
| 1698 |
+
"selector_regret": 0.9887764640152454,
|
| 1699 |
+
"success_selector_gap": 0.5,
|
| 1700 |
+
"success_support_gap": 0.0,
|
| 1701 |
+
"support_gap": 0.07623404636979103,
|
| 1702 |
+
"tau": 0.3741559563273496
|
| 1703 |
+
},
|
| 1704 |
+
"278008524/train2": {
|
| 1705 |
+
"base_success": 0.0,
|
| 1706 |
+
"base_utility": 0.042734989896416664,
|
| 1707 |
+
"coverage": 0.5,
|
| 1708 |
+
"execute_generated": 0.5,
|
| 1709 |
+
"fallback_rate": 0.5,
|
| 1710 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1711 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1712 |
+
"outcome_ptr": 1.0,
|
| 1713 |
+
"predicted_margin": 0.3708292723058839,
|
| 1714 |
+
"proposal_oracle_success": 0.5,
|
| 1715 |
+
"proposal_oracle_utility": 1.1359489113092422,
|
| 1716 |
+
"selected_candidate_index": 3.5,
|
| 1717 |
+
"selected_success": 0.5,
|
| 1718 |
+
"selected_success_gain_over_base": 0.5,
|
| 1719 |
+
"selected_utility": 1.0179431531578302,
|
| 1720 |
+
"selected_utility_gain_over_base": 0.9752081632614136,
|
| 1721 |
+
"selector_regret": 0.11800575815141201,
|
| 1722 |
+
"success_selector_gap": 0.0,
|
| 1723 |
+
"success_support_gap": 0.0,
|
| 1724 |
+
"support_gap": 0.0,
|
| 1725 |
+
"tau": 0.3741559563273496
|
| 1726 |
+
},
|
| 1727 |
+
"307068879/train0": {
|
| 1728 |
+
"base_success": 0.0,
|
| 1729 |
+
"base_utility": 0.6000905632972717,
|
| 1730 |
+
"coverage": 1.0,
|
| 1731 |
+
"execute_generated": 1.0,
|
| 1732 |
+
"fallback_rate": 0.0,
|
| 1733 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1734 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1735 |
+
"outcome_ptr": 0.0,
|
| 1736 |
+
"predicted_margin": 0.4702558631466304,
|
| 1737 |
+
"proposal_oracle_success": 0.0,
|
| 1738 |
+
"proposal_oracle_utility": 0.2115575522184372,
|
| 1739 |
+
"selected_candidate_index": 3.0,
|
| 1740 |
+
"selected_success": 0.0,
|
| 1741 |
+
"selected_success_gain_over_base": 0.0,
|
| 1742 |
+
"selected_utility": 0.20163558423519135,
|
| 1743 |
+
"selected_utility_gain_over_base": -0.3984549790620804,
|
| 1744 |
+
"selector_regret": 0.00992196798324585,
|
| 1745 |
+
"success_selector_gap": 0.0,
|
| 1746 |
+
"success_support_gap": 1.0,
|
| 1747 |
+
"support_gap": 1.7884424477815628,
|
| 1748 |
+
"tau": 0.3741559563273496
|
| 1749 |
+
},
|
| 1750 |
+
"307068879/train1": {
|
| 1751 |
+
"base_success": 0.0,
|
| 1752 |
+
"base_utility": 0.6000905632972717,
|
| 1753 |
+
"coverage": 1.0,
|
| 1754 |
+
"execute_generated": 1.0,
|
| 1755 |
+
"fallback_rate": 0.0,
|
| 1756 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1757 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1758 |
+
"outcome_ptr": 0.0,
|
| 1759 |
+
"predicted_margin": 0.3755843205364714,
|
| 1760 |
+
"proposal_oracle_success": 0.0,
|
| 1761 |
+
"proposal_oracle_utility": 0.5876073241233826,
|
| 1762 |
+
"selected_candidate_index": 5.0,
|
| 1763 |
+
"selected_success": 0.0,
|
| 1764 |
+
"selected_success_gain_over_base": 0.0,
|
| 1765 |
+
"selected_utility": 0.21116642653942108,
|
| 1766 |
+
"selected_utility_gain_over_base": -0.38892413675785065,
|
| 1767 |
+
"selector_regret": 0.3764408975839615,
|
| 1768 |
+
"success_selector_gap": 0.0,
|
| 1769 |
+
"success_support_gap": 1.0,
|
| 1770 |
+
"support_gap": 1.4123926758766174,
|
| 1771 |
+
"tau": 0.3741559563273496
|
| 1772 |
+
},
|
| 1773 |
+
"307068879/train2": {
|
| 1774 |
+
"base_success": 0.0,
|
| 1775 |
+
"base_utility": 0.6000905632972717,
|
| 1776 |
+
"coverage": 0.0,
|
| 1777 |
+
"execute_generated": 0.0,
|
| 1778 |
+
"fallback_rate": 1.0,
|
| 1779 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1780 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1781 |
+
"outcome_ptr": 0.0,
|
| 1782 |
+
"predicted_margin": 0.32005010012998786,
|
| 1783 |
+
"proposal_oracle_success": 0.0,
|
| 1784 |
+
"proposal_oracle_utility": 0.22727864980697632,
|
| 1785 |
+
"selected_candidate_index": 5.0,
|
| 1786 |
+
"selected_success": 0.0,
|
| 1787 |
+
"selected_success_gain_over_base": 0.0,
|
| 1788 |
+
"selected_utility": 0.6000905632972717,
|
| 1789 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1790 |
+
"selector_regret": 0.0,
|
| 1791 |
+
"success_selector_gap": 0.0,
|
| 1792 |
+
"success_support_gap": 1.0,
|
| 1793 |
+
"support_gap": 1.7727213501930237,
|
| 1794 |
+
"tau": 0.3741559563273496
|
| 1795 |
+
},
|
| 1796 |
+
"412102563/train0": {
|
| 1797 |
+
"base_success": 1.0,
|
| 1798 |
+
"base_utility": 2.0,
|
| 1799 |
+
"coverage": 0.0,
|
| 1800 |
+
"execute_generated": 0.0,
|
| 1801 |
+
"fallback_rate": 1.0,
|
| 1802 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1803 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1804 |
+
"outcome_ptr": 0.0,
|
| 1805 |
+
"predicted_margin": 0.28607089947933784,
|
| 1806 |
+
"proposal_oracle_success": 1.0,
|
| 1807 |
+
"proposal_oracle_utility": 2.0,
|
| 1808 |
+
"selected_candidate_index": 3.0,
|
| 1809 |
+
"selected_success": 1.0,
|
| 1810 |
+
"selected_success_gain_over_base": 0.0,
|
| 1811 |
+
"selected_utility": 2.0,
|
| 1812 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1813 |
+
"selector_regret": 0.0,
|
| 1814 |
+
"success_selector_gap": 0.0,
|
| 1815 |
+
"success_support_gap": 0.0,
|
| 1816 |
+
"support_gap": 0.0,
|
| 1817 |
+
"tau": 0.3741559563273496
|
| 1818 |
+
},
|
| 1819 |
+
"412102563/train1": {
|
| 1820 |
+
"base_success": 1.0,
|
| 1821 |
+
"base_utility": 2.0,
|
| 1822 |
+
"coverage": 0.0,
|
| 1823 |
+
"execute_generated": 0.0,
|
| 1824 |
+
"fallback_rate": 1.0,
|
| 1825 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1826 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1827 |
+
"outcome_ptr": 0.0,
|
| 1828 |
+
"predicted_margin": 0.3570017249937056,
|
| 1829 |
+
"proposal_oracle_success": 1.0,
|
| 1830 |
+
"proposal_oracle_utility": 2.0,
|
| 1831 |
+
"selected_candidate_index": 7.0,
|
| 1832 |
+
"selected_success": 1.0,
|
| 1833 |
+
"selected_success_gain_over_base": 0.0,
|
| 1834 |
+
"selected_utility": 2.0,
|
| 1835 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1836 |
+
"selector_regret": 0.0,
|
| 1837 |
+
"success_selector_gap": 0.0,
|
| 1838 |
+
"success_support_gap": 0.0,
|
| 1839 |
+
"support_gap": 0.0,
|
| 1840 |
+
"tau": 0.3741559563273496
|
| 1841 |
+
},
|
| 1842 |
+
"412102563/train2": {
|
| 1843 |
+
"base_success": 1.0,
|
| 1844 |
+
"base_utility": 2.0,
|
| 1845 |
+
"coverage": 0.0,
|
| 1846 |
+
"execute_generated": 0.0,
|
| 1847 |
+
"fallback_rate": 1.0,
|
| 1848 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1849 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1850 |
+
"outcome_ptr": 0.0,
|
| 1851 |
+
"predicted_margin": 0.37134486499196434,
|
| 1852 |
+
"proposal_oracle_success": 1.0,
|
| 1853 |
+
"proposal_oracle_utility": 2.0,
|
| 1854 |
+
"selected_candidate_index": 7.0,
|
| 1855 |
+
"selected_success": 1.0,
|
| 1856 |
+
"selected_success_gain_over_base": 0.0,
|
| 1857 |
+
"selected_utility": 2.0,
|
| 1858 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1859 |
+
"selector_regret": 0.0,
|
| 1860 |
+
"success_selector_gap": 0.0,
|
| 1861 |
+
"success_support_gap": 0.0,
|
| 1862 |
+
"support_gap": 0.0,
|
| 1863 |
+
"tau": 0.3741559563273496
|
| 1864 |
+
},
|
| 1865 |
+
"440577711/train0": {
|
| 1866 |
+
"base_success": 0.0,
|
| 1867 |
+
"base_utility": 0.036152780055999756,
|
| 1868 |
+
"coverage": 1.0,
|
| 1869 |
+
"execute_generated": 1.0,
|
| 1870 |
+
"fallback_rate": 0.0,
|
| 1871 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1872 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1873 |
+
"outcome_ptr": 1.0,
|
| 1874 |
+
"predicted_margin": 0.5804248011896158,
|
| 1875 |
+
"proposal_oracle_success": 1.0,
|
| 1876 |
+
"proposal_oracle_utility": 2.0,
|
| 1877 |
+
"selected_candidate_index": 0.0,
|
| 1878 |
+
"selected_success": 1.0,
|
| 1879 |
+
"selected_success_gain_over_base": 1.0,
|
| 1880 |
+
"selected_utility": 2.0,
|
| 1881 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1882 |
+
"selector_regret": 0.0,
|
| 1883 |
+
"success_selector_gap": 0.0,
|
| 1884 |
+
"success_support_gap": 0.0,
|
| 1885 |
+
"support_gap": 0.0,
|
| 1886 |
+
"tau": 0.3741559563273496
|
| 1887 |
+
},
|
| 1888 |
+
"440577711/train1": {
|
| 1889 |
+
"base_success": 0.0,
|
| 1890 |
+
"base_utility": 0.036152780055999756,
|
| 1891 |
+
"coverage": 1.0,
|
| 1892 |
+
"execute_generated": 1.0,
|
| 1893 |
+
"fallback_rate": 0.0,
|
| 1894 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1895 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1896 |
+
"outcome_ptr": 1.0,
|
| 1897 |
+
"predicted_margin": 0.5938315939300237,
|
| 1898 |
+
"proposal_oracle_success": 1.0,
|
| 1899 |
+
"proposal_oracle_utility": 2.0,
|
| 1900 |
+
"selected_candidate_index": 1.0,
|
| 1901 |
+
"selected_success": 0.0,
|
| 1902 |
+
"selected_success_gain_over_base": 0.0,
|
| 1903 |
+
"selected_utility": 0.02717691659927368,
|
| 1904 |
+
"selected_utility_gain_over_base": -0.008975863456726074,
|
| 1905 |
+
"selector_regret": 1.9728230834007263,
|
| 1906 |
+
"success_selector_gap": 1.0,
|
| 1907 |
+
"success_support_gap": 0.0,
|
| 1908 |
+
"support_gap": 0.0,
|
| 1909 |
+
"tau": 0.3741559563273496
|
| 1910 |
+
},
|
| 1911 |
+
"440577711/train2": {
|
| 1912 |
+
"base_success": 0.0,
|
| 1913 |
+
"base_utility": 0.036152780055999756,
|
| 1914 |
+
"coverage": 1.0,
|
| 1915 |
+
"execute_generated": 1.0,
|
| 1916 |
+
"fallback_rate": 0.0,
|
| 1917 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1918 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1919 |
+
"outcome_ptr": 1.0,
|
| 1920 |
+
"predicted_margin": 0.5137779251382697,
|
| 1921 |
+
"proposal_oracle_success": 1.0,
|
| 1922 |
+
"proposal_oracle_utility": 2.0,
|
| 1923 |
+
"selected_candidate_index": 0.0,
|
| 1924 |
+
"selected_success": 1.0,
|
| 1925 |
+
"selected_success_gain_over_base": 1.0,
|
| 1926 |
+
"selected_utility": 2.0,
|
| 1927 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1928 |
+
"selector_regret": 0.0,
|
| 1929 |
+
"success_selector_gap": 0.0,
|
| 1930 |
+
"success_support_gap": 0.0,
|
| 1931 |
+
"support_gap": 0.0,
|
| 1932 |
+
"tau": 0.3741559563273496
|
| 1933 |
+
},
|
| 1934 |
+
"441046872/train0": {
|
| 1935 |
+
"base_success": 0.0,
|
| 1936 |
+
"base_utility": 0.6999551653862,
|
| 1937 |
+
"coverage": 1.0,
|
| 1938 |
+
"execute_generated": 1.0,
|
| 1939 |
+
"fallback_rate": 0.0,
|
| 1940 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1941 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1942 |
+
"outcome_ptr": 0.0,
|
| 1943 |
+
"predicted_margin": 0.4581486946189829,
|
| 1944 |
+
"proposal_oracle_success": 0.0,
|
| 1945 |
+
"proposal_oracle_utility": 0.5148025155067444,
|
| 1946 |
+
"selected_candidate_index": 0.0,
|
| 1947 |
+
"selected_success": 0.0,
|
| 1948 |
+
"selected_success_gain_over_base": 0.0,
|
| 1949 |
+
"selected_utility": 0.21190984547138214,
|
| 1950 |
+
"selected_utility_gain_over_base": -0.4880453199148178,
|
| 1951 |
+
"selector_regret": 0.30289267003536224,
|
| 1952 |
+
"success_selector_gap": 0.0,
|
| 1953 |
+
"success_support_gap": 1.0,
|
| 1954 |
+
"support_gap": 1.4851974844932556,
|
| 1955 |
+
"tau": 0.3741559563273496
|
| 1956 |
+
},
|
| 1957 |
+
"441046872/train1": {
|
| 1958 |
+
"base_success": 0.0,
|
| 1959 |
+
"base_utility": 0.6999551653862,
|
| 1960 |
+
"coverage": 0.0,
|
| 1961 |
+
"execute_generated": 0.0,
|
| 1962 |
+
"fallback_rate": 1.0,
|
| 1963 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1964 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1965 |
+
"outcome_ptr": 1.0,
|
| 1966 |
+
"predicted_margin": 0.3622665827290821,
|
| 1967 |
+
"proposal_oracle_success": 0.0,
|
| 1968 |
+
"proposal_oracle_utility": 0.7233588695526123,
|
| 1969 |
+
"selected_candidate_index": 2.0,
|
| 1970 |
+
"selected_success": 0.0,
|
| 1971 |
+
"selected_success_gain_over_base": 0.0,
|
| 1972 |
+
"selected_utility": 0.6999551653862,
|
| 1973 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1974 |
+
"selector_regret": 0.023403704166412354,
|
| 1975 |
+
"success_selector_gap": 0.0,
|
| 1976 |
+
"success_support_gap": 1.0,
|
| 1977 |
+
"support_gap": 1.2766411304473877,
|
| 1978 |
+
"tau": 0.3741559563273496
|
| 1979 |
+
},
|
| 1980 |
+
"441046872/train2": {
|
| 1981 |
+
"base_success": 0.0,
|
| 1982 |
+
"base_utility": 0.6999551653862,
|
| 1983 |
+
"coverage": 0.0,
|
| 1984 |
+
"execute_generated": 0.0,
|
| 1985 |
+
"fallback_rate": 1.0,
|
| 1986 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1987 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1988 |
+
"outcome_ptr": 1.0,
|
| 1989 |
+
"predicted_margin": 0.3550679344666073,
|
| 1990 |
+
"proposal_oracle_success": 0.0,
|
| 1991 |
+
"proposal_oracle_utility": 0.7130289077758789,
|
| 1992 |
+
"selected_candidate_index": 1.0,
|
| 1993 |
+
"selected_success": 0.0,
|
| 1994 |
+
"selected_success_gain_over_base": 0.0,
|
| 1995 |
+
"selected_utility": 0.6999551653862,
|
| 1996 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1997 |
+
"selector_regret": 0.013073742389678955,
|
| 1998 |
+
"success_selector_gap": 0.0,
|
| 1999 |
+
"success_support_gap": 1.0,
|
| 2000 |
+
"support_gap": 1.286971092224121,
|
| 2001 |
+
"tau": 0.3741559563273496
|
| 2002 |
+
},
|
| 2003 |
+
"509430392/train0": {
|
| 2004 |
+
"base_success": 0.0,
|
| 2005 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2006 |
+
"coverage": 1.0,
|
| 2007 |
+
"execute_generated": 1.0,
|
| 2008 |
+
"fallback_rate": 0.0,
|
| 2009 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2010 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2011 |
+
"outcome_ptr": 1.0,
|
| 2012 |
+
"predicted_margin": 0.44036449124726545,
|
| 2013 |
+
"proposal_oracle_success": 1.0,
|
| 2014 |
+
"proposal_oracle_utility": 2.0,
|
| 2015 |
+
"selected_candidate_index": 0.0,
|
| 2016 |
+
"selected_success": 0.0,
|
| 2017 |
+
"selected_success_gain_over_base": 0.0,
|
| 2018 |
+
"selected_utility": 1.6689300537109375e-06,
|
| 2019 |
+
"selected_utility_gain_over_base": 1.4454126358032227e-06,
|
| 2020 |
+
"selector_regret": 1.9999983310699463,
|
| 2021 |
+
"success_selector_gap": 1.0,
|
| 2022 |
+
"success_support_gap": 0.0,
|
| 2023 |
+
"support_gap": 0.0,
|
| 2024 |
+
"tau": 0.3741559563273496
|
| 2025 |
+
},
|
| 2026 |
+
"509430392/train1": {
|
| 2027 |
+
"base_success": 0.0,
|
| 2028 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2029 |
+
"coverage": 1.0,
|
| 2030 |
+
"execute_generated": 1.0,
|
| 2031 |
+
"fallback_rate": 0.0,
|
| 2032 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2033 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2034 |
+
"outcome_ptr": 1.0,
|
| 2035 |
+
"predicted_margin": 0.4239855826799761,
|
| 2036 |
+
"proposal_oracle_success": 0.0,
|
| 2037 |
+
"proposal_oracle_utility": 6.164610385894775e-05,
|
| 2038 |
+
"selected_candidate_index": 5.0,
|
| 2039 |
+
"selected_success": 0.0,
|
| 2040 |
+
"selected_success_gain_over_base": 0.0,
|
| 2041 |
+
"selected_utility": 1.564621925354004e-06,
|
| 2042 |
+
"selected_utility_gain_over_base": 1.341104507446289e-06,
|
| 2043 |
+
"selector_regret": 6.008148193359375e-05,
|
| 2044 |
+
"success_selector_gap": 0.0,
|
| 2045 |
+
"success_support_gap": 1.0,
|
| 2046 |
+
"support_gap": 1.999938353896141,
|
| 2047 |
+
"tau": 0.3741559563273496
|
| 2048 |
+
},
|
| 2049 |
+
"509430392/train2": {
|
| 2050 |
+
"base_success": 0.0,
|
| 2051 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2052 |
+
"coverage": 0.0,
|
| 2053 |
+
"execute_generated": 0.0,
|
| 2054 |
+
"fallback_rate": 1.0,
|
| 2055 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2056 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2057 |
+
"outcome_ptr": 1.0,
|
| 2058 |
+
"predicted_margin": 0.329217542757152,
|
| 2059 |
+
"proposal_oracle_success": 0.0,
|
| 2060 |
+
"proposal_oracle_utility": 5.424022674560547e-06,
|
| 2061 |
+
"selected_candidate_index": 1.0,
|
| 2062 |
+
"selected_success": 0.0,
|
| 2063 |
+
"selected_success_gain_over_base": 0.0,
|
| 2064 |
+
"selected_utility": 2.2351741790771484e-07,
|
| 2065 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2066 |
+
"selector_regret": 5.200505256652832e-06,
|
| 2067 |
+
"success_selector_gap": 0.0,
|
| 2068 |
+
"success_support_gap": 1.0,
|
| 2069 |
+
"support_gap": 1.9999945759773254,
|
| 2070 |
+
"tau": 0.3741559563273496
|
| 2071 |
+
},
|
| 2072 |
+
"585904130/train0": {
|
| 2073 |
+
"base_success": 0.0,
|
| 2074 |
+
"base_utility": 0.18171554803848267,
|
| 2075 |
+
"coverage": 0.0,
|
| 2076 |
+
"execute_generated": 0.0,
|
| 2077 |
+
"fallback_rate": 1.0,
|
| 2078 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2079 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2080 |
+
"outcome_ptr": 1.0,
|
| 2081 |
+
"predicted_margin": 0.3029974497765087,
|
| 2082 |
+
"proposal_oracle_success": 1.0,
|
| 2083 |
+
"proposal_oracle_utility": 2.0,
|
| 2084 |
+
"selected_candidate_index": 0.0,
|
| 2085 |
+
"selected_success": 0.0,
|
| 2086 |
+
"selected_success_gain_over_base": 0.0,
|
| 2087 |
+
"selected_utility": 0.18171554803848267,
|
| 2088 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2089 |
+
"selector_regret": 1.8182844519615173,
|
| 2090 |
+
"success_selector_gap": 1.0,
|
| 2091 |
+
"success_support_gap": 0.0,
|
| 2092 |
+
"support_gap": 0.0,
|
| 2093 |
+
"tau": 0.3741559563273496
|
| 2094 |
+
},
|
| 2095 |
+
"585904130/train1": {
|
| 2096 |
+
"base_success": 0.0,
|
| 2097 |
+
"base_utility": 0.18171554803848267,
|
| 2098 |
+
"coverage": 0.0,
|
| 2099 |
+
"execute_generated": 0.0,
|
| 2100 |
+
"fallback_rate": 1.0,
|
| 2101 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2102 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2103 |
+
"outcome_ptr": 1.0,
|
| 2104 |
+
"predicted_margin": 0.28994114758485556,
|
| 2105 |
+
"proposal_oracle_success": 1.0,
|
| 2106 |
+
"proposal_oracle_utility": 2.0,
|
| 2107 |
+
"selected_candidate_index": 0.0,
|
| 2108 |
+
"selected_success": 0.0,
|
| 2109 |
+
"selected_success_gain_over_base": 0.0,
|
| 2110 |
+
"selected_utility": 0.18171554803848267,
|
| 2111 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2112 |
+
"selector_regret": 1.8182844519615173,
|
| 2113 |
+
"success_selector_gap": 1.0,
|
| 2114 |
+
"success_support_gap": 0.0,
|
| 2115 |
+
"support_gap": 0.0,
|
| 2116 |
+
"tau": 0.3741559563273496
|
| 2117 |
+
},
|
| 2118 |
+
"585904130/train2": {
|
| 2119 |
+
"base_success": 0.0,
|
| 2120 |
+
"base_utility": 0.18171554803848267,
|
| 2121 |
+
"coverage": 0.0,
|
| 2122 |
+
"execute_generated": 0.0,
|
| 2123 |
+
"fallback_rate": 1.0,
|
| 2124 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2125 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2126 |
+
"outcome_ptr": 1.0,
|
| 2127 |
+
"predicted_margin": 0.2844961787136048,
|
| 2128 |
+
"proposal_oracle_success": 1.0,
|
| 2129 |
+
"proposal_oracle_utility": 2.0,
|
| 2130 |
+
"selected_candidate_index": 2.0,
|
| 2131 |
+
"selected_success": 0.0,
|
| 2132 |
+
"selected_success_gain_over_base": 0.0,
|
| 2133 |
+
"selected_utility": 0.18171554803848267,
|
| 2134 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2135 |
+
"selector_regret": 1.8182844519615173,
|
| 2136 |
+
"success_selector_gap": 1.0,
|
| 2137 |
+
"success_support_gap": 0.0,
|
| 2138 |
+
"support_gap": 0.0,
|
| 2139 |
+
"tau": 0.3741559563273496
|
| 2140 |
+
},
|
| 2141 |
+
"608016290/train0": {
|
| 2142 |
+
"base_success": 0.0,
|
| 2143 |
+
"base_utility": 0.725701630115509,
|
| 2144 |
+
"coverage": 0.0,
|
| 2145 |
+
"execute_generated": 0.0,
|
| 2146 |
+
"fallback_rate": 1.0,
|
| 2147 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2148 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2149 |
+
"outcome_ptr": 1.0,
|
| 2150 |
+
"predicted_margin": 0.3621977651439929,
|
| 2151 |
+
"proposal_oracle_success": 1.0,
|
| 2152 |
+
"proposal_oracle_utility": 2.0,
|
| 2153 |
+
"selected_candidate_index": 5.0,
|
| 2154 |
+
"selected_success": 0.0,
|
| 2155 |
+
"selected_success_gain_over_base": 0.0,
|
| 2156 |
+
"selected_utility": 0.725701630115509,
|
| 2157 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2158 |
+
"selector_regret": 1.274298369884491,
|
| 2159 |
+
"success_selector_gap": 1.0,
|
| 2160 |
+
"success_support_gap": 0.0,
|
| 2161 |
+
"support_gap": 0.0,
|
| 2162 |
+
"tau": 0.3741559563273496
|
| 2163 |
+
},
|
| 2164 |
+
"608016290/train1": {
|
| 2165 |
+
"base_success": 0.0,
|
| 2166 |
+
"base_utility": 0.725701630115509,
|
| 2167 |
+
"coverage": 0.0,
|
| 2168 |
+
"execute_generated": 0.0,
|
| 2169 |
+
"fallback_rate": 1.0,
|
| 2170 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2171 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2172 |
+
"outcome_ptr": 1.0,
|
| 2173 |
+
"predicted_margin": 0.3622665827290821,
|
| 2174 |
+
"proposal_oracle_success": 1.0,
|
| 2175 |
+
"proposal_oracle_utility": 2.0,
|
| 2176 |
+
"selected_candidate_index": 1.0,
|
| 2177 |
+
"selected_success": 0.0,
|
| 2178 |
+
"selected_success_gain_over_base": 0.0,
|
| 2179 |
+
"selected_utility": 0.725701630115509,
|
| 2180 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2181 |
+
"selector_regret": 1.274298369884491,
|
| 2182 |
+
"success_selector_gap": 1.0,
|
| 2183 |
+
"success_support_gap": 0.0,
|
| 2184 |
+
"support_gap": 0.0,
|
| 2185 |
+
"tau": 0.3741559563273496
|
| 2186 |
+
},
|
| 2187 |
+
"608016290/train2": {
|
| 2188 |
+
"base_success": 0.0,
|
| 2189 |
+
"base_utility": 0.725701630115509,
|
| 2190 |
+
"coverage": 0.0,
|
| 2191 |
+
"execute_generated": 0.0,
|
| 2192 |
+
"fallback_rate": 1.0,
|
| 2193 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2194 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2195 |
+
"outcome_ptr": 0.0,
|
| 2196 |
+
"predicted_margin": 0.2897073440884107,
|
| 2197 |
+
"proposal_oracle_success": 0.0,
|
| 2198 |
+
"proposal_oracle_utility": 0.6825780272483826,
|
| 2199 |
+
"selected_candidate_index": 4.0,
|
| 2200 |
+
"selected_success": 0.0,
|
| 2201 |
+
"selected_success_gain_over_base": 0.0,
|
| 2202 |
+
"selected_utility": 0.725701630115509,
|
| 2203 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2204 |
+
"selector_regret": 0.0,
|
| 2205 |
+
"success_selector_gap": 0.0,
|
| 2206 |
+
"success_support_gap": 1.0,
|
| 2207 |
+
"support_gap": 1.3174219727516174,
|
| 2208 |
+
"tau": 0.3741559563273496
|
| 2209 |
+
},
|
| 2210 |
+
"626486813/train0": {
|
| 2211 |
+
"base_success": 0.0,
|
| 2212 |
+
"base_utility": 0.00509834272088483,
|
| 2213 |
+
"coverage": 1.0,
|
| 2214 |
+
"execute_generated": 1.0,
|
| 2215 |
+
"fallback_rate": 0.0,
|
| 2216 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2217 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2218 |
+
"outcome_ptr": 1.0,
|
| 2219 |
+
"predicted_margin": 0.4254541339617848,
|
| 2220 |
+
"proposal_oracle_success": 0.0,
|
| 2221 |
+
"proposal_oracle_utility": 0.043898362666368484,
|
| 2222 |
+
"selected_candidate_index": 2.0,
|
| 2223 |
+
"selected_success": 0.0,
|
| 2224 |
+
"selected_success_gain_over_base": 0.0,
|
| 2225 |
+
"selected_utility": 0.021180112613365054,
|
| 2226 |
+
"selected_utility_gain_over_base": 0.016081769892480224,
|
| 2227 |
+
"selector_regret": 0.02271825005300343,
|
| 2228 |
+
"success_selector_gap": 0.0,
|
| 2229 |
+
"success_support_gap": 0.0,
|
| 2230 |
+
"support_gap": 0.12241578102111816,
|
| 2231 |
+
"tau": 0.3741559563273496
|
| 2232 |
+
},
|
| 2233 |
+
"626486813/train1": {
|
| 2234 |
+
"base_success": 0.0,
|
| 2235 |
+
"base_utility": 0.00509834272088483,
|
| 2236 |
+
"coverage": 1.0,
|
| 2237 |
+
"execute_generated": 1.0,
|
| 2238 |
+
"fallback_rate": 0.0,
|
| 2239 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2240 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2241 |
+
"outcome_ptr": 1.0,
|
| 2242 |
+
"predicted_margin": 0.5266725872996079,
|
| 2243 |
+
"proposal_oracle_success": 0.0,
|
| 2244 |
+
"proposal_oracle_utility": 0.030555277597159147,
|
| 2245 |
+
"selected_candidate_index": 1.5,
|
| 2246 |
+
"selected_success": 0.0,
|
| 2247 |
+
"selected_success_gain_over_base": 0.0,
|
| 2248 |
+
"selected_utility": 0.011683384887874126,
|
| 2249 |
+
"selected_utility_gain_over_base": 0.006585042166989297,
|
| 2250 |
+
"selector_regret": 0.01887189270928502,
|
| 2251 |
+
"success_selector_gap": 0.0,
|
| 2252 |
+
"success_support_gap": 0.0,
|
| 2253 |
+
"support_gap": 0.13502710359171033,
|
| 2254 |
+
"tau": 0.3741559563273496
|
| 2255 |
+
},
|
| 2256 |
+
"626486813/train2": {
|
| 2257 |
+
"base_success": 0.0,
|
| 2258 |
+
"base_utility": 0.00509834272088483,
|
| 2259 |
+
"coverage": 0.5,
|
| 2260 |
+
"execute_generated": 0.5,
|
| 2261 |
+
"fallback_rate": 0.5,
|
| 2262 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2263 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2264 |
+
"outcome_ptr": 1.0,
|
| 2265 |
+
"predicted_margin": 0.37597652661121267,
|
| 2266 |
+
"proposal_oracle_success": 0.0,
|
| 2267 |
+
"proposal_oracle_utility": 0.03856666944921017,
|
| 2268 |
+
"selected_candidate_index": 0.0,
|
| 2269 |
+
"selected_success": 0.0,
|
| 2270 |
+
"selected_success_gain_over_base": 0.0,
|
| 2271 |
+
"selected_utility": 0.015375842805951834,
|
| 2272 |
+
"selected_utility_gain_over_base": 0.010277500085067004,
|
| 2273 |
+
"selector_regret": 0.023190826643258333,
|
| 2274 |
+
"success_selector_gap": 0.0,
|
| 2275 |
+
"success_support_gap": 0.0,
|
| 2276 |
+
"support_gap": 0.1270157117396593,
|
| 2277 |
+
"tau": 0.3741559563273496
|
| 2278 |
+
},
|
| 2279 |
+
"636680137/train0": {
|
| 2280 |
+
"base_success": 0.0,
|
| 2281 |
+
"base_utility": 0.08313504606485367,
|
| 2282 |
+
"coverage": 1.0,
|
| 2283 |
+
"execute_generated": 1.0,
|
| 2284 |
+
"fallback_rate": 0.0,
|
| 2285 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2286 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2287 |
+
"outcome_ptr": 1.0,
|
| 2288 |
+
"predicted_margin": 0.48545416581659245,
|
| 2289 |
+
"proposal_oracle_success": 0.0,
|
| 2290 |
+
"proposal_oracle_utility": 0.08826130628585815,
|
| 2291 |
+
"selected_candidate_index": 2.0,
|
| 2292 |
+
"selected_success": 0.0,
|
| 2293 |
+
"selected_success_gain_over_base": 0.0,
|
| 2294 |
+
"selected_utility": 0.01579594612121582,
|
| 2295 |
+
"selected_utility_gain_over_base": -0.06733909994363785,
|
| 2296 |
+
"selector_regret": 0.07246536016464233,
|
| 2297 |
+
"success_selector_gap": 0.0,
|
| 2298 |
+
"success_support_gap": 0.0,
|
| 2299 |
+
"support_gap": 0.0823030173778534,
|
| 2300 |
+
"tau": 0.3741559563273496
|
| 2301 |
+
},
|
| 2302 |
+
"636680137/train1": {
|
| 2303 |
+
"base_success": 0.0,
|
| 2304 |
+
"base_utility": 0.08313504606485367,
|
| 2305 |
+
"coverage": 1.0,
|
| 2306 |
+
"execute_generated": 1.0,
|
| 2307 |
+
"fallback_rate": 0.0,
|
| 2308 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2309 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2310 |
+
"outcome_ptr": 0.0,
|
| 2311 |
+
"predicted_margin": 0.43111137474421807,
|
| 2312 |
+
"proposal_oracle_success": 0.0,
|
| 2313 |
+
"proposal_oracle_utility": 0.06741118431091309,
|
| 2314 |
+
"selected_candidate_index": 1.0,
|
| 2315 |
+
"selected_success": 0.0,
|
| 2316 |
+
"selected_success_gain_over_base": 0.0,
|
| 2317 |
+
"selected_utility": 0.017789265140891075,
|
| 2318 |
+
"selected_utility_gain_over_base": -0.0653457809239626,
|
| 2319 |
+
"selector_regret": 0.04962191917002201,
|
| 2320 |
+
"success_selector_gap": 0.0,
|
| 2321 |
+
"success_support_gap": 0.0,
|
| 2322 |
+
"support_gap": 0.10315313935279846,
|
| 2323 |
+
"tau": 0.3741559563273496
|
| 2324 |
+
},
|
| 2325 |
+
"636680137/train2": {
|
| 2326 |
+
"base_success": 0.0,
|
| 2327 |
+
"base_utility": 0.08313504606485367,
|
| 2328 |
+
"coverage": 1.0,
|
| 2329 |
+
"execute_generated": 1.0,
|
| 2330 |
+
"fallback_rate": 0.0,
|
| 2331 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2332 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2333 |
+
"outcome_ptr": 0.0,
|
| 2334 |
+
"predicted_margin": 0.42062384206560416,
|
| 2335 |
+
"proposal_oracle_success": 0.0,
|
| 2336 |
+
"proposal_oracle_utility": 0.0756516233086586,
|
| 2337 |
+
"selected_candidate_index": 2.0,
|
| 2338 |
+
"selected_success": 0.0,
|
| 2339 |
+
"selected_success_gain_over_base": 0.0,
|
| 2340 |
+
"selected_utility": 0.0756516233086586,
|
| 2341 |
+
"selected_utility_gain_over_base": -0.007483422756195068,
|
| 2342 |
+
"selector_regret": 0.0,
|
| 2343 |
+
"success_selector_gap": 0.0,
|
| 2344 |
+
"success_support_gap": 0.0,
|
| 2345 |
+
"support_gap": 0.09491270035505295,
|
| 2346 |
+
"tau": 0.3741559563273496
|
| 2347 |
+
},
|
| 2348 |
+
"655884605/train0": {
|
| 2349 |
+
"base_success": 0.0,
|
| 2350 |
+
"base_utility": 0.16300667822360992,
|
| 2351 |
+
"coverage": 0.0,
|
| 2352 |
+
"execute_generated": 0.0,
|
| 2353 |
+
"fallback_rate": 1.0,
|
| 2354 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2355 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2356 |
+
"outcome_ptr": 0.0,
|
| 2357 |
+
"predicted_margin": 0.2996766962199408,
|
| 2358 |
+
"proposal_oracle_success": 0.0,
|
| 2359 |
+
"proposal_oracle_utility": 0.13732868432998657,
|
| 2360 |
+
"selected_candidate_index": 6.0,
|
| 2361 |
+
"selected_success": 0.0,
|
| 2362 |
+
"selected_success_gain_over_base": 0.0,
|
| 2363 |
+
"selected_utility": 0.16300667822360992,
|
| 2364 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2365 |
+
"selector_regret": 0.0,
|
| 2366 |
+
"success_selector_gap": 0.0,
|
| 2367 |
+
"success_support_gap": 1.0,
|
| 2368 |
+
"support_gap": 1.8626713156700134,
|
| 2369 |
+
"tau": 0.3741559563273496
|
| 2370 |
+
},
|
| 2371 |
+
"655884605/train1": {
|
| 2372 |
+
"base_success": 0.0,
|
| 2373 |
+
"base_utility": 0.16300667822360992,
|
| 2374 |
+
"coverage": 0.0,
|
| 2375 |
+
"execute_generated": 0.0,
|
| 2376 |
+
"fallback_rate": 1.0,
|
| 2377 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2378 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2379 |
+
"outcome_ptr": 1.0,
|
| 2380 |
+
"predicted_margin": 0.32254979421285396,
|
| 2381 |
+
"proposal_oracle_success": 0.0,
|
| 2382 |
+
"proposal_oracle_utility": 0.1651531159877777,
|
| 2383 |
+
"selected_candidate_index": 5.0,
|
| 2384 |
+
"selected_success": 0.0,
|
| 2385 |
+
"selected_success_gain_over_base": 0.0,
|
| 2386 |
+
"selected_utility": 0.16300667822360992,
|
| 2387 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2388 |
+
"selector_regret": 0.0021464377641677856,
|
| 2389 |
+
"success_selector_gap": 0.0,
|
| 2390 |
+
"success_support_gap": 1.0,
|
| 2391 |
+
"support_gap": 1.8348468840122223,
|
| 2392 |
+
"tau": 0.3741559563273496
|
| 2393 |
+
},
|
| 2394 |
+
"655884605/train2": {
|
| 2395 |
+
"base_success": 0.0,
|
| 2396 |
+
"base_utility": 0.16300667822360992,
|
| 2397 |
+
"coverage": 0.0,
|
| 2398 |
+
"execute_generated": 0.0,
|
| 2399 |
+
"fallback_rate": 1.0,
|
| 2400 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2401 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2402 |
+
"outcome_ptr": 1.0,
|
| 2403 |
+
"predicted_margin": 0.31908267001192103,
|
| 2404 |
+
"proposal_oracle_success": 0.0,
|
| 2405 |
+
"proposal_oracle_utility": 0.21447330713272095,
|
| 2406 |
+
"selected_candidate_index": 1.0,
|
| 2407 |
+
"selected_success": 0.0,
|
| 2408 |
+
"selected_success_gain_over_base": 0.0,
|
| 2409 |
+
"selected_utility": 0.16300667822360992,
|
| 2410 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2411 |
+
"selector_regret": 0.05146662890911102,
|
| 2412 |
+
"success_selector_gap": 0.0,
|
| 2413 |
+
"success_support_gap": 1.0,
|
| 2414 |
+
"support_gap": 1.785526692867279,
|
| 2415 |
+
"tau": 0.3741559563273496
|
| 2416 |
+
},
|
| 2417 |
+
"672328262/train0": {
|
| 2418 |
+
"base_success": 1.0,
|
| 2419 |
+
"base_utility": 2.0,
|
| 2420 |
+
"coverage": 0.0,
|
| 2421 |
+
"execute_generated": 0.0,
|
| 2422 |
+
"fallback_rate": 1.0,
|
| 2423 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2424 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2425 |
+
"outcome_ptr": 0.0,
|
| 2426 |
+
"predicted_margin": 0.2791544623573796,
|
| 2427 |
+
"proposal_oracle_success": 1.0,
|
| 2428 |
+
"proposal_oracle_utility": 2.0,
|
| 2429 |
+
"selected_candidate_index": 1.0,
|
| 2430 |
+
"selected_success": 1.0,
|
| 2431 |
+
"selected_success_gain_over_base": 0.0,
|
| 2432 |
+
"selected_utility": 2.0,
|
| 2433 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2434 |
+
"selector_regret": 0.0,
|
| 2435 |
+
"success_selector_gap": 0.0,
|
| 2436 |
+
"success_support_gap": 0.0,
|
| 2437 |
+
"support_gap": 0.0,
|
| 2438 |
+
"tau": 0.3741559563273496
|
| 2439 |
+
},
|
| 2440 |
+
"672328262/train1": {
|
| 2441 |
+
"base_success": 1.0,
|
| 2442 |
+
"base_utility": 2.0,
|
| 2443 |
+
"coverage": 0.0,
|
| 2444 |
+
"execute_generated": 0.0,
|
| 2445 |
+
"fallback_rate": 1.0,
|
| 2446 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2447 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2448 |
+
"outcome_ptr": 0.0,
|
| 2449 |
+
"predicted_margin": 0.3059562851528022,
|
| 2450 |
+
"proposal_oracle_success": 1.0,
|
| 2451 |
+
"proposal_oracle_utility": 2.0,
|
| 2452 |
+
"selected_candidate_index": 0.0,
|
| 2453 |
+
"selected_success": 1.0,
|
| 2454 |
+
"selected_success_gain_over_base": 0.0,
|
| 2455 |
+
"selected_utility": 2.0,
|
| 2456 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2457 |
+
"selector_regret": 0.0,
|
| 2458 |
+
"success_selector_gap": 0.0,
|
| 2459 |
+
"success_support_gap": 0.0,
|
| 2460 |
+
"support_gap": 0.0,
|
| 2461 |
+
"tau": 0.3741559563273496
|
| 2462 |
+
},
|
| 2463 |
+
"672328262/train2": {
|
| 2464 |
+
"base_success": 1.0,
|
| 2465 |
+
"base_utility": 2.0,
|
| 2466 |
+
"coverage": 0.0,
|
| 2467 |
+
"execute_generated": 0.0,
|
| 2468 |
+
"fallback_rate": 1.0,
|
| 2469 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2470 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2471 |
+
"outcome_ptr": 0.0,
|
| 2472 |
+
"predicted_margin": 0.3435013909594266,
|
| 2473 |
+
"proposal_oracle_success": 1.0,
|
| 2474 |
+
"proposal_oracle_utility": 2.0,
|
| 2475 |
+
"selected_candidate_index": 1.0,
|
| 2476 |
+
"selected_success": 1.0,
|
| 2477 |
+
"selected_success_gain_over_base": 0.0,
|
| 2478 |
+
"selected_utility": 2.0,
|
| 2479 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2480 |
+
"selector_regret": 0.0,
|
| 2481 |
+
"success_selector_gap": 0.0,
|
| 2482 |
+
"success_support_gap": 0.0,
|
| 2483 |
+
"support_gap": 0.0,
|
| 2484 |
+
"tau": 0.3741559563273496
|
| 2485 |
+
},
|
| 2486 |
+
"701667486/train0": {
|
| 2487 |
+
"base_success": 1.0,
|
| 2488 |
+
"base_utility": 2.0,
|
| 2489 |
+
"coverage": 0.0,
|
| 2490 |
+
"execute_generated": 0.0,
|
| 2491 |
+
"fallback_rate": 1.0,
|
| 2492 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2493 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2494 |
+
"outcome_ptr": 0.0,
|
| 2495 |
+
"predicted_margin": 0.2996766962199408,
|
| 2496 |
+
"proposal_oracle_success": 1.0,
|
| 2497 |
+
"proposal_oracle_utility": 2.0,
|
| 2498 |
+
"selected_candidate_index": 7.0,
|
| 2499 |
+
"selected_success": 1.0,
|
| 2500 |
+
"selected_success_gain_over_base": 0.0,
|
| 2501 |
+
"selected_utility": 2.0,
|
| 2502 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2503 |
+
"selector_regret": 0.0,
|
| 2504 |
+
"success_selector_gap": 0.0,
|
| 2505 |
+
"success_support_gap": 0.0,
|
| 2506 |
+
"support_gap": 0.0,
|
| 2507 |
+
"tau": 0.3741559563273496
|
| 2508 |
+
},
|
| 2509 |
+
"701667486/train1": {
|
| 2510 |
+
"base_success": 1.0,
|
| 2511 |
+
"base_utility": 2.0,
|
| 2512 |
+
"coverage": 1.0,
|
| 2513 |
+
"execute_generated": 1.0,
|
| 2514 |
+
"fallback_rate": 0.0,
|
| 2515 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2516 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2517 |
+
"outcome_ptr": 0.0,
|
| 2518 |
+
"predicted_margin": 0.3954257212909892,
|
| 2519 |
+
"proposal_oracle_success": 1.0,
|
| 2520 |
+
"proposal_oracle_utility": 2.0,
|
| 2521 |
+
"selected_candidate_index": 7.0,
|
| 2522 |
+
"selected_success": 1.0,
|
| 2523 |
+
"selected_success_gain_over_base": 0.0,
|
| 2524 |
+
"selected_utility": 2.0,
|
| 2525 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2526 |
+
"selector_regret": 0.0,
|
| 2527 |
+
"success_selector_gap": 0.0,
|
| 2528 |
+
"success_support_gap": 0.0,
|
| 2529 |
+
"support_gap": 0.0,
|
| 2530 |
+
"tau": 0.3741559563273496
|
| 2531 |
+
},
|
| 2532 |
+
"701667486/train2": {
|
| 2533 |
+
"base_success": 1.0,
|
| 2534 |
+
"base_utility": 2.0,
|
| 2535 |
+
"coverage": 1.0,
|
| 2536 |
+
"execute_generated": 1.0,
|
| 2537 |
+
"fallback_rate": 0.0,
|
| 2538 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2539 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2540 |
+
"outcome_ptr": 0.0,
|
| 2541 |
+
"predicted_margin": 0.5158707077594902,
|
| 2542 |
+
"proposal_oracle_success": 1.0,
|
| 2543 |
+
"proposal_oracle_utility": 2.0,
|
| 2544 |
+
"selected_candidate_index": 0.0,
|
| 2545 |
+
"selected_success": 1.0,
|
| 2546 |
+
"selected_success_gain_over_base": 0.0,
|
| 2547 |
+
"selected_utility": 2.0,
|
| 2548 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2549 |
+
"selector_regret": 0.0,
|
| 2550 |
+
"success_selector_gap": 0.0,
|
| 2551 |
+
"success_support_gap": 0.0,
|
| 2552 |
+
"support_gap": 0.0,
|
| 2553 |
+
"tau": 0.3741559563273496
|
| 2554 |
+
},
|
| 2555 |
+
"747260437/train0": {
|
| 2556 |
+
"base_success": 1.0,
|
| 2557 |
+
"base_utility": 2.0,
|
| 2558 |
+
"coverage": 0.0,
|
| 2559 |
+
"execute_generated": 0.0,
|
| 2560 |
+
"fallback_rate": 1.0,
|
| 2561 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2562 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2563 |
+
"outcome_ptr": 0.0,
|
| 2564 |
+
"predicted_margin": 0.3303509116866848,
|
| 2565 |
+
"proposal_oracle_success": 0.0,
|
| 2566 |
+
"proposal_oracle_utility": 0.10839563608169556,
|
| 2567 |
+
"selected_candidate_index": 5.0,
|
| 2568 |
+
"selected_success": 1.0,
|
| 2569 |
+
"selected_success_gain_over_base": 0.0,
|
| 2570 |
+
"selected_utility": 2.0,
|
| 2571 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2572 |
+
"selector_regret": 0.0,
|
| 2573 |
+
"success_selector_gap": 0.0,
|
| 2574 |
+
"success_support_gap": 0.0,
|
| 2575 |
+
"support_gap": 0.17026761174201965,
|
| 2576 |
+
"tau": 0.3741559563273496
|
| 2577 |
+
},
|
| 2578 |
+
"747260437/train1": {
|
| 2579 |
+
"base_success": 1.0,
|
| 2580 |
+
"base_utility": 2.0,
|
| 2581 |
+
"coverage": 0.0,
|
| 2582 |
+
"execute_generated": 0.0,
|
| 2583 |
+
"fallback_rate": 1.0,
|
| 2584 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2585 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2586 |
+
"outcome_ptr": 0.0,
|
| 2587 |
+
"predicted_margin": 0.365539554390633,
|
| 2588 |
+
"proposal_oracle_success": 0.0,
|
| 2589 |
+
"proposal_oracle_utility": 0.05267423391342163,
|
| 2590 |
+
"selected_candidate_index": 0.0,
|
| 2591 |
+
"selected_success": 1.0,
|
| 2592 |
+
"selected_success_gain_over_base": 0.0,
|
| 2593 |
+
"selected_utility": 2.0,
|
| 2594 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2595 |
+
"selector_regret": 0.0,
|
| 2596 |
+
"success_selector_gap": 0.0,
|
| 2597 |
+
"success_support_gap": 0.0,
|
| 2598 |
+
"support_gap": 0.22598901391029358,
|
| 2599 |
+
"tau": 0.3741559563273496
|
| 2600 |
+
},
|
| 2601 |
+
"747260437/train2": {
|
| 2602 |
+
"base_success": 1.0,
|
| 2603 |
+
"base_utility": 2.0,
|
| 2604 |
+
"coverage": 1.0,
|
| 2605 |
+
"execute_generated": 1.0,
|
| 2606 |
+
"fallback_rate": 0.0,
|
| 2607 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2608 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2609 |
+
"outcome_ptr": 0.0,
|
| 2610 |
+
"predicted_margin": 0.39450829110578517,
|
| 2611 |
+
"proposal_oracle_success": 0.0,
|
| 2612 |
+
"proposal_oracle_utility": 0.12510187923908234,
|
| 2613 |
+
"selected_candidate_index": 0.0,
|
| 2614 |
+
"selected_success": 0.0,
|
| 2615 |
+
"selected_success_gain_over_base": -1.0,
|
| 2616 |
+
"selected_utility": 0.06004788354039192,
|
| 2617 |
+
"selected_utility_gain_over_base": -1.939952116459608,
|
| 2618 |
+
"selector_regret": 0.06505399569869041,
|
| 2619 |
+
"success_selector_gap": 0.0,
|
| 2620 |
+
"success_support_gap": 0.0,
|
| 2621 |
+
"support_gap": 0.15356136858463287,
|
| 2622 |
+
"tau": 0.3741559563273496
|
| 2623 |
+
},
|
| 2624 |
+
"750448296/train0": {
|
| 2625 |
+
"base_success": 0.0,
|
| 2626 |
+
"base_utility": 0.11759314934412639,
|
| 2627 |
+
"coverage": 0.3333333333333333,
|
| 2628 |
+
"execute_generated": 0.3333333333333333,
|
| 2629 |
+
"fallback_rate": 0.6666666666666666,
|
| 2630 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2631 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2632 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2633 |
+
"predicted_margin": 0.3273610892800461,
|
| 2634 |
+
"proposal_oracle_success": 0.3333333333333333,
|
| 2635 |
+
"proposal_oracle_utility": 0.7526603279014429,
|
| 2636 |
+
"selected_candidate_index": 3.6666666666666665,
|
| 2637 |
+
"selected_success": 0.0,
|
| 2638 |
+
"selected_success_gain_over_base": 0.0,
|
| 2639 |
+
"selected_utility": 0.09317883538703124,
|
| 2640 |
+
"selected_utility_gain_over_base": -0.024414313957095146,
|
| 2641 |
+
"selector_regret": 0.6594814925144116,
|
| 2642 |
+
"success_selector_gap": 0.3333333333333333,
|
| 2643 |
+
"success_support_gap": 0.3333333333333333,
|
| 2644 |
+
"support_gap": 0.6553361676633358,
|
| 2645 |
+
"tau": 0.3741559563273496
|
| 2646 |
+
},
|
| 2647 |
+
"750448296/train1": {
|
| 2648 |
+
"base_success": 0.0,
|
| 2649 |
+
"base_utility": 0.11759314934412639,
|
| 2650 |
+
"coverage": 0.0,
|
| 2651 |
+
"execute_generated": 0.0,
|
| 2652 |
+
"fallback_rate": 1.0,
|
| 2653 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2654 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2655 |
+
"outcome_ptr": 1.0,
|
| 2656 |
+
"predicted_margin": 0.32791893647515086,
|
| 2657 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2658 |
+
"proposal_oracle_utility": 1.3705032741030057,
|
| 2659 |
+
"selected_candidate_index": 2.6666666666666665,
|
| 2660 |
+
"selected_success": 0.0,
|
| 2661 |
+
"selected_success_gain_over_base": 0.0,
|
| 2662 |
+
"selected_utility": 0.11759314934412639,
|
| 2663 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2664 |
+
"selector_regret": 1.2529101247588794,
|
| 2665 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2666 |
+
"success_support_gap": 0.0,
|
| 2667 |
+
"support_gap": 0.03749322146177292,
|
| 2668 |
+
"tau": 0.3741559563273496
|
| 2669 |
+
},
|
| 2670 |
+
"750448296/train2": {
|
| 2671 |
+
"base_success": 0.0,
|
| 2672 |
+
"base_utility": 0.11759314934412639,
|
| 2673 |
+
"coverage": 0.3333333333333333,
|
| 2674 |
+
"execute_generated": 0.3333333333333333,
|
| 2675 |
+
"fallback_rate": 0.6666666666666666,
|
| 2676 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2677 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2678 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2679 |
+
"predicted_margin": 0.3074438824092352,
|
| 2680 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2681 |
+
"proposal_oracle_utility": 1.349846323331197,
|
| 2682 |
+
"selected_candidate_index": 4.0,
|
| 2683 |
+
"selected_success": 0.0,
|
| 2684 |
+
"selected_success_gain_over_base": 0.0,
|
| 2685 |
+
"selected_utility": 0.09884339570999146,
|
| 2686 |
+
"selected_utility_gain_over_base": -0.01874975363413493,
|
| 2687 |
+
"selector_regret": 1.2510029276212056,
|
| 2688 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2689 |
+
"success_support_gap": 0.0,
|
| 2690 |
+
"support_gap": 0.05815017223358154,
|
| 2691 |
+
"tau": 0.3741559563273496
|
| 2692 |
+
},
|
| 2693 |
+
"767747424/train0": {
|
| 2694 |
+
"base_success": 0.25,
|
| 2695 |
+
"base_utility": 0.5731993420049548,
|
| 2696 |
+
"coverage": 0.0,
|
| 2697 |
+
"execute_generated": 0.0,
|
| 2698 |
+
"fallback_rate": 1.0,
|
| 2699 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2700 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2701 |
+
"outcome_ptr": 0.5,
|
| 2702 |
+
"predicted_margin": 0.30689233926456017,
|
| 2703 |
+
"proposal_oracle_success": 0.5,
|
| 2704 |
+
"proposal_oracle_utility": 1.0424291878007352,
|
| 2705 |
+
"selected_candidate_index": 3.25,
|
| 2706 |
+
"selected_success": 0.25,
|
| 2707 |
+
"selected_success_gain_over_base": 0.0,
|
| 2708 |
+
"selected_utility": 0.5731993420049548,
|
| 2709 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2710 |
+
"selector_regret": 0.4779601227492094,
|
| 2711 |
+
"success_selector_gap": 0.25,
|
| 2712 |
+
"success_support_gap": 0.0,
|
| 2713 |
+
"support_gap": 0.06562284985557199,
|
| 2714 |
+
"tau": 0.3741559563273496
|
| 2715 |
+
},
|
| 2716 |
+
"767747424/train1": {
|
| 2717 |
+
"base_success": 0.25,
|
| 2718 |
+
"base_utility": 0.5731993420049548,
|
| 2719 |
+
"coverage": 0.5,
|
| 2720 |
+
"execute_generated": 0.5,
|
| 2721 |
+
"fallback_rate": 0.5,
|
| 2722 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2723 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2724 |
+
"outcome_ptr": 0.25,
|
| 2725 |
+
"predicted_margin": 0.37594414604343307,
|
| 2726 |
+
"proposal_oracle_success": 0.25,
|
| 2727 |
+
"proposal_oracle_utility": 0.5951075805351138,
|
| 2728 |
+
"selected_candidate_index": 0.75,
|
| 2729 |
+
"selected_success": 0.25,
|
| 2730 |
+
"selected_success_gain_over_base": 0.0,
|
| 2731 |
+
"selected_utility": 0.5766910687088966,
|
| 2732 |
+
"selected_utility_gain_over_base": 0.003491726703941822,
|
| 2733 |
+
"selector_regret": 0.026683504693210125,
|
| 2734 |
+
"success_selector_gap": 0.0,
|
| 2735 |
+
"success_support_gap": 0.25,
|
| 2736 |
+
"support_gap": 0.5129444571211934,
|
| 2737 |
+
"tau": 0.3741559563273496
|
| 2738 |
+
},
|
| 2739 |
+
"767747424/train2": {
|
| 2740 |
+
"base_success": 0.25,
|
| 2741 |
+
"base_utility": 0.5731993420049548,
|
| 2742 |
+
"coverage": 0.25,
|
| 2743 |
+
"execute_generated": 0.25,
|
| 2744 |
+
"fallback_rate": 0.75,
|
| 2745 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2746 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2747 |
+
"outcome_ptr": 0.5,
|
| 2748 |
+
"predicted_margin": 0.35262652983499576,
|
| 2749 |
+
"proposal_oracle_success": 0.25,
|
| 2750 |
+
"proposal_oracle_utility": 0.6134321661666036,
|
| 2751 |
+
"selected_candidate_index": 2.5,
|
| 2752 |
+
"selected_success": 0.25,
|
| 2753 |
+
"selected_success_gain_over_base": 0.0,
|
| 2754 |
+
"selected_utility": 0.5685367146506906,
|
| 2755 |
+
"selected_utility_gain_over_base": -0.004662627354264259,
|
| 2756 |
+
"selector_regret": 0.04489545151591301,
|
| 2757 |
+
"success_selector_gap": 0.0,
|
| 2758 |
+
"success_support_gap": 0.25,
|
| 2759 |
+
"support_gap": 0.49461987148970366,
|
| 2760 |
+
"tau": 0.3741559563273496
|
| 2761 |
+
}
|
| 2762 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/metrics_by_task.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"LiftPegUpright-v1": {
|
| 3 |
+
"base_success": 0.2,
|
| 4 |
+
"base_utility": 0.9498705387115478,
|
| 5 |
+
"coverage": 0.26666666666666666,
|
| 6 |
+
"execute_generated": 0.26666666666666666,
|
| 7 |
+
"fallback_rate": 0.7333333333333333,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.4666666666666667,
|
| 11 |
+
"predicted_margin": 0.35719920667608923,
|
| 12 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 13 |
+
"proposal_oracle_utility": 1.2244940986235937,
|
| 14 |
+
"selected_candidate_index": 3.533333333333333,
|
| 15 |
+
"selected_success": 0.2,
|
| 16 |
+
"selected_success_gain_over_base": 0.0,
|
| 17 |
+
"selected_utility": 0.8626041044791539,
|
| 18 |
+
"selected_utility_gain_over_base": -0.0872664342323939,
|
| 19 |
+
"selector_regret": 0.47580571969350177,
|
| 20 |
+
"success_selector_gap": 0.3333333333333333,
|
| 21 |
+
"success_support_gap": 0.5333333333333333,
|
| 22 |
+
"support_gap": 0.7755059013764064,
|
| 23 |
+
"tau": 0.3741559563273497
|
| 24 |
+
},
|
| 25 |
+
"PickCube-v1": {
|
| 26 |
+
"base_success": 0.0,
|
| 27 |
+
"base_utility": 0.5839591026306152,
|
| 28 |
+
"coverage": 0.0,
|
| 29 |
+
"execute_generated": 0.0,
|
| 30 |
+
"fallback_rate": 1.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.23591124007650266,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.13425676027933756,
|
| 37 |
+
"selected_candidate_index": 3.3333333333333335,
|
| 38 |
+
"selected_success": 0.0,
|
| 39 |
+
"selected_success_gain_over_base": 0.0,
|
| 40 |
+
"selected_utility": 0.5839591026306152,
|
| 41 |
+
"selected_utility_gain_over_base": 0.0,
|
| 42 |
+
"selector_regret": 0.0,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.8657432397206624,
|
| 46 |
+
"tau": 0.3741559563273496
|
| 47 |
+
},
|
| 48 |
+
"PullCube-v1": {
|
| 49 |
+
"base_success": 0.36,
|
| 50 |
+
"base_utility": 0.7751704612234608,
|
| 51 |
+
"coverage": 0.36,
|
| 52 |
+
"execute_generated": 0.36,
|
| 53 |
+
"fallback_rate": 0.64,
|
| 54 |
+
"hidden_chart_oracle_success": 0.52,
|
| 55 |
+
"hidden_chart_oracle_utility": 1.1467878860235214,
|
| 56 |
+
"outcome_ptr": 0.44,
|
| 57 |
+
"predicted_margin": 0.357845382167158,
|
| 58 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 59 |
+
"proposal_oracle_utility": 0.9816135169876119,
|
| 60 |
+
"selected_candidate_index": 2.4266666666666667,
|
| 61 |
+
"selected_success": 0.36,
|
| 62 |
+
"selected_success_gain_over_base": 0.0,
|
| 63 |
+
"selected_utility": 0.7684198118560016,
|
| 64 |
+
"selected_utility_gain_over_base": -0.006750649367459119,
|
| 65 |
+
"selector_regret": 0.3684106833053132,
|
| 66 |
+
"success_selector_gap": 0.18666666666666668,
|
| 67 |
+
"success_support_gap": 0.09333333333333334,
|
| 68 |
+
"support_gap": 0.23527305972451965,
|
| 69 |
+
"tau": 0.3741559563273497
|
| 70 |
+
},
|
| 71 |
+
"PushCube-v1": {
|
| 72 |
+
"base_success": 0.16666666666666666,
|
| 73 |
+
"base_utility": 0.3924041787783305,
|
| 74 |
+
"coverage": 0.8888888888888888,
|
| 75 |
+
"execute_generated": 0.8888888888888888,
|
| 76 |
+
"fallback_rate": 0.1111111111111111,
|
| 77 |
+
"hidden_chart_oracle_success": 0.8333333333333334,
|
| 78 |
+
"hidden_chart_oracle_utility": 1.7015800600250561,
|
| 79 |
+
"outcome_ptr": 0.7777777777777778,
|
| 80 |
+
"predicted_margin": 0.4616574102239464,
|
| 81 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 82 |
+
"proposal_oracle_utility": 1.365773618221283,
|
| 83 |
+
"selected_candidate_index": 2.5555555555555554,
|
| 84 |
+
"selected_success": 0.2777777777777778,
|
| 85 |
+
"selected_success_gain_over_base": 0.1111111111111111,
|
| 86 |
+
"selected_utility": 0.5970487553212378,
|
| 87 |
+
"selected_utility_gain_over_base": 0.2046445765429073,
|
| 88 |
+
"selector_regret": 0.7687248629000452,
|
| 89 |
+
"success_selector_gap": 0.3888888888888889,
|
| 90 |
+
"success_support_gap": 0.3333333333333333,
|
| 91 |
+
"support_gap": 0.634226381778717,
|
| 92 |
+
"tau": 0.3741559563273497
|
| 93 |
+
},
|
| 94 |
+
"StackCube-v1": {
|
| 95 |
+
"base_success": 0.2727272727272727,
|
| 96 |
+
"base_utility": 0.7763947045261209,
|
| 97 |
+
"coverage": 0.12121212121212122,
|
| 98 |
+
"execute_generated": 0.12121212121212122,
|
| 99 |
+
"fallback_rate": 0.8787878787878788,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 0.5757575757575758,
|
| 103 |
+
"predicted_margin": 0.32668460753400885,
|
| 104 |
+
"proposal_oracle_success": 0.45454545454545453,
|
| 105 |
+
"proposal_oracle_utility": 1.0546941955884297,
|
| 106 |
+
"selected_candidate_index": 4.242424242424242,
|
| 107 |
+
"selected_success": 0.2727272727272727,
|
| 108 |
+
"selected_success_gain_over_base": 0.0,
|
| 109 |
+
"selected_utility": 0.7366133878628413,
|
| 110 |
+
"selected_utility_gain_over_base": -0.03978131666327968,
|
| 111 |
+
"selector_regret": 0.32240295003760944,
|
| 112 |
+
"success_selector_gap": 0.18181818181818182,
|
| 113 |
+
"success_support_gap": 0.5454545454545454,
|
| 114 |
+
"support_gap": 0.9453058044115702,
|
| 115 |
+
"tau": 0.3741559563273497
|
| 116 |
+
}
|
| 117 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/report.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Nonlinear Train-Calibrated CTT Selector
|
| 2 |
+
|
| 3 |
+
Calibration rows: `432`
|
| 4 |
+
Fit rows: `277`
|
| 5 |
+
Selection rows: `155`
|
| 6 |
+
Eval rows: `144`
|
| 7 |
+
Selected model: `rf_regressor`
|
| 8 |
+
Selected params: `{"max_depth": 3, "min_samples_leaf": 8, "n_estimators": 128, "n_jobs": 1, "random_state": 0}`
|
| 9 |
+
Tau: `0.374156`
|
| 10 |
+
Feature set: `basic`
|
| 11 |
+
Target: `positive_margin`
|
| 12 |
+
|
| 13 |
+
The model is fit on calibration-fit rows, and model/tau are selected on held-out calibration-selection rows only. Eval outcomes are used only for reporting.
|
| 14 |
+
|
| 15 |
+
| Split | Coverage | Fallback | Base success | Selected success | Proposal oracle | OutcomePTR | Success support gap | Success selector gap |
|
| 16 |
+
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 17 |
+
| fit | 0.4007 | 0.5993 | 0.2780 | 0.3538 | 0.4910 | 0.4838 | 0.2058 | 0.1986 |
|
| 18 |
+
| selection | 0.3613 | 0.6387 | 0.2774 | 0.3355 | 0.4387 | 0.5032 | 0.2774 | 0.1677 |
|
| 19 |
+
| eval | 0.3542 | 0.6458 | 0.2917 | 0.3056 | 0.4792 | 0.5069 | 0.2917 | 0.2222 |
|
| 20 |
+
|
| 21 |
+
This is a train-calibrated selector diagnostic over already measured candidates, not a new rollout.
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/split_hash.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_target_index": {
|
| 3 |
+
"content_hash": "67f7b4a692f7c7e71da24378dc71e3399c5d35afc14c494869eba6087b765c42",
|
| 4 |
+
"retrieval_index_allowed": true,
|
| 5 |
+
"split": "train",
|
| 6 |
+
"split_hash": "867a94a1c67686c082765671a7bf8d74a9d633085e1b2619c83197c60bf58372"
|
| 7 |
+
},
|
| 8 |
+
"eval_target_index": {
|
| 9 |
+
"content_hash": "0c38d73dc9bc4ab756e12006671b5d12f1a23358b281e54b3f6a9ae3cbf6e9af",
|
| 10 |
+
"retrieval_index_allowed": false,
|
| 11 |
+
"split": "test",
|
| 12 |
+
"split_hash": "84151df9e88c219b76751677558cc5bbbc19082bf358cea7330158e9e403e25f"
|
| 13 |
+
}
|
| 14 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/table.tex
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
% Auto-generated by scripts/eval_nonlinear_dominance_selector.py
|
| 2 |
+
\begin{tabular}{lrrrrrrrr}
|
| 3 |
+
\toprule
|
| 4 |
+
Rows & Coverage & Fallback & Base succ. & Selected succ. & Oracle succ. & OutcomePTR & Succ. support gap & Succ. selector gap \\
|
| 5 |
+
\midrule
|
| 6 |
+
144 & 0.3542 & 0.6458 & 0.2917 & 0.3056 & 0.4792 & 0.5069 & 0.2917 & 0.2222 \\
|
| 7 |
+
\bottomrule
|
| 8 |
+
\end{tabular}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_positive_envclip_train_to_test/train.log
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
trained nonlinear dominance selector on calibration-fit rows only
|
| 2 |
+
selected_model_type=rf_regressor
|
| 3 |
+
selected_model_params={"max_depth": 3, "min_samples_leaf": 8, "n_estimators": 128, "n_jobs": 1, "random_state": 0}
|
| 4 |
+
tau=0.374156
|
| 5 |
+
calibration_input=runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/command.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
python scripts/eval_nonlinear_dominance_selector.py --calibration-input runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json --calibration-target-index data/cil_charts_rgb_refs/train/index.json --eval-input runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json --eval-target-index data/cil_charts_rgb_refs/test/index.json --checkpoint-template runs/ctt_residual_base_context_obs_seed{seed}/model.pt --out-dir runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test --feature-set basic --target success --k 8 --bootstrap-samples 1000
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/config.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bootstrap_samples: 1000
|
| 2 |
+
calibration_input: runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
calibration_target_index: data/cil_charts_rgb_refs/train/index.json
|
| 4 |
+
checkpoint_template: runs/ctt_residual_base_context_obs_seed{seed}/model.pt
|
| 5 |
+
eval_input: runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 6 |
+
eval_target_index: data/cil_charts_rgb_refs/test/index.json
|
| 7 |
+
feature_set: basic
|
| 8 |
+
k: 8
|
| 9 |
+
model_types: hgb_classifier,hgb_regressor,rf_regressor
|
| 10 |
+
out_dir: runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test
|
| 11 |
+
seed: 0
|
| 12 |
+
selection_frac: 0.35
|
| 13 |
+
target: success
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/data_hash.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_input": "06375099001e740a377c402e34b77bf6974be3dc2a468974340ce41eb1b487f0",
|
| 3 |
+
"calibration_target_index": "67973c50072aa87a3b97533b6292b08a8b4d88a95571dc22e91b6e8fd19e0d85",
|
| 4 |
+
"eval_input": "57df43ff4802379dfd60b5209d5a04028d721256406685decededccdbec0d49c",
|
| 5 |
+
"eval_target_index": "dee1b5225485df6624747dd4c5074bcf514685b54017d05e698d2051638fbf36"
|
| 6 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/eval.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
selected model/tau on held-out calibration-selection rows; evaluated on held-out measured rollout rows
|
| 2 |
+
eval_input=runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
num_eval_rows=144
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/git_hash.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
14e81292e2004925f81e0bb4810f6f144bfd87b7
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/metrics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/metrics_by_seed.json
ADDED
|
@@ -0,0 +1,2762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"1073161778/train0": {
|
| 3 |
+
"base_success": 1.0,
|
| 4 |
+
"base_utility": 2.0,
|
| 5 |
+
"coverage": 1.0,
|
| 6 |
+
"execute_generated": 1.0,
|
| 7 |
+
"fallback_rate": 0.0,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.0,
|
| 11 |
+
"predicted_margin": 0.3909969586459246,
|
| 12 |
+
"proposal_oracle_success": 1.0,
|
| 13 |
+
"proposal_oracle_utility": 2.0,
|
| 14 |
+
"selected_candidate_index": 0.0,
|
| 15 |
+
"selected_success": 0.0,
|
| 16 |
+
"selected_success_gain_over_base": -1.0,
|
| 17 |
+
"selected_utility": 0.6859632134437561,
|
| 18 |
+
"selected_utility_gain_over_base": -1.314036786556244,
|
| 19 |
+
"selector_regret": 1.314036786556244,
|
| 20 |
+
"success_selector_gap": 1.0,
|
| 21 |
+
"success_support_gap": 0.0,
|
| 22 |
+
"support_gap": 0.0,
|
| 23 |
+
"tau": 0.38358192370540556
|
| 24 |
+
},
|
| 25 |
+
"1073161778/train1": {
|
| 26 |
+
"base_success": 1.0,
|
| 27 |
+
"base_utility": 2.0,
|
| 28 |
+
"coverage": 0.0,
|
| 29 |
+
"execute_generated": 0.0,
|
| 30 |
+
"fallback_rate": 1.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.3225177112831876,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.7071996331214905,
|
| 37 |
+
"selected_candidate_index": 1.0,
|
| 38 |
+
"selected_success": 1.0,
|
| 39 |
+
"selected_success_gain_over_base": 0.0,
|
| 40 |
+
"selected_utility": 2.0,
|
| 41 |
+
"selected_utility_gain_over_base": 0.0,
|
| 42 |
+
"selector_regret": 0.0,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.2928003668785095,
|
| 46 |
+
"tau": 0.38358192370540556
|
| 47 |
+
},
|
| 48 |
+
"1073161778/train2": {
|
| 49 |
+
"base_success": 1.0,
|
| 50 |
+
"base_utility": 2.0,
|
| 51 |
+
"coverage": 1.0,
|
| 52 |
+
"execute_generated": 1.0,
|
| 53 |
+
"fallback_rate": 0.0,
|
| 54 |
+
"hidden_chart_oracle_success": 1.0,
|
| 55 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 56 |
+
"outcome_ptr": 0.0,
|
| 57 |
+
"predicted_margin": 0.40035915866759314,
|
| 58 |
+
"proposal_oracle_success": 1.0,
|
| 59 |
+
"proposal_oracle_utility": 2.0,
|
| 60 |
+
"selected_candidate_index": 0.0,
|
| 61 |
+
"selected_success": 1.0,
|
| 62 |
+
"selected_success_gain_over_base": 0.0,
|
| 63 |
+
"selected_utility": 2.0,
|
| 64 |
+
"selected_utility_gain_over_base": 0.0,
|
| 65 |
+
"selector_regret": 0.0,
|
| 66 |
+
"success_selector_gap": 0.0,
|
| 67 |
+
"success_support_gap": 0.0,
|
| 68 |
+
"support_gap": 0.0,
|
| 69 |
+
"tau": 0.38358192370540556
|
| 70 |
+
},
|
| 71 |
+
"1113371261/train0": {
|
| 72 |
+
"base_success": 0.0,
|
| 73 |
+
"base_utility": 0.15842342376708984,
|
| 74 |
+
"coverage": 0.0,
|
| 75 |
+
"execute_generated": 0.0,
|
| 76 |
+
"fallback_rate": 1.0,
|
| 77 |
+
"hidden_chart_oracle_success": 1.0,
|
| 78 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 79 |
+
"outcome_ptr": 0.0,
|
| 80 |
+
"predicted_margin": 0.2491980513901653,
|
| 81 |
+
"proposal_oracle_success": 0.0,
|
| 82 |
+
"proposal_oracle_utility": 0.10274861752986908,
|
| 83 |
+
"selected_candidate_index": 1.0,
|
| 84 |
+
"selected_success": 0.0,
|
| 85 |
+
"selected_success_gain_over_base": 0.0,
|
| 86 |
+
"selected_utility": 0.15842342376708984,
|
| 87 |
+
"selected_utility_gain_over_base": 0.0,
|
| 88 |
+
"selector_regret": 0.0,
|
| 89 |
+
"success_selector_gap": 0.0,
|
| 90 |
+
"success_support_gap": 1.0,
|
| 91 |
+
"support_gap": 1.897251382470131,
|
| 92 |
+
"tau": 0.38358192370540556
|
| 93 |
+
},
|
| 94 |
+
"1113371261/train1": {
|
| 95 |
+
"base_success": 0.0,
|
| 96 |
+
"base_utility": 0.15842342376708984,
|
| 97 |
+
"coverage": 1.0,
|
| 98 |
+
"execute_generated": 1.0,
|
| 99 |
+
"fallback_rate": 0.0,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 1.0,
|
| 103 |
+
"predicted_margin": 0.3857945730136731,
|
| 104 |
+
"proposal_oracle_success": 0.0,
|
| 105 |
+
"proposal_oracle_utility": 0.18093222379684448,
|
| 106 |
+
"selected_candidate_index": 1.0,
|
| 107 |
+
"selected_success": 0.0,
|
| 108 |
+
"selected_success_gain_over_base": 0.0,
|
| 109 |
+
"selected_utility": 0.1746392846107483,
|
| 110 |
+
"selected_utility_gain_over_base": 0.016215860843658447,
|
| 111 |
+
"selector_regret": 0.006292939186096191,
|
| 112 |
+
"success_selector_gap": 0.0,
|
| 113 |
+
"success_support_gap": 1.0,
|
| 114 |
+
"support_gap": 1.8190677762031555,
|
| 115 |
+
"tau": 0.38358192370540556
|
| 116 |
+
},
|
| 117 |
+
"1113371261/train2": {
|
| 118 |
+
"base_success": 0.0,
|
| 119 |
+
"base_utility": 0.15842342376708984,
|
| 120 |
+
"coverage": 0.0,
|
| 121 |
+
"execute_generated": 0.0,
|
| 122 |
+
"fallback_rate": 1.0,
|
| 123 |
+
"hidden_chart_oracle_success": 1.0,
|
| 124 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 125 |
+
"outcome_ptr": 1.0,
|
| 126 |
+
"predicted_margin": 0.28595948187094367,
|
| 127 |
+
"proposal_oracle_success": 0.0,
|
| 128 |
+
"proposal_oracle_utility": 0.19527167081832886,
|
| 129 |
+
"selected_candidate_index": 7.0,
|
| 130 |
+
"selected_success": 0.0,
|
| 131 |
+
"selected_success_gain_over_base": 0.0,
|
| 132 |
+
"selected_utility": 0.15842342376708984,
|
| 133 |
+
"selected_utility_gain_over_base": 0.0,
|
| 134 |
+
"selector_regret": 0.036848247051239014,
|
| 135 |
+
"success_selector_gap": 0.0,
|
| 136 |
+
"success_support_gap": 1.0,
|
| 137 |
+
"support_gap": 1.8047283291816711,
|
| 138 |
+
"tau": 0.38358192370540556
|
| 139 |
+
},
|
| 140 |
+
"1151410346/train0": {
|
| 141 |
+
"base_success": 0.0,
|
| 142 |
+
"base_utility": 0.2260012924671173,
|
| 143 |
+
"coverage": 1.0,
|
| 144 |
+
"execute_generated": 1.0,
|
| 145 |
+
"fallback_rate": 0.0,
|
| 146 |
+
"hidden_chart_oracle_success": 1.0,
|
| 147 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 148 |
+
"outcome_ptr": 1.0,
|
| 149 |
+
"predicted_margin": 0.40609260924754975,
|
| 150 |
+
"proposal_oracle_success": 0.0,
|
| 151 |
+
"proposal_oracle_utility": 0.8663521409034729,
|
| 152 |
+
"selected_candidate_index": 1.0,
|
| 153 |
+
"selected_success": 0.0,
|
| 154 |
+
"selected_success_gain_over_base": 0.0,
|
| 155 |
+
"selected_utility": 0.1854255497455597,
|
| 156 |
+
"selected_utility_gain_over_base": -0.04057574272155762,
|
| 157 |
+
"selector_regret": 0.6809265911579132,
|
| 158 |
+
"success_selector_gap": 0.0,
|
| 159 |
+
"success_support_gap": 1.0,
|
| 160 |
+
"support_gap": 1.133647859096527,
|
| 161 |
+
"tau": 0.38358192370540556
|
| 162 |
+
},
|
| 163 |
+
"1151410346/train1": {
|
| 164 |
+
"base_success": 0.0,
|
| 165 |
+
"base_utility": 0.2260012924671173,
|
| 166 |
+
"coverage": 1.0,
|
| 167 |
+
"execute_generated": 1.0,
|
| 168 |
+
"fallback_rate": 0.0,
|
| 169 |
+
"hidden_chart_oracle_success": 1.0,
|
| 170 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 171 |
+
"outcome_ptr": 1.0,
|
| 172 |
+
"predicted_margin": 0.40035915866759314,
|
| 173 |
+
"proposal_oracle_success": 0.0,
|
| 174 |
+
"proposal_oracle_utility": 0.8138919472694397,
|
| 175 |
+
"selected_candidate_index": 3.0,
|
| 176 |
+
"selected_success": 0.0,
|
| 177 |
+
"selected_success_gain_over_base": 0.0,
|
| 178 |
+
"selected_utility": 0.8127282857894897,
|
| 179 |
+
"selected_utility_gain_over_base": 0.5867269933223724,
|
| 180 |
+
"selector_regret": 0.0011636614799499512,
|
| 181 |
+
"success_selector_gap": 0.0,
|
| 182 |
+
"success_support_gap": 1.0,
|
| 183 |
+
"support_gap": 1.1861080527305603,
|
| 184 |
+
"tau": 0.38358192370540556
|
| 185 |
+
},
|
| 186 |
+
"1151410346/train2": {
|
| 187 |
+
"base_success": 0.0,
|
| 188 |
+
"base_utility": 0.2260012924671173,
|
| 189 |
+
"coverage": 1.0,
|
| 190 |
+
"execute_generated": 1.0,
|
| 191 |
+
"fallback_rate": 0.0,
|
| 192 |
+
"hidden_chart_oracle_success": 1.0,
|
| 193 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 194 |
+
"outcome_ptr": 0.0,
|
| 195 |
+
"predicted_margin": 0.40035915866759314,
|
| 196 |
+
"proposal_oracle_success": 0.0,
|
| 197 |
+
"proposal_oracle_utility": 0.21912741661071777,
|
| 198 |
+
"selected_candidate_index": 0.0,
|
| 199 |
+
"selected_success": 0.0,
|
| 200 |
+
"selected_success_gain_over_base": 0.0,
|
| 201 |
+
"selected_utility": 0.21912741661071777,
|
| 202 |
+
"selected_utility_gain_over_base": -0.006873875856399536,
|
| 203 |
+
"selector_regret": 0.0,
|
| 204 |
+
"success_selector_gap": 0.0,
|
| 205 |
+
"success_support_gap": 1.0,
|
| 206 |
+
"support_gap": 1.7808725833892822,
|
| 207 |
+
"tau": 0.38358192370540556
|
| 208 |
+
},
|
| 209 |
+
"1261930456/train0": {
|
| 210 |
+
"base_success": 1.0,
|
| 211 |
+
"base_utility": 2.0,
|
| 212 |
+
"coverage": 1.0,
|
| 213 |
+
"execute_generated": 1.0,
|
| 214 |
+
"fallback_rate": 0.0,
|
| 215 |
+
"hidden_chart_oracle_success": 1.0,
|
| 216 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 217 |
+
"outcome_ptr": 0.0,
|
| 218 |
+
"predicted_margin": 0.4001447846515211,
|
| 219 |
+
"proposal_oracle_success": 1.0,
|
| 220 |
+
"proposal_oracle_utility": 2.0,
|
| 221 |
+
"selected_candidate_index": 3.0,
|
| 222 |
+
"selected_success": 0.0,
|
| 223 |
+
"selected_success_gain_over_base": -1.0,
|
| 224 |
+
"selected_utility": 0.06716175377368927,
|
| 225 |
+
"selected_utility_gain_over_base": -1.9328382462263107,
|
| 226 |
+
"selector_regret": 1.9328382462263107,
|
| 227 |
+
"success_selector_gap": 1.0,
|
| 228 |
+
"success_support_gap": 0.0,
|
| 229 |
+
"support_gap": 0.0,
|
| 230 |
+
"tau": 0.38358192370540556
|
| 231 |
+
},
|
| 232 |
+
"1261930456/train1": {
|
| 233 |
+
"base_success": 1.0,
|
| 234 |
+
"base_utility": 2.0,
|
| 235 |
+
"coverage": 1.0,
|
| 236 |
+
"execute_generated": 1.0,
|
| 237 |
+
"fallback_rate": 0.0,
|
| 238 |
+
"hidden_chart_oracle_success": 1.0,
|
| 239 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 240 |
+
"outcome_ptr": 0.0,
|
| 241 |
+
"predicted_margin": 0.3980862785873208,
|
| 242 |
+
"proposal_oracle_success": 1.0,
|
| 243 |
+
"proposal_oracle_utility": 2.0,
|
| 244 |
+
"selected_candidate_index": 1.0,
|
| 245 |
+
"selected_success": 0.0,
|
| 246 |
+
"selected_success_gain_over_base": -1.0,
|
| 247 |
+
"selected_utility": 0.04773080348968506,
|
| 248 |
+
"selected_utility_gain_over_base": -1.952269196510315,
|
| 249 |
+
"selector_regret": 1.952269196510315,
|
| 250 |
+
"success_selector_gap": 1.0,
|
| 251 |
+
"success_support_gap": 0.0,
|
| 252 |
+
"support_gap": 0.0,
|
| 253 |
+
"tau": 0.38358192370540556
|
| 254 |
+
},
|
| 255 |
+
"1261930456/train2": {
|
| 256 |
+
"base_success": 1.0,
|
| 257 |
+
"base_utility": 2.0,
|
| 258 |
+
"coverage": 1.0,
|
| 259 |
+
"execute_generated": 1.0,
|
| 260 |
+
"fallback_rate": 0.0,
|
| 261 |
+
"hidden_chart_oracle_success": 1.0,
|
| 262 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 263 |
+
"outcome_ptr": 0.0,
|
| 264 |
+
"predicted_margin": 0.40957871141638863,
|
| 265 |
+
"proposal_oracle_success": 1.0,
|
| 266 |
+
"proposal_oracle_utility": 2.0,
|
| 267 |
+
"selected_candidate_index": 6.0,
|
| 268 |
+
"selected_success": 1.0,
|
| 269 |
+
"selected_success_gain_over_base": 0.0,
|
| 270 |
+
"selected_utility": 2.0,
|
| 271 |
+
"selected_utility_gain_over_base": 0.0,
|
| 272 |
+
"selector_regret": 0.0,
|
| 273 |
+
"success_selector_gap": 0.0,
|
| 274 |
+
"success_support_gap": 0.0,
|
| 275 |
+
"support_gap": 0.0,
|
| 276 |
+
"tau": 0.38358192370540556
|
| 277 |
+
},
|
| 278 |
+
"1324133122/train0": {
|
| 279 |
+
"base_success": 0.0,
|
| 280 |
+
"base_utility": 0.09220491349697113,
|
| 281 |
+
"coverage": 0.0,
|
| 282 |
+
"execute_generated": 0.0,
|
| 283 |
+
"fallback_rate": 1.0,
|
| 284 |
+
"hidden_chart_oracle_success": 1.0,
|
| 285 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 286 |
+
"outcome_ptr": 0.0,
|
| 287 |
+
"predicted_margin": 0.28595948187094367,
|
| 288 |
+
"proposal_oracle_success": 0.0,
|
| 289 |
+
"proposal_oracle_utility": 0.054989203810691833,
|
| 290 |
+
"selected_candidate_index": 6.0,
|
| 291 |
+
"selected_success": 0.0,
|
| 292 |
+
"selected_success_gain_over_base": 0.0,
|
| 293 |
+
"selected_utility": 0.09220491349697113,
|
| 294 |
+
"selected_utility_gain_over_base": 0.0,
|
| 295 |
+
"selector_regret": 0.0,
|
| 296 |
+
"success_selector_gap": 0.0,
|
| 297 |
+
"success_support_gap": 1.0,
|
| 298 |
+
"support_gap": 1.9450107961893082,
|
| 299 |
+
"tau": 0.38358192370540556
|
| 300 |
+
},
|
| 301 |
+
"1324133122/train1": {
|
| 302 |
+
"base_success": 0.0,
|
| 303 |
+
"base_utility": 0.09220491349697113,
|
| 304 |
+
"coverage": 0.0,
|
| 305 |
+
"execute_generated": 0.0,
|
| 306 |
+
"fallback_rate": 1.0,
|
| 307 |
+
"hidden_chart_oracle_success": 1.0,
|
| 308 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 309 |
+
"outcome_ptr": 1.0,
|
| 310 |
+
"predicted_margin": 0.30738451498868596,
|
| 311 |
+
"proposal_oracle_success": 0.0,
|
| 312 |
+
"proposal_oracle_utility": 0.1324586570262909,
|
| 313 |
+
"selected_candidate_index": 0.0,
|
| 314 |
+
"selected_success": 0.0,
|
| 315 |
+
"selected_success_gain_over_base": 0.0,
|
| 316 |
+
"selected_utility": 0.09220491349697113,
|
| 317 |
+
"selected_utility_gain_over_base": 0.0,
|
| 318 |
+
"selector_regret": 0.04025374352931976,
|
| 319 |
+
"success_selector_gap": 0.0,
|
| 320 |
+
"success_support_gap": 1.0,
|
| 321 |
+
"support_gap": 1.867541342973709,
|
| 322 |
+
"tau": 0.38358192370540556
|
| 323 |
+
},
|
| 324 |
+
"1324133122/train2": {
|
| 325 |
+
"base_success": 0.0,
|
| 326 |
+
"base_utility": 0.09220491349697113,
|
| 327 |
+
"coverage": 0.0,
|
| 328 |
+
"execute_generated": 0.0,
|
| 329 |
+
"fallback_rate": 1.0,
|
| 330 |
+
"hidden_chart_oracle_success": 1.0,
|
| 331 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 332 |
+
"outcome_ptr": 1.0,
|
| 333 |
+
"predicted_margin": 0.2491980513901653,
|
| 334 |
+
"proposal_oracle_success": 0.0,
|
| 335 |
+
"proposal_oracle_utility": 0.19291165471076965,
|
| 336 |
+
"selected_candidate_index": 0.0,
|
| 337 |
+
"selected_success": 0.0,
|
| 338 |
+
"selected_success_gain_over_base": 0.0,
|
| 339 |
+
"selected_utility": 0.09220491349697113,
|
| 340 |
+
"selected_utility_gain_over_base": 0.0,
|
| 341 |
+
"selector_regret": 0.10070674121379852,
|
| 342 |
+
"success_selector_gap": 0.0,
|
| 343 |
+
"success_support_gap": 1.0,
|
| 344 |
+
"support_gap": 1.8070883452892303,
|
| 345 |
+
"tau": 0.38358192370540556
|
| 346 |
+
},
|
| 347 |
+
"1324642411/train0": {
|
| 348 |
+
"base_success": 0.0,
|
| 349 |
+
"base_utility": 0.10647052526473999,
|
| 350 |
+
"coverage": 0.0,
|
| 351 |
+
"execute_generated": 0.0,
|
| 352 |
+
"fallback_rate": 1.0,
|
| 353 |
+
"hidden_chart_oracle_success": 1.0,
|
| 354 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 355 |
+
"outcome_ptr": 1.0,
|
| 356 |
+
"predicted_margin": 0.3620474910733139,
|
| 357 |
+
"proposal_oracle_success": 0.0,
|
| 358 |
+
"proposal_oracle_utility": 0.17193320393562317,
|
| 359 |
+
"selected_candidate_index": 0.0,
|
| 360 |
+
"selected_success": 0.0,
|
| 361 |
+
"selected_success_gain_over_base": 0.0,
|
| 362 |
+
"selected_utility": 0.10647052526473999,
|
| 363 |
+
"selected_utility_gain_over_base": 0.0,
|
| 364 |
+
"selector_regret": 0.06546267867088318,
|
| 365 |
+
"success_selector_gap": 0.0,
|
| 366 |
+
"success_support_gap": 1.0,
|
| 367 |
+
"support_gap": 1.8280667960643768,
|
| 368 |
+
"tau": 0.38358192370540556
|
| 369 |
+
},
|
| 370 |
+
"1324642411/train1": {
|
| 371 |
+
"base_success": 0.0,
|
| 372 |
+
"base_utility": 0.10647052526473999,
|
| 373 |
+
"coverage": 0.0,
|
| 374 |
+
"execute_generated": 0.0,
|
| 375 |
+
"fallback_rate": 1.0,
|
| 376 |
+
"hidden_chart_oracle_success": 1.0,
|
| 377 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 378 |
+
"outcome_ptr": 1.0,
|
| 379 |
+
"predicted_margin": 0.32395056402489136,
|
| 380 |
+
"proposal_oracle_success": 0.0,
|
| 381 |
+
"proposal_oracle_utility": 0.1836909055709839,
|
| 382 |
+
"selected_candidate_index": 2.0,
|
| 383 |
+
"selected_success": 0.0,
|
| 384 |
+
"selected_success_gain_over_base": 0.0,
|
| 385 |
+
"selected_utility": 0.10647052526473999,
|
| 386 |
+
"selected_utility_gain_over_base": 0.0,
|
| 387 |
+
"selector_regret": 0.0772203803062439,
|
| 388 |
+
"success_selector_gap": 0.0,
|
| 389 |
+
"success_support_gap": 1.0,
|
| 390 |
+
"support_gap": 1.8163090944290161,
|
| 391 |
+
"tau": 0.38358192370540556
|
| 392 |
+
},
|
| 393 |
+
"1324642411/train2": {
|
| 394 |
+
"base_success": 0.0,
|
| 395 |
+
"base_utility": 0.10647052526473999,
|
| 396 |
+
"coverage": 0.0,
|
| 397 |
+
"execute_generated": 0.0,
|
| 398 |
+
"fallback_rate": 1.0,
|
| 399 |
+
"hidden_chart_oracle_success": 1.0,
|
| 400 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 401 |
+
"outcome_ptr": 1.0,
|
| 402 |
+
"predicted_margin": 0.3230424852763191,
|
| 403 |
+
"proposal_oracle_success": 1.0,
|
| 404 |
+
"proposal_oracle_utility": 2.0,
|
| 405 |
+
"selected_candidate_index": 4.0,
|
| 406 |
+
"selected_success": 0.0,
|
| 407 |
+
"selected_success_gain_over_base": 0.0,
|
| 408 |
+
"selected_utility": 0.10647052526473999,
|
| 409 |
+
"selected_utility_gain_over_base": 0.0,
|
| 410 |
+
"selector_regret": 1.89352947473526,
|
| 411 |
+
"success_selector_gap": 1.0,
|
| 412 |
+
"success_support_gap": 0.0,
|
| 413 |
+
"support_gap": 0.0,
|
| 414 |
+
"tau": 0.38358192370540556
|
| 415 |
+
},
|
| 416 |
+
"1375492786/train0": {
|
| 417 |
+
"base_success": 1.0,
|
| 418 |
+
"base_utility": 2.0,
|
| 419 |
+
"coverage": 0.0,
|
| 420 |
+
"execute_generated": 0.0,
|
| 421 |
+
"fallback_rate": 1.0,
|
| 422 |
+
"hidden_chart_oracle_success": 1.0,
|
| 423 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 424 |
+
"outcome_ptr": 0.0,
|
| 425 |
+
"predicted_margin": 0.16255764631774658,
|
| 426 |
+
"proposal_oracle_success": 1.0,
|
| 427 |
+
"proposal_oracle_utility": 2.0,
|
| 428 |
+
"selected_candidate_index": 0.0,
|
| 429 |
+
"selected_success": 1.0,
|
| 430 |
+
"selected_success_gain_over_base": 0.0,
|
| 431 |
+
"selected_utility": 2.0,
|
| 432 |
+
"selected_utility_gain_over_base": 0.0,
|
| 433 |
+
"selector_regret": 0.0,
|
| 434 |
+
"success_selector_gap": 0.0,
|
| 435 |
+
"success_support_gap": 0.0,
|
| 436 |
+
"support_gap": 0.0,
|
| 437 |
+
"tau": 0.38358192370540556
|
| 438 |
+
},
|
| 439 |
+
"1375492786/train1": {
|
| 440 |
+
"base_success": 1.0,
|
| 441 |
+
"base_utility": 2.0,
|
| 442 |
+
"coverage": 1.0,
|
| 443 |
+
"execute_generated": 1.0,
|
| 444 |
+
"fallback_rate": 0.0,
|
| 445 |
+
"hidden_chart_oracle_success": 1.0,
|
| 446 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 447 |
+
"outcome_ptr": 0.0,
|
| 448 |
+
"predicted_margin": 0.5817233097262897,
|
| 449 |
+
"proposal_oracle_success": 0.0,
|
| 450 |
+
"proposal_oracle_utility": 0.08251869678497314,
|
| 451 |
+
"selected_candidate_index": 3.0,
|
| 452 |
+
"selected_success": 0.0,
|
| 453 |
+
"selected_success_gain_over_base": -1.0,
|
| 454 |
+
"selected_utility": 1.9868215517249155e-08,
|
| 455 |
+
"selected_utility_gain_over_base": -1.9999999801317845,
|
| 456 |
+
"selector_regret": 0.08251867691675763,
|
| 457 |
+
"success_selector_gap": 0.0,
|
| 458 |
+
"success_support_gap": 1.0,
|
| 459 |
+
"support_gap": 1.9174813032150269,
|
| 460 |
+
"tau": 0.38358192370540556
|
| 461 |
+
},
|
| 462 |
+
"1375492786/train2": {
|
| 463 |
+
"base_success": 1.0,
|
| 464 |
+
"base_utility": 2.0,
|
| 465 |
+
"coverage": 0.0,
|
| 466 |
+
"execute_generated": 0.0,
|
| 467 |
+
"fallback_rate": 1.0,
|
| 468 |
+
"hidden_chart_oracle_success": 1.0,
|
| 469 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 470 |
+
"outcome_ptr": 0.0,
|
| 471 |
+
"predicted_margin": 0.1270820819653565,
|
| 472 |
+
"proposal_oracle_success": 1.0,
|
| 473 |
+
"proposal_oracle_utility": 2.0,
|
| 474 |
+
"selected_candidate_index": 7.0,
|
| 475 |
+
"selected_success": 1.0,
|
| 476 |
+
"selected_success_gain_over_base": 0.0,
|
| 477 |
+
"selected_utility": 2.0,
|
| 478 |
+
"selected_utility_gain_over_base": 0.0,
|
| 479 |
+
"selector_regret": 0.0,
|
| 480 |
+
"success_selector_gap": 0.0,
|
| 481 |
+
"success_support_gap": 0.0,
|
| 482 |
+
"support_gap": 0.0,
|
| 483 |
+
"tau": 0.38358192370540556
|
| 484 |
+
},
|
| 485 |
+
"141984615/train0": {
|
| 486 |
+
"base_success": 0.0,
|
| 487 |
+
"base_utility": 0.10283424705266953,
|
| 488 |
+
"coverage": 0.0,
|
| 489 |
+
"execute_generated": 0.0,
|
| 490 |
+
"fallback_rate": 1.0,
|
| 491 |
+
"hidden_chart_oracle_success": 0.0,
|
| 492 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 493 |
+
"outcome_ptr": 0.0,
|
| 494 |
+
"predicted_margin": 0.23320400581891038,
|
| 495 |
+
"proposal_oracle_success": 0.0,
|
| 496 |
+
"proposal_oracle_utility": 0.007291515823453665,
|
| 497 |
+
"selected_candidate_index": 7.0,
|
| 498 |
+
"selected_success": 0.0,
|
| 499 |
+
"selected_success_gain_over_base": 0.0,
|
| 500 |
+
"selected_utility": 0.10283424705266953,
|
| 501 |
+
"selected_utility_gain_over_base": 0.0,
|
| 502 |
+
"selector_regret": 0.0,
|
| 503 |
+
"success_selector_gap": 0.0,
|
| 504 |
+
"success_support_gap": 0.0,
|
| 505 |
+
"support_gap": 0.27848575497046113,
|
| 506 |
+
"tau": 0.38358192370540556
|
| 507 |
+
},
|
| 508 |
+
"141984615/train1": {
|
| 509 |
+
"base_success": 0.0,
|
| 510 |
+
"base_utility": 0.10283424705266953,
|
| 511 |
+
"coverage": 0.0,
|
| 512 |
+
"execute_generated": 0.0,
|
| 513 |
+
"fallback_rate": 1.0,
|
| 514 |
+
"hidden_chart_oracle_success": 0.0,
|
| 515 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 516 |
+
"outcome_ptr": 0.0,
|
| 517 |
+
"predicted_margin": 0.32395056402489136,
|
| 518 |
+
"proposal_oracle_success": 0.0,
|
| 519 |
+
"proposal_oracle_utility": 0.037011127918958664,
|
| 520 |
+
"selected_candidate_index": 1.0,
|
| 521 |
+
"selected_success": 0.0,
|
| 522 |
+
"selected_success_gain_over_base": 0.0,
|
| 523 |
+
"selected_utility": 0.10283424705266953,
|
| 524 |
+
"selected_utility_gain_over_base": 0.0,
|
| 525 |
+
"selector_regret": 0.0,
|
| 526 |
+
"success_selector_gap": 0.0,
|
| 527 |
+
"success_support_gap": 0.0,
|
| 528 |
+
"support_gap": 0.24876614287495613,
|
| 529 |
+
"tau": 0.38358192370540556
|
| 530 |
+
},
|
| 531 |
+
"141984615/train2": {
|
| 532 |
+
"base_success": 0.0,
|
| 533 |
+
"base_utility": 0.10283424705266953,
|
| 534 |
+
"coverage": 1.0,
|
| 535 |
+
"execute_generated": 1.0,
|
| 536 |
+
"fallback_rate": 0.0,
|
| 537 |
+
"hidden_chart_oracle_success": 0.0,
|
| 538 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 539 |
+
"outcome_ptr": 0.0,
|
| 540 |
+
"predicted_margin": 0.5202342636576475,
|
| 541 |
+
"proposal_oracle_success": 0.0,
|
| 542 |
+
"proposal_oracle_utility": 0.030228236690163612,
|
| 543 |
+
"selected_candidate_index": 7.0,
|
| 544 |
+
"selected_success": 0.0,
|
| 545 |
+
"selected_success_gain_over_base": 0.0,
|
| 546 |
+
"selected_utility": 0.030228236690163612,
|
| 547 |
+
"selected_utility_gain_over_base": -0.07260601036250591,
|
| 548 |
+
"selector_regret": 0.0,
|
| 549 |
+
"success_selector_gap": 0.0,
|
| 550 |
+
"success_support_gap": 0.0,
|
| 551 |
+
"support_gap": 0.2555490341037512,
|
| 552 |
+
"tau": 0.38358192370540556
|
| 553 |
+
},
|
| 554 |
+
"1461069713/train0": {
|
| 555 |
+
"base_success": 0.0,
|
| 556 |
+
"base_utility": 0.0939030647277832,
|
| 557 |
+
"coverage": 0.0,
|
| 558 |
+
"execute_generated": 0.0,
|
| 559 |
+
"fallback_rate": 1.0,
|
| 560 |
+
"hidden_chart_oracle_success": 0.0,
|
| 561 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 562 |
+
"outcome_ptr": 0.0,
|
| 563 |
+
"predicted_margin": 0.14848772192116344,
|
| 564 |
+
"proposal_oracle_success": 0.0,
|
| 565 |
+
"proposal_oracle_utility": 0.06019836664199829,
|
| 566 |
+
"selected_candidate_index": 0.0,
|
| 567 |
+
"selected_success": 0.0,
|
| 568 |
+
"selected_success_gain_over_base": 0.0,
|
| 569 |
+
"selected_utility": 0.0939030647277832,
|
| 570 |
+
"selected_utility_gain_over_base": 0.0,
|
| 571 |
+
"selector_regret": 0.0,
|
| 572 |
+
"success_selector_gap": 0.0,
|
| 573 |
+
"success_support_gap": 0.0,
|
| 574 |
+
"support_gap": 0.0991440862417221,
|
| 575 |
+
"tau": 0.38358192370540556
|
| 576 |
+
},
|
| 577 |
+
"1461069713/train1": {
|
| 578 |
+
"base_success": 0.0,
|
| 579 |
+
"base_utility": 0.0939030647277832,
|
| 580 |
+
"coverage": 0.0,
|
| 581 |
+
"execute_generated": 0.0,
|
| 582 |
+
"fallback_rate": 1.0,
|
| 583 |
+
"hidden_chart_oracle_success": 0.0,
|
| 584 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 585 |
+
"outcome_ptr": 0.0,
|
| 586 |
+
"predicted_margin": 0.3206164719378812,
|
| 587 |
+
"proposal_oracle_success": 0.0,
|
| 588 |
+
"proposal_oracle_utility": 0.016585012897849083,
|
| 589 |
+
"selected_candidate_index": 0.0,
|
| 590 |
+
"selected_success": 0.0,
|
| 591 |
+
"selected_success_gain_over_base": 0.0,
|
| 592 |
+
"selected_utility": 0.0939030647277832,
|
| 593 |
+
"selected_utility_gain_over_base": 0.0,
|
| 594 |
+
"selector_regret": 0.0,
|
| 595 |
+
"success_selector_gap": 0.0,
|
| 596 |
+
"success_support_gap": 0.0,
|
| 597 |
+
"support_gap": 0.14275743998587132,
|
| 598 |
+
"tau": 0.38358192370540556
|
| 599 |
+
},
|
| 600 |
+
"1461069713/train2": {
|
| 601 |
+
"base_success": 0.0,
|
| 602 |
+
"base_utility": 0.0939030647277832,
|
| 603 |
+
"coverage": 0.0,
|
| 604 |
+
"execute_generated": 0.0,
|
| 605 |
+
"fallback_rate": 1.0,
|
| 606 |
+
"hidden_chart_oracle_success": 0.0,
|
| 607 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 608 |
+
"outcome_ptr": 1.0,
|
| 609 |
+
"predicted_margin": 0.32395056402489136,
|
| 610 |
+
"proposal_oracle_success": 0.0,
|
| 611 |
+
"proposal_oracle_utility": 0.09970339387655258,
|
| 612 |
+
"selected_candidate_index": 3.0,
|
| 613 |
+
"selected_success": 0.0,
|
| 614 |
+
"selected_success_gain_over_base": 0.0,
|
| 615 |
+
"selected_utility": 0.0939030647277832,
|
| 616 |
+
"selected_utility_gain_over_base": 0.0,
|
| 617 |
+
"selector_regret": 0.005800329148769379,
|
| 618 |
+
"success_selector_gap": 0.0,
|
| 619 |
+
"success_support_gap": 0.0,
|
| 620 |
+
"support_gap": 0.059639059007167816,
|
| 621 |
+
"tau": 0.38358192370540556
|
| 622 |
+
},
|
| 623 |
+
"1480856810/train0": {
|
| 624 |
+
"base_success": 0.0,
|
| 625 |
+
"base_utility": 0.08703407645225525,
|
| 626 |
+
"coverage": 1.0,
|
| 627 |
+
"execute_generated": 1.0,
|
| 628 |
+
"fallback_rate": 0.0,
|
| 629 |
+
"hidden_chart_oracle_success": 0.0,
|
| 630 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 631 |
+
"outcome_ptr": 1.0,
|
| 632 |
+
"predicted_margin": 0.43218295351476793,
|
| 633 |
+
"proposal_oracle_success": 1.0,
|
| 634 |
+
"proposal_oracle_utility": 2.0,
|
| 635 |
+
"selected_candidate_index": 1.0,
|
| 636 |
+
"selected_success": 1.0,
|
| 637 |
+
"selected_success_gain_over_base": 1.0,
|
| 638 |
+
"selected_utility": 2.0,
|
| 639 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 640 |
+
"selector_regret": 0.0,
|
| 641 |
+
"success_selector_gap": 0.0,
|
| 642 |
+
"success_support_gap": 0.0,
|
| 643 |
+
"support_gap": 0.0,
|
| 644 |
+
"tau": 0.38358192370540556
|
| 645 |
+
},
|
| 646 |
+
"1480856810/train1": {
|
| 647 |
+
"base_success": 0.0,
|
| 648 |
+
"base_utility": 0.08703407645225525,
|
| 649 |
+
"coverage": 1.0,
|
| 650 |
+
"execute_generated": 1.0,
|
| 651 |
+
"fallback_rate": 0.0,
|
| 652 |
+
"hidden_chart_oracle_success": 0.0,
|
| 653 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 654 |
+
"outcome_ptr": 1.0,
|
| 655 |
+
"predicted_margin": 0.3956988400244218,
|
| 656 |
+
"proposal_oracle_success": 1.0,
|
| 657 |
+
"proposal_oracle_utility": 2.0,
|
| 658 |
+
"selected_candidate_index": 0.0,
|
| 659 |
+
"selected_success": 0.0,
|
| 660 |
+
"selected_success_gain_over_base": 0.0,
|
| 661 |
+
"selected_utility": 0.20867714285850525,
|
| 662 |
+
"selected_utility_gain_over_base": 0.12164306640625,
|
| 663 |
+
"selector_regret": 1.7913228571414948,
|
| 664 |
+
"success_selector_gap": 1.0,
|
| 665 |
+
"success_support_gap": 0.0,
|
| 666 |
+
"support_gap": 0.0,
|
| 667 |
+
"tau": 0.38358192370540556
|
| 668 |
+
},
|
| 669 |
+
"1480856810/train2": {
|
| 670 |
+
"base_success": 0.0,
|
| 671 |
+
"base_utility": 0.08703407645225525,
|
| 672 |
+
"coverage": 1.0,
|
| 673 |
+
"execute_generated": 1.0,
|
| 674 |
+
"fallback_rate": 0.0,
|
| 675 |
+
"hidden_chart_oracle_success": 0.0,
|
| 676 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 677 |
+
"outcome_ptr": 1.0,
|
| 678 |
+
"predicted_margin": 0.43218295351476793,
|
| 679 |
+
"proposal_oracle_success": 1.0,
|
| 680 |
+
"proposal_oracle_utility": 2.0,
|
| 681 |
+
"selected_candidate_index": 0.0,
|
| 682 |
+
"selected_success": 1.0,
|
| 683 |
+
"selected_success_gain_over_base": 1.0,
|
| 684 |
+
"selected_utility": 2.0,
|
| 685 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 686 |
+
"selector_regret": 0.0,
|
| 687 |
+
"success_selector_gap": 0.0,
|
| 688 |
+
"success_support_gap": 0.0,
|
| 689 |
+
"support_gap": 0.0,
|
| 690 |
+
"tau": 0.38358192370540556
|
| 691 |
+
},
|
| 692 |
+
"1509980664/train0": {
|
| 693 |
+
"base_success": 0.0,
|
| 694 |
+
"base_utility": 0.8334100246429443,
|
| 695 |
+
"coverage": 1.0,
|
| 696 |
+
"execute_generated": 1.0,
|
| 697 |
+
"fallback_rate": 0.0,
|
| 698 |
+
"hidden_chart_oracle_success": 1.0,
|
| 699 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 700 |
+
"outcome_ptr": 1.0,
|
| 701 |
+
"predicted_margin": 0.4266296552350286,
|
| 702 |
+
"proposal_oracle_success": 1.0,
|
| 703 |
+
"proposal_oracle_utility": 2.0,
|
| 704 |
+
"selected_candidate_index": 7.0,
|
| 705 |
+
"selected_success": 1.0,
|
| 706 |
+
"selected_success_gain_over_base": 1.0,
|
| 707 |
+
"selected_utility": 2.0,
|
| 708 |
+
"selected_utility_gain_over_base": 1.1665899753570557,
|
| 709 |
+
"selector_regret": 0.0,
|
| 710 |
+
"success_selector_gap": 0.0,
|
| 711 |
+
"success_support_gap": 0.0,
|
| 712 |
+
"support_gap": 0.0,
|
| 713 |
+
"tau": 0.38358192370540556
|
| 714 |
+
},
|
| 715 |
+
"1509980664/train1": {
|
| 716 |
+
"base_success": 0.0,
|
| 717 |
+
"base_utility": 0.8334100246429443,
|
| 718 |
+
"coverage": 0.0,
|
| 719 |
+
"execute_generated": 0.0,
|
| 720 |
+
"fallback_rate": 1.0,
|
| 721 |
+
"hidden_chart_oracle_success": 1.0,
|
| 722 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 723 |
+
"outcome_ptr": 1.0,
|
| 724 |
+
"predicted_margin": 0.36178751330826875,
|
| 725 |
+
"proposal_oracle_success": 1.0,
|
| 726 |
+
"proposal_oracle_utility": 2.0,
|
| 727 |
+
"selected_candidate_index": 0.0,
|
| 728 |
+
"selected_success": 0.0,
|
| 729 |
+
"selected_success_gain_over_base": 0.0,
|
| 730 |
+
"selected_utility": 0.8334100246429443,
|
| 731 |
+
"selected_utility_gain_over_base": 0.0,
|
| 732 |
+
"selector_regret": 1.1665899753570557,
|
| 733 |
+
"success_selector_gap": 1.0,
|
| 734 |
+
"success_support_gap": 0.0,
|
| 735 |
+
"support_gap": 0.0,
|
| 736 |
+
"tau": 0.38358192370540556
|
| 737 |
+
},
|
| 738 |
+
"1509980664/train2": {
|
| 739 |
+
"base_success": 0.0,
|
| 740 |
+
"base_utility": 0.8334100246429443,
|
| 741 |
+
"coverage": 0.0,
|
| 742 |
+
"execute_generated": 0.0,
|
| 743 |
+
"fallback_rate": 1.0,
|
| 744 |
+
"hidden_chart_oracle_success": 1.0,
|
| 745 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 746 |
+
"outcome_ptr": 0.0,
|
| 747 |
+
"predicted_margin": 0.32395056402489136,
|
| 748 |
+
"proposal_oracle_success": 0.0,
|
| 749 |
+
"proposal_oracle_utility": 0.8162217140197754,
|
| 750 |
+
"selected_candidate_index": 0.0,
|
| 751 |
+
"selected_success": 0.0,
|
| 752 |
+
"selected_success_gain_over_base": 0.0,
|
| 753 |
+
"selected_utility": 0.8334100246429443,
|
| 754 |
+
"selected_utility_gain_over_base": 0.0,
|
| 755 |
+
"selector_regret": 0.0,
|
| 756 |
+
"success_selector_gap": 0.0,
|
| 757 |
+
"success_support_gap": 1.0,
|
| 758 |
+
"support_gap": 1.1837782859802246,
|
| 759 |
+
"tau": 0.38358192370540556
|
| 760 |
+
},
|
| 761 |
+
"1522272686/train0": {
|
| 762 |
+
"base_success": 0.0,
|
| 763 |
+
"base_utility": 0.5839591026306152,
|
| 764 |
+
"coverage": 1.0,
|
| 765 |
+
"execute_generated": 1.0,
|
| 766 |
+
"fallback_rate": 0.0,
|
| 767 |
+
"hidden_chart_oracle_success": 1.0,
|
| 768 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 769 |
+
"outcome_ptr": 0.0,
|
| 770 |
+
"predicted_margin": 0.7332244720170006,
|
| 771 |
+
"proposal_oracle_success": 0.0,
|
| 772 |
+
"proposal_oracle_utility": 0.18325337767601013,
|
| 773 |
+
"selected_candidate_index": 6.0,
|
| 774 |
+
"selected_success": 0.0,
|
| 775 |
+
"selected_success_gain_over_base": 0.0,
|
| 776 |
+
"selected_utility": 0.14637050032615662,
|
| 777 |
+
"selected_utility_gain_over_base": -0.4375886023044586,
|
| 778 |
+
"selector_regret": 0.036882877349853516,
|
| 779 |
+
"success_selector_gap": 0.0,
|
| 780 |
+
"success_support_gap": 1.0,
|
| 781 |
+
"support_gap": 1.8167466223239899,
|
| 782 |
+
"tau": 0.38358192370540556
|
| 783 |
+
},
|
| 784 |
+
"1522272686/train1": {
|
| 785 |
+
"base_success": 0.0,
|
| 786 |
+
"base_utility": 0.5839591026306152,
|
| 787 |
+
"coverage": 1.0,
|
| 788 |
+
"execute_generated": 1.0,
|
| 789 |
+
"fallback_rate": 0.0,
|
| 790 |
+
"hidden_chart_oracle_success": 1.0,
|
| 791 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 792 |
+
"outcome_ptr": 0.0,
|
| 793 |
+
"predicted_margin": 0.4395953574467041,
|
| 794 |
+
"proposal_oracle_success": 0.0,
|
| 795 |
+
"proposal_oracle_utility": 0.07014383375644684,
|
| 796 |
+
"selected_candidate_index": 3.0,
|
| 797 |
+
"selected_success": 0.0,
|
| 798 |
+
"selected_success_gain_over_base": 0.0,
|
| 799 |
+
"selected_utility": 0.059747494757175446,
|
| 800 |
+
"selected_utility_gain_over_base": -0.5242116078734398,
|
| 801 |
+
"selector_regret": 0.010396338999271393,
|
| 802 |
+
"success_selector_gap": 0.0,
|
| 803 |
+
"success_support_gap": 1.0,
|
| 804 |
+
"support_gap": 1.9298561662435532,
|
| 805 |
+
"tau": 0.38358192370540556
|
| 806 |
+
},
|
| 807 |
+
"1522272686/train2": {
|
| 808 |
+
"base_success": 0.0,
|
| 809 |
+
"base_utility": 0.5839591026306152,
|
| 810 |
+
"coverage": 1.0,
|
| 811 |
+
"execute_generated": 1.0,
|
| 812 |
+
"fallback_rate": 0.0,
|
| 813 |
+
"hidden_chart_oracle_success": 1.0,
|
| 814 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 815 |
+
"outcome_ptr": 0.0,
|
| 816 |
+
"predicted_margin": 0.4163633817877295,
|
| 817 |
+
"proposal_oracle_success": 0.0,
|
| 818 |
+
"proposal_oracle_utility": 0.14937306940555573,
|
| 819 |
+
"selected_candidate_index": 2.0,
|
| 820 |
+
"selected_success": 0.0,
|
| 821 |
+
"selected_success_gain_over_base": 0.0,
|
| 822 |
+
"selected_utility": 0.09545384347438812,
|
| 823 |
+
"selected_utility_gain_over_base": -0.4885052591562271,
|
| 824 |
+
"selector_regret": 0.0539192259311676,
|
| 825 |
+
"success_selector_gap": 0.0,
|
| 826 |
+
"success_support_gap": 1.0,
|
| 827 |
+
"support_gap": 1.8506269305944443,
|
| 828 |
+
"tau": 0.38358192370540556
|
| 829 |
+
},
|
| 830 |
+
"1549324805/train0": {
|
| 831 |
+
"base_success": 0.0,
|
| 832 |
+
"base_utility": 0.10451483726501465,
|
| 833 |
+
"coverage": 0.0,
|
| 834 |
+
"execute_generated": 0.0,
|
| 835 |
+
"fallback_rate": 1.0,
|
| 836 |
+
"hidden_chart_oracle_success": 0.0,
|
| 837 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 838 |
+
"outcome_ptr": 0.0,
|
| 839 |
+
"predicted_margin": 0.3612605931849642,
|
| 840 |
+
"proposal_oracle_success": 0.0,
|
| 841 |
+
"proposal_oracle_utility": 0.0415392704308033,
|
| 842 |
+
"selected_candidate_index": 0.0,
|
| 843 |
+
"selected_success": 0.0,
|
| 844 |
+
"selected_success_gain_over_base": 0.0,
|
| 845 |
+
"selected_utility": 0.10451483726501465,
|
| 846 |
+
"selected_utility_gain_over_base": 0.0,
|
| 847 |
+
"selector_regret": 0.0,
|
| 848 |
+
"success_selector_gap": 0.0,
|
| 849 |
+
"success_support_gap": 0.0,
|
| 850 |
+
"support_gap": 0.255916815251112,
|
| 851 |
+
"tau": 0.38358192370540556
|
| 852 |
+
},
|
| 853 |
+
"1549324805/train1": {
|
| 854 |
+
"base_success": 0.0,
|
| 855 |
+
"base_utility": 0.10451483726501465,
|
| 856 |
+
"coverage": 0.0,
|
| 857 |
+
"execute_generated": 0.0,
|
| 858 |
+
"fallback_rate": 1.0,
|
| 859 |
+
"hidden_chart_oracle_success": 0.0,
|
| 860 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 861 |
+
"outcome_ptr": 1.0,
|
| 862 |
+
"predicted_margin": 0.3570522478872308,
|
| 863 |
+
"proposal_oracle_success": 0.0,
|
| 864 |
+
"proposal_oracle_utility": 0.19892151653766632,
|
| 865 |
+
"selected_candidate_index": 0.0,
|
| 866 |
+
"selected_success": 0.0,
|
| 867 |
+
"selected_success_gain_over_base": 0.0,
|
| 868 |
+
"selected_utility": 0.10451483726501465,
|
| 869 |
+
"selected_utility_gain_over_base": 0.0,
|
| 870 |
+
"selector_regret": 0.09440667927265167,
|
| 871 |
+
"success_selector_gap": 0.0,
|
| 872 |
+
"success_support_gap": 0.0,
|
| 873 |
+
"support_gap": 0.09853456914424896,
|
| 874 |
+
"tau": 0.38358192370540556
|
| 875 |
+
},
|
| 876 |
+
"1549324805/train2": {
|
| 877 |
+
"base_success": 0.0,
|
| 878 |
+
"base_utility": 0.10451483726501465,
|
| 879 |
+
"coverage": 1.0,
|
| 880 |
+
"execute_generated": 1.0,
|
| 881 |
+
"fallback_rate": 0.0,
|
| 882 |
+
"hidden_chart_oracle_success": 0.0,
|
| 883 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 884 |
+
"outcome_ptr": 0.0,
|
| 885 |
+
"predicted_margin": 0.43218295351476793,
|
| 886 |
+
"proposal_oracle_success": 0.0,
|
| 887 |
+
"proposal_oracle_utility": 0.09092829376459122,
|
| 888 |
+
"selected_candidate_index": 5.0,
|
| 889 |
+
"selected_success": 0.0,
|
| 890 |
+
"selected_success_gain_over_base": 0.0,
|
| 891 |
+
"selected_utility": 0.03745478391647339,
|
| 892 |
+
"selected_utility_gain_over_base": -0.06706005334854126,
|
| 893 |
+
"selector_regret": 0.05347350984811783,
|
| 894 |
+
"success_selector_gap": 0.0,
|
| 895 |
+
"success_support_gap": 0.0,
|
| 896 |
+
"support_gap": 0.20652779191732407,
|
| 897 |
+
"tau": 0.38358192370540556
|
| 898 |
+
},
|
| 899 |
+
"1578990937/train0": {
|
| 900 |
+
"base_success": 0.0,
|
| 901 |
+
"base_utility": 0.82413649559021,
|
| 902 |
+
"coverage": 1.0,
|
| 903 |
+
"execute_generated": 1.0,
|
| 904 |
+
"fallback_rate": 0.0,
|
| 905 |
+
"hidden_chart_oracle_success": 1.0,
|
| 906 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 907 |
+
"outcome_ptr": 1.0,
|
| 908 |
+
"predicted_margin": 0.40609260924754975,
|
| 909 |
+
"proposal_oracle_success": 1.0,
|
| 910 |
+
"proposal_oracle_utility": 2.0,
|
| 911 |
+
"selected_candidate_index": 0.0,
|
| 912 |
+
"selected_success": 0.0,
|
| 913 |
+
"selected_success_gain_over_base": 0.0,
|
| 914 |
+
"selected_utility": 0.15893937647342682,
|
| 915 |
+
"selected_utility_gain_over_base": -0.6651971191167831,
|
| 916 |
+
"selector_regret": 1.8410606235265732,
|
| 917 |
+
"success_selector_gap": 1.0,
|
| 918 |
+
"success_support_gap": 0.0,
|
| 919 |
+
"support_gap": 0.0,
|
| 920 |
+
"tau": 0.38358192370540556
|
| 921 |
+
},
|
| 922 |
+
"1578990937/train1": {
|
| 923 |
+
"base_success": 0.0,
|
| 924 |
+
"base_utility": 0.82413649559021,
|
| 925 |
+
"coverage": 1.0,
|
| 926 |
+
"execute_generated": 1.0,
|
| 927 |
+
"fallback_rate": 0.0,
|
| 928 |
+
"hidden_chart_oracle_success": 1.0,
|
| 929 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 930 |
+
"outcome_ptr": 1.0,
|
| 931 |
+
"predicted_margin": 0.40035915866759314,
|
| 932 |
+
"proposal_oracle_success": 1.0,
|
| 933 |
+
"proposal_oracle_utility": 2.0,
|
| 934 |
+
"selected_candidate_index": 1.0,
|
| 935 |
+
"selected_success": 1.0,
|
| 936 |
+
"selected_success_gain_over_base": 1.0,
|
| 937 |
+
"selected_utility": 2.0,
|
| 938 |
+
"selected_utility_gain_over_base": 1.17586350440979,
|
| 939 |
+
"selector_regret": 0.0,
|
| 940 |
+
"success_selector_gap": 0.0,
|
| 941 |
+
"success_support_gap": 0.0,
|
| 942 |
+
"support_gap": 0.0,
|
| 943 |
+
"tau": 0.38358192370540556
|
| 944 |
+
},
|
| 945 |
+
"1578990937/train2": {
|
| 946 |
+
"base_success": 0.0,
|
| 947 |
+
"base_utility": 0.82413649559021,
|
| 948 |
+
"coverage": 1.0,
|
| 949 |
+
"execute_generated": 1.0,
|
| 950 |
+
"fallback_rate": 0.0,
|
| 951 |
+
"hidden_chart_oracle_success": 1.0,
|
| 952 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 953 |
+
"outcome_ptr": 1.0,
|
| 954 |
+
"predicted_margin": 0.3975936184766528,
|
| 955 |
+
"proposal_oracle_success": 1.0,
|
| 956 |
+
"proposal_oracle_utility": 2.0,
|
| 957 |
+
"selected_candidate_index": 0.0,
|
| 958 |
+
"selected_success": 0.0,
|
| 959 |
+
"selected_success_gain_over_base": 0.0,
|
| 960 |
+
"selected_utility": 0.13359522819519043,
|
| 961 |
+
"selected_utility_gain_over_base": -0.6905412673950195,
|
| 962 |
+
"selector_regret": 1.8664047718048096,
|
| 963 |
+
"success_selector_gap": 1.0,
|
| 964 |
+
"success_support_gap": 0.0,
|
| 965 |
+
"support_gap": 0.0,
|
| 966 |
+
"tau": 0.38358192370540556
|
| 967 |
+
},
|
| 968 |
+
"1747178030/train0": {
|
| 969 |
+
"base_success": 1.0,
|
| 970 |
+
"base_utility": 2.0,
|
| 971 |
+
"coverage": 1.0,
|
| 972 |
+
"execute_generated": 1.0,
|
| 973 |
+
"fallback_rate": 0.0,
|
| 974 |
+
"hidden_chart_oracle_success": 1.0,
|
| 975 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 976 |
+
"outcome_ptr": 0.0,
|
| 977 |
+
"predicted_margin": 0.6386407145727108,
|
| 978 |
+
"proposal_oracle_success": 1.0,
|
| 979 |
+
"proposal_oracle_utility": 2.0,
|
| 980 |
+
"selected_candidate_index": 1.0,
|
| 981 |
+
"selected_success": 1.0,
|
| 982 |
+
"selected_success_gain_over_base": 0.0,
|
| 983 |
+
"selected_utility": 2.0,
|
| 984 |
+
"selected_utility_gain_over_base": 0.0,
|
| 985 |
+
"selector_regret": 0.0,
|
| 986 |
+
"success_selector_gap": 0.0,
|
| 987 |
+
"success_support_gap": 0.0,
|
| 988 |
+
"support_gap": 0.0,
|
| 989 |
+
"tau": 0.38358192370540556
|
| 990 |
+
},
|
| 991 |
+
"1747178030/train1": {
|
| 992 |
+
"base_success": 1.0,
|
| 993 |
+
"base_utility": 2.0,
|
| 994 |
+
"coverage": 1.0,
|
| 995 |
+
"execute_generated": 1.0,
|
| 996 |
+
"fallback_rate": 0.0,
|
| 997 |
+
"hidden_chart_oracle_success": 1.0,
|
| 998 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 999 |
+
"outcome_ptr": 0.0,
|
| 1000 |
+
"predicted_margin": 0.4043307605631733,
|
| 1001 |
+
"proposal_oracle_success": 1.0,
|
| 1002 |
+
"proposal_oracle_utility": 2.0,
|
| 1003 |
+
"selected_candidate_index": 6.0,
|
| 1004 |
+
"selected_success": 1.0,
|
| 1005 |
+
"selected_success_gain_over_base": 0.0,
|
| 1006 |
+
"selected_utility": 2.0,
|
| 1007 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1008 |
+
"selector_regret": 0.0,
|
| 1009 |
+
"success_selector_gap": 0.0,
|
| 1010 |
+
"success_support_gap": 0.0,
|
| 1011 |
+
"support_gap": 0.0,
|
| 1012 |
+
"tau": 0.38358192370540556
|
| 1013 |
+
},
|
| 1014 |
+
"1747178030/train2": {
|
| 1015 |
+
"base_success": 1.0,
|
| 1016 |
+
"base_utility": 2.0,
|
| 1017 |
+
"coverage": 1.0,
|
| 1018 |
+
"execute_generated": 1.0,
|
| 1019 |
+
"fallback_rate": 0.0,
|
| 1020 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1021 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1022 |
+
"outcome_ptr": 0.0,
|
| 1023 |
+
"predicted_margin": 0.47855082301126006,
|
| 1024 |
+
"proposal_oracle_success": 1.0,
|
| 1025 |
+
"proposal_oracle_utility": 2.0,
|
| 1026 |
+
"selected_candidate_index": 5.0,
|
| 1027 |
+
"selected_success": 1.0,
|
| 1028 |
+
"selected_success_gain_over_base": 0.0,
|
| 1029 |
+
"selected_utility": 2.0,
|
| 1030 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1031 |
+
"selector_regret": 0.0,
|
| 1032 |
+
"success_selector_gap": 0.0,
|
| 1033 |
+
"success_support_gap": 0.0,
|
| 1034 |
+
"support_gap": 0.0,
|
| 1035 |
+
"tau": 0.38358192370540556
|
| 1036 |
+
},
|
| 1037 |
+
"1790188787/train0": {
|
| 1038 |
+
"base_success": 0.0,
|
| 1039 |
+
"base_utility": 0.12476746737957001,
|
| 1040 |
+
"coverage": 1.0,
|
| 1041 |
+
"execute_generated": 1.0,
|
| 1042 |
+
"fallback_rate": 0.0,
|
| 1043 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1044 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1045 |
+
"outcome_ptr": 0.0,
|
| 1046 |
+
"predicted_margin": 0.3857945730136731,
|
| 1047 |
+
"proposal_oracle_success": 0.0,
|
| 1048 |
+
"proposal_oracle_utility": 0.09791924059391022,
|
| 1049 |
+
"selected_candidate_index": 7.0,
|
| 1050 |
+
"selected_success": 0.0,
|
| 1051 |
+
"selected_success_gain_over_base": 0.0,
|
| 1052 |
+
"selected_utility": 0.09734146296977997,
|
| 1053 |
+
"selected_utility_gain_over_base": -0.02742600440979004,
|
| 1054 |
+
"selector_regret": 0.000577777624130249,
|
| 1055 |
+
"success_selector_gap": 0.0,
|
| 1056 |
+
"success_support_gap": 1.0,
|
| 1057 |
+
"support_gap": 1.9020807594060898,
|
| 1058 |
+
"tau": 0.38358192370540556
|
| 1059 |
+
},
|
| 1060 |
+
"1790188787/train1": {
|
| 1061 |
+
"base_success": 0.0,
|
| 1062 |
+
"base_utility": 0.12476746737957001,
|
| 1063 |
+
"coverage": 1.0,
|
| 1064 |
+
"execute_generated": 1.0,
|
| 1065 |
+
"fallback_rate": 0.0,
|
| 1066 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1067 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1068 |
+
"outcome_ptr": 1.0,
|
| 1069 |
+
"predicted_margin": 0.38895499821801166,
|
| 1070 |
+
"proposal_oracle_success": 0.0,
|
| 1071 |
+
"proposal_oracle_utility": 0.13031470775604248,
|
| 1072 |
+
"selected_candidate_index": 0.0,
|
| 1073 |
+
"selected_success": 0.0,
|
| 1074 |
+
"selected_success_gain_over_base": 0.0,
|
| 1075 |
+
"selected_utility": 0.1146477460861206,
|
| 1076 |
+
"selected_utility_gain_over_base": -0.010119721293449402,
|
| 1077 |
+
"selector_regret": 0.015666961669921875,
|
| 1078 |
+
"success_selector_gap": 0.0,
|
| 1079 |
+
"success_support_gap": 1.0,
|
| 1080 |
+
"support_gap": 1.8696852922439575,
|
| 1081 |
+
"tau": 0.38358192370540556
|
| 1082 |
+
},
|
| 1083 |
+
"1790188787/train2": {
|
| 1084 |
+
"base_success": 0.0,
|
| 1085 |
+
"base_utility": 0.12476746737957001,
|
| 1086 |
+
"coverage": 1.0,
|
| 1087 |
+
"execute_generated": 1.0,
|
| 1088 |
+
"fallback_rate": 0.0,
|
| 1089 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1090 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1091 |
+
"outcome_ptr": 1.0,
|
| 1092 |
+
"predicted_margin": 0.38895499821801166,
|
| 1093 |
+
"proposal_oracle_success": 1.0,
|
| 1094 |
+
"proposal_oracle_utility": 2.0,
|
| 1095 |
+
"selected_candidate_index": 1.0,
|
| 1096 |
+
"selected_success": 0.0,
|
| 1097 |
+
"selected_success_gain_over_base": 0.0,
|
| 1098 |
+
"selected_utility": 0.1341685652732849,
|
| 1099 |
+
"selected_utility_gain_over_base": 0.009401097893714905,
|
| 1100 |
+
"selector_regret": 1.865831434726715,
|
| 1101 |
+
"success_selector_gap": 1.0,
|
| 1102 |
+
"success_support_gap": 0.0,
|
| 1103 |
+
"support_gap": 0.0,
|
| 1104 |
+
"tau": 0.38358192370540556
|
| 1105 |
+
},
|
| 1106 |
+
"1822210471/train0": {
|
| 1107 |
+
"base_success": 0.0,
|
| 1108 |
+
"base_utility": 0.07191530615091324,
|
| 1109 |
+
"coverage": 1.0,
|
| 1110 |
+
"execute_generated": 1.0,
|
| 1111 |
+
"fallback_rate": 0.0,
|
| 1112 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1113 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1114 |
+
"outcome_ptr": 1.0,
|
| 1115 |
+
"predicted_margin": 0.38895499821801166,
|
| 1116 |
+
"proposal_oracle_success": 1.0,
|
| 1117 |
+
"proposal_oracle_utility": 2.0,
|
| 1118 |
+
"selected_candidate_index": 4.0,
|
| 1119 |
+
"selected_success": 0.0,
|
| 1120 |
+
"selected_success_gain_over_base": 0.0,
|
| 1121 |
+
"selected_utility": 0.06247224286198616,
|
| 1122 |
+
"selected_utility_gain_over_base": -0.009443063288927078,
|
| 1123 |
+
"selector_regret": 1.9375277571380138,
|
| 1124 |
+
"success_selector_gap": 1.0,
|
| 1125 |
+
"success_support_gap": 0.0,
|
| 1126 |
+
"support_gap": 0.0,
|
| 1127 |
+
"tau": 0.38358192370540556
|
| 1128 |
+
},
|
| 1129 |
+
"1822210471/train1": {
|
| 1130 |
+
"base_success": 0.0,
|
| 1131 |
+
"base_utility": 0.07191530615091324,
|
| 1132 |
+
"coverage": 0.0,
|
| 1133 |
+
"execute_generated": 0.0,
|
| 1134 |
+
"fallback_rate": 1.0,
|
| 1135 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1136 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1137 |
+
"outcome_ptr": 1.0,
|
| 1138 |
+
"predicted_margin": 0.15771149224890263,
|
| 1139 |
+
"proposal_oracle_success": 1.0,
|
| 1140 |
+
"proposal_oracle_utility": 2.0,
|
| 1141 |
+
"selected_candidate_index": 7.0,
|
| 1142 |
+
"selected_success": 0.0,
|
| 1143 |
+
"selected_success_gain_over_base": 0.0,
|
| 1144 |
+
"selected_utility": 0.07191530615091324,
|
| 1145 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1146 |
+
"selector_regret": 1.9280846938490868,
|
| 1147 |
+
"success_selector_gap": 1.0,
|
| 1148 |
+
"success_support_gap": 0.0,
|
| 1149 |
+
"support_gap": 0.0,
|
| 1150 |
+
"tau": 0.38358192370540556
|
| 1151 |
+
},
|
| 1152 |
+
"1822210471/train2": {
|
| 1153 |
+
"base_success": 0.0,
|
| 1154 |
+
"base_utility": 0.07191530615091324,
|
| 1155 |
+
"coverage": 1.0,
|
| 1156 |
+
"execute_generated": 1.0,
|
| 1157 |
+
"fallback_rate": 0.0,
|
| 1158 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1159 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1160 |
+
"outcome_ptr": 1.0,
|
| 1161 |
+
"predicted_margin": 0.38895499821801166,
|
| 1162 |
+
"proposal_oracle_success": 1.0,
|
| 1163 |
+
"proposal_oracle_utility": 2.0,
|
| 1164 |
+
"selected_candidate_index": 3.0,
|
| 1165 |
+
"selected_success": 0.0,
|
| 1166 |
+
"selected_success_gain_over_base": 0.0,
|
| 1167 |
+
"selected_utility": 0.0774010419845581,
|
| 1168 |
+
"selected_utility_gain_over_base": 0.005485735833644867,
|
| 1169 |
+
"selector_regret": 1.922598958015442,
|
| 1170 |
+
"success_selector_gap": 1.0,
|
| 1171 |
+
"success_support_gap": 0.0,
|
| 1172 |
+
"support_gap": 0.0,
|
| 1173 |
+
"tau": 0.38358192370540556
|
| 1174 |
+
},
|
| 1175 |
+
"1845489013/train0": {
|
| 1176 |
+
"base_success": 1.0,
|
| 1177 |
+
"base_utility": 2.0,
|
| 1178 |
+
"coverage": 0.0,
|
| 1179 |
+
"execute_generated": 0.0,
|
| 1180 |
+
"fallback_rate": 1.0,
|
| 1181 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1182 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1183 |
+
"outcome_ptr": 0.0,
|
| 1184 |
+
"predicted_margin": 0.36221896637920825,
|
| 1185 |
+
"proposal_oracle_success": 1.0,
|
| 1186 |
+
"proposal_oracle_utility": 2.0,
|
| 1187 |
+
"selected_candidate_index": 0.0,
|
| 1188 |
+
"selected_success": 1.0,
|
| 1189 |
+
"selected_success_gain_over_base": 0.0,
|
| 1190 |
+
"selected_utility": 2.0,
|
| 1191 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1192 |
+
"selector_regret": 0.0,
|
| 1193 |
+
"success_selector_gap": 0.0,
|
| 1194 |
+
"success_support_gap": 0.0,
|
| 1195 |
+
"support_gap": 0.0,
|
| 1196 |
+
"tau": 0.38358192370540556
|
| 1197 |
+
},
|
| 1198 |
+
"1845489013/train1": {
|
| 1199 |
+
"base_success": 1.0,
|
| 1200 |
+
"base_utility": 2.0,
|
| 1201 |
+
"coverage": 1.0,
|
| 1202 |
+
"execute_generated": 1.0,
|
| 1203 |
+
"fallback_rate": 0.0,
|
| 1204 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1205 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1206 |
+
"outcome_ptr": 0.0,
|
| 1207 |
+
"predicted_margin": 0.38895499821801166,
|
| 1208 |
+
"proposal_oracle_success": 1.0,
|
| 1209 |
+
"proposal_oracle_utility": 2.0,
|
| 1210 |
+
"selected_candidate_index": 2.0,
|
| 1211 |
+
"selected_success": 1.0,
|
| 1212 |
+
"selected_success_gain_over_base": 0.0,
|
| 1213 |
+
"selected_utility": 2.0,
|
| 1214 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1215 |
+
"selector_regret": 0.0,
|
| 1216 |
+
"success_selector_gap": 0.0,
|
| 1217 |
+
"success_support_gap": 0.0,
|
| 1218 |
+
"support_gap": 0.0,
|
| 1219 |
+
"tau": 0.38358192370540556
|
| 1220 |
+
},
|
| 1221 |
+
"1845489013/train2": {
|
| 1222 |
+
"base_success": 1.0,
|
| 1223 |
+
"base_utility": 2.0,
|
| 1224 |
+
"coverage": 1.0,
|
| 1225 |
+
"execute_generated": 1.0,
|
| 1226 |
+
"fallback_rate": 0.0,
|
| 1227 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1228 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1229 |
+
"outcome_ptr": 0.0,
|
| 1230 |
+
"predicted_margin": 0.39716629921595253,
|
| 1231 |
+
"proposal_oracle_success": 1.0,
|
| 1232 |
+
"proposal_oracle_utility": 2.0,
|
| 1233 |
+
"selected_candidate_index": 5.0,
|
| 1234 |
+
"selected_success": 1.0,
|
| 1235 |
+
"selected_success_gain_over_base": 0.0,
|
| 1236 |
+
"selected_utility": 2.0,
|
| 1237 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1238 |
+
"selector_regret": 0.0,
|
| 1239 |
+
"success_selector_gap": 0.0,
|
| 1240 |
+
"success_support_gap": 0.0,
|
| 1241 |
+
"support_gap": 0.0,
|
| 1242 |
+
"tau": 0.38358192370540556
|
| 1243 |
+
},
|
| 1244 |
+
"1999022574/train0": {
|
| 1245 |
+
"base_success": 1.0,
|
| 1246 |
+
"base_utility": 2.0,
|
| 1247 |
+
"coverage": 1.0,
|
| 1248 |
+
"execute_generated": 1.0,
|
| 1249 |
+
"fallback_rate": 0.0,
|
| 1250 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1251 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1252 |
+
"outcome_ptr": 0.0,
|
| 1253 |
+
"predicted_margin": 0.4006380153774231,
|
| 1254 |
+
"proposal_oracle_success": 1.0,
|
| 1255 |
+
"proposal_oracle_utility": 2.0,
|
| 1256 |
+
"selected_candidate_index": 0.0,
|
| 1257 |
+
"selected_success": 0.0,
|
| 1258 |
+
"selected_success_gain_over_base": -1.0,
|
| 1259 |
+
"selected_utility": 0.1476449966430664,
|
| 1260 |
+
"selected_utility_gain_over_base": -1.8523550033569336,
|
| 1261 |
+
"selector_regret": 1.8523550033569336,
|
| 1262 |
+
"success_selector_gap": 1.0,
|
| 1263 |
+
"success_support_gap": 0.0,
|
| 1264 |
+
"support_gap": 0.0,
|
| 1265 |
+
"tau": 0.38358192370540556
|
| 1266 |
+
},
|
| 1267 |
+
"1999022574/train1": {
|
| 1268 |
+
"base_success": 1.0,
|
| 1269 |
+
"base_utility": 2.0,
|
| 1270 |
+
"coverage": 1.0,
|
| 1271 |
+
"execute_generated": 1.0,
|
| 1272 |
+
"fallback_rate": 0.0,
|
| 1273 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1274 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1275 |
+
"outcome_ptr": 0.0,
|
| 1276 |
+
"predicted_margin": 0.38895499821801166,
|
| 1277 |
+
"proposal_oracle_success": 1.0,
|
| 1278 |
+
"proposal_oracle_utility": 2.0,
|
| 1279 |
+
"selected_candidate_index": 5.0,
|
| 1280 |
+
"selected_success": 0.0,
|
| 1281 |
+
"selected_success_gain_over_base": -1.0,
|
| 1282 |
+
"selected_utility": 0.8125,
|
| 1283 |
+
"selected_utility_gain_over_base": -1.1875,
|
| 1284 |
+
"selector_regret": 1.1875,
|
| 1285 |
+
"success_selector_gap": 1.0,
|
| 1286 |
+
"success_support_gap": 0.0,
|
| 1287 |
+
"support_gap": 0.0,
|
| 1288 |
+
"tau": 0.38358192370540556
|
| 1289 |
+
},
|
| 1290 |
+
"1999022574/train2": {
|
| 1291 |
+
"base_success": 1.0,
|
| 1292 |
+
"base_utility": 2.0,
|
| 1293 |
+
"coverage": 1.0,
|
| 1294 |
+
"execute_generated": 1.0,
|
| 1295 |
+
"fallback_rate": 0.0,
|
| 1296 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1297 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1298 |
+
"outcome_ptr": 0.0,
|
| 1299 |
+
"predicted_margin": 0.38895499821801166,
|
| 1300 |
+
"proposal_oracle_success": 1.0,
|
| 1301 |
+
"proposal_oracle_utility": 2.0,
|
| 1302 |
+
"selected_candidate_index": 3.0,
|
| 1303 |
+
"selected_success": 0.0,
|
| 1304 |
+
"selected_success_gain_over_base": -1.0,
|
| 1305 |
+
"selected_utility": 0.1785425841808319,
|
| 1306 |
+
"selected_utility_gain_over_base": -1.821457415819168,
|
| 1307 |
+
"selector_regret": 1.821457415819168,
|
| 1308 |
+
"success_selector_gap": 1.0,
|
| 1309 |
+
"success_support_gap": 0.0,
|
| 1310 |
+
"support_gap": 0.0,
|
| 1311 |
+
"tau": 0.38358192370540556
|
| 1312 |
+
},
|
| 1313 |
+
"2012211287/train0": {
|
| 1314 |
+
"base_success": 0.0,
|
| 1315 |
+
"base_utility": 0.7236053347587585,
|
| 1316 |
+
"coverage": 0.0,
|
| 1317 |
+
"execute_generated": 0.0,
|
| 1318 |
+
"fallback_rate": 1.0,
|
| 1319 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1320 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1321 |
+
"outcome_ptr": 1.0,
|
| 1322 |
+
"predicted_margin": 0.373318150625259,
|
| 1323 |
+
"proposal_oracle_success": 1.0,
|
| 1324 |
+
"proposal_oracle_utility": 2.0,
|
| 1325 |
+
"selected_candidate_index": 0.0,
|
| 1326 |
+
"selected_success": 0.0,
|
| 1327 |
+
"selected_success_gain_over_base": 0.0,
|
| 1328 |
+
"selected_utility": 0.7236053347587585,
|
| 1329 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1330 |
+
"selector_regret": 1.2763946652412415,
|
| 1331 |
+
"success_selector_gap": 1.0,
|
| 1332 |
+
"success_support_gap": 0.0,
|
| 1333 |
+
"support_gap": 0.0,
|
| 1334 |
+
"tau": 0.38358192370540556
|
| 1335 |
+
},
|
| 1336 |
+
"2012211287/train1": {
|
| 1337 |
+
"base_success": 0.0,
|
| 1338 |
+
"base_utility": 0.7236053347587585,
|
| 1339 |
+
"coverage": 0.0,
|
| 1340 |
+
"execute_generated": 0.0,
|
| 1341 |
+
"fallback_rate": 1.0,
|
| 1342 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1343 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1344 |
+
"outcome_ptr": 1.0,
|
| 1345 |
+
"predicted_margin": 0.38358192370540556,
|
| 1346 |
+
"proposal_oracle_success": 1.0,
|
| 1347 |
+
"proposal_oracle_utility": 2.0,
|
| 1348 |
+
"selected_candidate_index": 0.0,
|
| 1349 |
+
"selected_success": 0.0,
|
| 1350 |
+
"selected_success_gain_over_base": 0.0,
|
| 1351 |
+
"selected_utility": 0.7236053347587585,
|
| 1352 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1353 |
+
"selector_regret": 1.2763946652412415,
|
| 1354 |
+
"success_selector_gap": 1.0,
|
| 1355 |
+
"success_support_gap": 0.0,
|
| 1356 |
+
"support_gap": 0.0,
|
| 1357 |
+
"tau": 0.38358192370540556
|
| 1358 |
+
},
|
| 1359 |
+
"2012211287/train2": {
|
| 1360 |
+
"base_success": 0.0,
|
| 1361 |
+
"base_utility": 0.7236053347587585,
|
| 1362 |
+
"coverage": 0.0,
|
| 1363 |
+
"execute_generated": 0.0,
|
| 1364 |
+
"fallback_rate": 1.0,
|
| 1365 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1366 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1367 |
+
"outcome_ptr": 1.0,
|
| 1368 |
+
"predicted_margin": 0.3804379751300867,
|
| 1369 |
+
"proposal_oracle_success": 1.0,
|
| 1370 |
+
"proposal_oracle_utility": 2.0,
|
| 1371 |
+
"selected_candidate_index": 2.0,
|
| 1372 |
+
"selected_success": 0.0,
|
| 1373 |
+
"selected_success_gain_over_base": 0.0,
|
| 1374 |
+
"selected_utility": 0.7236053347587585,
|
| 1375 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1376 |
+
"selector_regret": 1.2763946652412415,
|
| 1377 |
+
"success_selector_gap": 1.0,
|
| 1378 |
+
"success_support_gap": 0.0,
|
| 1379 |
+
"support_gap": 0.0,
|
| 1380 |
+
"tau": 0.38358192370540556
|
| 1381 |
+
},
|
| 1382 |
+
"2038594191/train0": {
|
| 1383 |
+
"base_success": 1.0,
|
| 1384 |
+
"base_utility": 2.0,
|
| 1385 |
+
"coverage": 0.0,
|
| 1386 |
+
"execute_generated": 0.0,
|
| 1387 |
+
"fallback_rate": 1.0,
|
| 1388 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1389 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1390 |
+
"outcome_ptr": 0.0,
|
| 1391 |
+
"predicted_margin": 0.32967755546826816,
|
| 1392 |
+
"proposal_oracle_success": 1.0,
|
| 1393 |
+
"proposal_oracle_utility": 2.0,
|
| 1394 |
+
"selected_candidate_index": 6.0,
|
| 1395 |
+
"selected_success": 1.0,
|
| 1396 |
+
"selected_success_gain_over_base": 0.0,
|
| 1397 |
+
"selected_utility": 2.0,
|
| 1398 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1399 |
+
"selector_regret": 0.0,
|
| 1400 |
+
"success_selector_gap": 0.0,
|
| 1401 |
+
"success_support_gap": 0.0,
|
| 1402 |
+
"support_gap": 0.0,
|
| 1403 |
+
"tau": 0.38358192370540556
|
| 1404 |
+
},
|
| 1405 |
+
"2038594191/train1": {
|
| 1406 |
+
"base_success": 1.0,
|
| 1407 |
+
"base_utility": 2.0,
|
| 1408 |
+
"coverage": 0.0,
|
| 1409 |
+
"execute_generated": 0.0,
|
| 1410 |
+
"fallback_rate": 1.0,
|
| 1411 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1412 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1413 |
+
"outcome_ptr": 0.0,
|
| 1414 |
+
"predicted_margin": 0.3225177112831876,
|
| 1415 |
+
"proposal_oracle_success": 1.0,
|
| 1416 |
+
"proposal_oracle_utility": 2.0,
|
| 1417 |
+
"selected_candidate_index": 1.0,
|
| 1418 |
+
"selected_success": 1.0,
|
| 1419 |
+
"selected_success_gain_over_base": 0.0,
|
| 1420 |
+
"selected_utility": 2.0,
|
| 1421 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1422 |
+
"selector_regret": 0.0,
|
| 1423 |
+
"success_selector_gap": 0.0,
|
| 1424 |
+
"success_support_gap": 0.0,
|
| 1425 |
+
"support_gap": 0.0,
|
| 1426 |
+
"tau": 0.38358192370540556
|
| 1427 |
+
},
|
| 1428 |
+
"2038594191/train2": {
|
| 1429 |
+
"base_success": 1.0,
|
| 1430 |
+
"base_utility": 2.0,
|
| 1431 |
+
"coverage": 1.0,
|
| 1432 |
+
"execute_generated": 1.0,
|
| 1433 |
+
"fallback_rate": 0.0,
|
| 1434 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1435 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1436 |
+
"outcome_ptr": 0.0,
|
| 1437 |
+
"predicted_margin": 0.39493036586117725,
|
| 1438 |
+
"proposal_oracle_success": 1.0,
|
| 1439 |
+
"proposal_oracle_utility": 2.0,
|
| 1440 |
+
"selected_candidate_index": 0.0,
|
| 1441 |
+
"selected_success": 0.0,
|
| 1442 |
+
"selected_success_gain_over_base": -1.0,
|
| 1443 |
+
"selected_utility": 0.04917396977543831,
|
| 1444 |
+
"selected_utility_gain_over_base": -1.9508260302245617,
|
| 1445 |
+
"selector_regret": 1.9508260302245617,
|
| 1446 |
+
"success_selector_gap": 1.0,
|
| 1447 |
+
"success_support_gap": 0.0,
|
| 1448 |
+
"support_gap": 0.0,
|
| 1449 |
+
"tau": 0.38358192370540556
|
| 1450 |
+
},
|
| 1451 |
+
"2054899126/train0": {
|
| 1452 |
+
"base_success": 1.0,
|
| 1453 |
+
"base_utility": 2.0,
|
| 1454 |
+
"coverage": 0.0,
|
| 1455 |
+
"execute_generated": 0.0,
|
| 1456 |
+
"fallback_rate": 1.0,
|
| 1457 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1458 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1459 |
+
"outcome_ptr": 0.0,
|
| 1460 |
+
"predicted_margin": 0.22163620371066634,
|
| 1461 |
+
"proposal_oracle_success": 0.5,
|
| 1462 |
+
"proposal_oracle_utility": 1.077283151447773,
|
| 1463 |
+
"selected_candidate_index": 0.0,
|
| 1464 |
+
"selected_success": 1.0,
|
| 1465 |
+
"selected_success_gain_over_base": 0.0,
|
| 1466 |
+
"selected_utility": 2.0,
|
| 1467 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1468 |
+
"selector_regret": 0.0,
|
| 1469 |
+
"success_selector_gap": 0.0,
|
| 1470 |
+
"success_support_gap": 0.5,
|
| 1471 |
+
"support_gap": 0.922716848552227,
|
| 1472 |
+
"tau": 0.38358192370540556
|
| 1473 |
+
},
|
| 1474 |
+
"2054899126/train1": {
|
| 1475 |
+
"base_success": 1.0,
|
| 1476 |
+
"base_utility": 2.0,
|
| 1477 |
+
"coverage": 0.5,
|
| 1478 |
+
"execute_generated": 0.5,
|
| 1479 |
+
"fallback_rate": 0.5,
|
| 1480 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1481 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1482 |
+
"outcome_ptr": 0.0,
|
| 1483 |
+
"predicted_margin": 0.27996525202086264,
|
| 1484 |
+
"proposal_oracle_success": 0.5,
|
| 1485 |
+
"proposal_oracle_utility": 1.0696808770298958,
|
| 1486 |
+
"selected_candidate_index": 0.0,
|
| 1487 |
+
"selected_success": 1.0,
|
| 1488 |
+
"selected_success_gain_over_base": 0.0,
|
| 1489 |
+
"selected_utility": 2.0,
|
| 1490 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1491 |
+
"selector_regret": 0.0,
|
| 1492 |
+
"success_selector_gap": 0.0,
|
| 1493 |
+
"success_support_gap": 0.5,
|
| 1494 |
+
"support_gap": 0.9303191229701042,
|
| 1495 |
+
"tau": 0.38358192370540556
|
| 1496 |
+
},
|
| 1497 |
+
"2054899126/train2": {
|
| 1498 |
+
"base_success": 1.0,
|
| 1499 |
+
"base_utility": 2.0,
|
| 1500 |
+
"coverage": 0.5,
|
| 1501 |
+
"execute_generated": 0.5,
|
| 1502 |
+
"fallback_rate": 0.5,
|
| 1503 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1504 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1505 |
+
"outcome_ptr": 0.0,
|
| 1506 |
+
"predicted_margin": 0.2705486918890879,
|
| 1507 |
+
"proposal_oracle_success": 0.5,
|
| 1508 |
+
"proposal_oracle_utility": 1.0455262660980225,
|
| 1509 |
+
"selected_candidate_index": 0.0,
|
| 1510 |
+
"selected_success": 1.0,
|
| 1511 |
+
"selected_success_gain_over_base": 0.0,
|
| 1512 |
+
"selected_utility": 2.0,
|
| 1513 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1514 |
+
"selector_regret": 0.0,
|
| 1515 |
+
"success_selector_gap": 0.0,
|
| 1516 |
+
"success_support_gap": 0.5,
|
| 1517 |
+
"support_gap": 0.9544737339019775,
|
| 1518 |
+
"tau": 0.38358192370540556
|
| 1519 |
+
},
|
| 1520 |
+
"2061635888/train0": {
|
| 1521 |
+
"base_success": 0.0,
|
| 1522 |
+
"base_utility": 0.05225050449371338,
|
| 1523 |
+
"coverage": 0.0,
|
| 1524 |
+
"execute_generated": 0.0,
|
| 1525 |
+
"fallback_rate": 1.0,
|
| 1526 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1527 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1528 |
+
"outcome_ptr": 1.0,
|
| 1529 |
+
"predicted_margin": 0.29614285515247524,
|
| 1530 |
+
"proposal_oracle_success": 0.0,
|
| 1531 |
+
"proposal_oracle_utility": 0.09799930453300476,
|
| 1532 |
+
"selected_candidate_index": 6.0,
|
| 1533 |
+
"selected_success": 0.0,
|
| 1534 |
+
"selected_success_gain_over_base": 0.0,
|
| 1535 |
+
"selected_utility": 0.05225050449371338,
|
| 1536 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1537 |
+
"selector_regret": 0.04574880003929138,
|
| 1538 |
+
"success_selector_gap": 0.0,
|
| 1539 |
+
"success_support_gap": 1.0,
|
| 1540 |
+
"support_gap": 1.9020006954669952,
|
| 1541 |
+
"tau": 0.38358192370540556
|
| 1542 |
+
},
|
| 1543 |
+
"2061635888/train1": {
|
| 1544 |
+
"base_success": 0.0,
|
| 1545 |
+
"base_utility": 0.05225050449371338,
|
| 1546 |
+
"coverage": 1.0,
|
| 1547 |
+
"execute_generated": 1.0,
|
| 1548 |
+
"fallback_rate": 0.0,
|
| 1549 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1550 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1551 |
+
"outcome_ptr": 1.0,
|
| 1552 |
+
"predicted_margin": 0.3857945730136731,
|
| 1553 |
+
"proposal_oracle_success": 0.0,
|
| 1554 |
+
"proposal_oracle_utility": 0.07580336928367615,
|
| 1555 |
+
"selected_candidate_index": 0.0,
|
| 1556 |
+
"selected_success": 0.0,
|
| 1557 |
+
"selected_success_gain_over_base": 0.0,
|
| 1558 |
+
"selected_utility": 0.05141691863536835,
|
| 1559 |
+
"selected_utility_gain_over_base": -0.0008335858583450317,
|
| 1560 |
+
"selector_regret": 0.0243864506483078,
|
| 1561 |
+
"success_selector_gap": 0.0,
|
| 1562 |
+
"success_support_gap": 1.0,
|
| 1563 |
+
"support_gap": 1.9241966307163239,
|
| 1564 |
+
"tau": 0.38358192370540556
|
| 1565 |
+
},
|
| 1566 |
+
"2061635888/train2": {
|
| 1567 |
+
"base_success": 0.0,
|
| 1568 |
+
"base_utility": 0.05225050449371338,
|
| 1569 |
+
"coverage": 0.0,
|
| 1570 |
+
"execute_generated": 0.0,
|
| 1571 |
+
"fallback_rate": 1.0,
|
| 1572 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1573 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1574 |
+
"outcome_ptr": 1.0,
|
| 1575 |
+
"predicted_margin": 0.3025802788019403,
|
| 1576 |
+
"proposal_oracle_success": 0.0,
|
| 1577 |
+
"proposal_oracle_utility": 0.11105132102966309,
|
| 1578 |
+
"selected_candidate_index": 0.0,
|
| 1579 |
+
"selected_success": 0.0,
|
| 1580 |
+
"selected_success_gain_over_base": 0.0,
|
| 1581 |
+
"selected_utility": 0.05225050449371338,
|
| 1582 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1583 |
+
"selector_regret": 0.05880081653594971,
|
| 1584 |
+
"success_selector_gap": 0.0,
|
| 1585 |
+
"success_support_gap": 1.0,
|
| 1586 |
+
"support_gap": 1.888948678970337,
|
| 1587 |
+
"tau": 0.38358192370540556
|
| 1588 |
+
},
|
| 1589 |
+
"211245842/train0": {
|
| 1590 |
+
"base_success": 0.0,
|
| 1591 |
+
"base_utility": 0.19090841710567474,
|
| 1592 |
+
"coverage": 1.0,
|
| 1593 |
+
"execute_generated": 1.0,
|
| 1594 |
+
"fallback_rate": 0.0,
|
| 1595 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1596 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1597 |
+
"outcome_ptr": 1.0,
|
| 1598 |
+
"predicted_margin": 0.42005283704628976,
|
| 1599 |
+
"proposal_oracle_success": 1.0,
|
| 1600 |
+
"proposal_oracle_utility": 2.0,
|
| 1601 |
+
"selected_candidate_index": 1.0,
|
| 1602 |
+
"selected_success": 0.0,
|
| 1603 |
+
"selected_success_gain_over_base": 0.0,
|
| 1604 |
+
"selected_utility": 0.12738418579101562,
|
| 1605 |
+
"selected_utility_gain_over_base": -0.06352423131465912,
|
| 1606 |
+
"selector_regret": 1.8726158142089844,
|
| 1607 |
+
"success_selector_gap": 1.0,
|
| 1608 |
+
"success_support_gap": 0.0,
|
| 1609 |
+
"support_gap": 0.0,
|
| 1610 |
+
"tau": 0.38358192370540556
|
| 1611 |
+
},
|
| 1612 |
+
"211245842/train1": {
|
| 1613 |
+
"base_success": 0.0,
|
| 1614 |
+
"base_utility": 0.19090841710567474,
|
| 1615 |
+
"coverage": 1.0,
|
| 1616 |
+
"execute_generated": 1.0,
|
| 1617 |
+
"fallback_rate": 0.0,
|
| 1618 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1619 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1620 |
+
"outcome_ptr": 1.0,
|
| 1621 |
+
"predicted_margin": 0.38895499821801166,
|
| 1622 |
+
"proposal_oracle_success": 0.0,
|
| 1623 |
+
"proposal_oracle_utility": 0.21295717358589172,
|
| 1624 |
+
"selected_candidate_index": 1.0,
|
| 1625 |
+
"selected_success": 0.0,
|
| 1626 |
+
"selected_success_gain_over_base": 0.0,
|
| 1627 |
+
"selected_utility": 0.18482810258865356,
|
| 1628 |
+
"selected_utility_gain_over_base": -0.006080314517021179,
|
| 1629 |
+
"selector_regret": 0.02812907099723816,
|
| 1630 |
+
"success_selector_gap": 0.0,
|
| 1631 |
+
"success_support_gap": 1.0,
|
| 1632 |
+
"support_gap": 1.7870428264141083,
|
| 1633 |
+
"tau": 0.38358192370540556
|
| 1634 |
+
},
|
| 1635 |
+
"211245842/train2": {
|
| 1636 |
+
"base_success": 0.0,
|
| 1637 |
+
"base_utility": 0.19090841710567474,
|
| 1638 |
+
"coverage": 1.0,
|
| 1639 |
+
"execute_generated": 1.0,
|
| 1640 |
+
"fallback_rate": 0.0,
|
| 1641 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1642 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1643 |
+
"outcome_ptr": 1.0,
|
| 1644 |
+
"predicted_margin": 0.4041207910395072,
|
| 1645 |
+
"proposal_oracle_success": 0.0,
|
| 1646 |
+
"proposal_oracle_utility": 0.21523693203926086,
|
| 1647 |
+
"selected_candidate_index": 2.0,
|
| 1648 |
+
"selected_success": 0.0,
|
| 1649 |
+
"selected_success_gain_over_base": 0.0,
|
| 1650 |
+
"selected_utility": 0.21523693203926086,
|
| 1651 |
+
"selected_utility_gain_over_base": 0.02432851493358612,
|
| 1652 |
+
"selector_regret": 0.0,
|
| 1653 |
+
"success_selector_gap": 0.0,
|
| 1654 |
+
"success_support_gap": 1.0,
|
| 1655 |
+
"support_gap": 1.7847630679607391,
|
| 1656 |
+
"tau": 0.38358192370540556
|
| 1657 |
+
},
|
| 1658 |
+
"278008524/train0": {
|
| 1659 |
+
"base_success": 0.0,
|
| 1660 |
+
"base_utility": 0.042734989896416664,
|
| 1661 |
+
"coverage": 0.0,
|
| 1662 |
+
"execute_generated": 0.0,
|
| 1663 |
+
"fallback_rate": 1.0,
|
| 1664 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1665 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1666 |
+
"outcome_ptr": 1.0,
|
| 1667 |
+
"predicted_margin": 0.31326542141341585,
|
| 1668 |
+
"proposal_oracle_success": 0.5,
|
| 1669 |
+
"proposal_oracle_utility": 1.0287093725055456,
|
| 1670 |
+
"selected_candidate_index": 0.0,
|
| 1671 |
+
"selected_success": 0.0,
|
| 1672 |
+
"selected_success_gain_over_base": 0.0,
|
| 1673 |
+
"selected_utility": 0.042734989896416664,
|
| 1674 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1675 |
+
"selector_regret": 0.985974382609129,
|
| 1676 |
+
"success_selector_gap": 0.5,
|
| 1677 |
+
"success_support_gap": 0.0,
|
| 1678 |
+
"support_gap": 0.08519926853477955,
|
| 1679 |
+
"tau": 0.38358192370540556
|
| 1680 |
+
},
|
| 1681 |
+
"278008524/train1": {
|
| 1682 |
+
"base_success": 0.0,
|
| 1683 |
+
"base_utility": 0.042734989896416664,
|
| 1684 |
+
"coverage": 0.0,
|
| 1685 |
+
"execute_generated": 0.0,
|
| 1686 |
+
"fallback_rate": 1.0,
|
| 1687 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1688 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1689 |
+
"outcome_ptr": 1.0,
|
| 1690 |
+
"predicted_margin": 0.3507924735705492,
|
| 1691 |
+
"proposal_oracle_success": 0.5,
|
| 1692 |
+
"proposal_oracle_utility": 1.0376745946705341,
|
| 1693 |
+
"selected_candidate_index": 6.5,
|
| 1694 |
+
"selected_success": 0.0,
|
| 1695 |
+
"selected_success_gain_over_base": 0.0,
|
| 1696 |
+
"selected_utility": 0.042734989896416664,
|
| 1697 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1698 |
+
"selector_regret": 0.9949396047741175,
|
| 1699 |
+
"success_selector_gap": 0.5,
|
| 1700 |
+
"success_support_gap": 0.0,
|
| 1701 |
+
"support_gap": 0.07623404636979103,
|
| 1702 |
+
"tau": 0.38358192370540556
|
| 1703 |
+
},
|
| 1704 |
+
"278008524/train2": {
|
| 1705 |
+
"base_success": 0.0,
|
| 1706 |
+
"base_utility": 0.042734989896416664,
|
| 1707 |
+
"coverage": 0.0,
|
| 1708 |
+
"execute_generated": 0.0,
|
| 1709 |
+
"fallback_rate": 1.0,
|
| 1710 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1711 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1712 |
+
"outcome_ptr": 1.0,
|
| 1713 |
+
"predicted_margin": 0.352194269577489,
|
| 1714 |
+
"proposal_oracle_success": 0.5,
|
| 1715 |
+
"proposal_oracle_utility": 1.1359489113092422,
|
| 1716 |
+
"selected_candidate_index": 2.0,
|
| 1717 |
+
"selected_success": 0.0,
|
| 1718 |
+
"selected_success_gain_over_base": 0.0,
|
| 1719 |
+
"selected_utility": 0.042734989896416664,
|
| 1720 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1721 |
+
"selector_regret": 1.0932139214128256,
|
| 1722 |
+
"success_selector_gap": 0.5,
|
| 1723 |
+
"success_support_gap": 0.0,
|
| 1724 |
+
"support_gap": 0.0,
|
| 1725 |
+
"tau": 0.38358192370540556
|
| 1726 |
+
},
|
| 1727 |
+
"307068879/train0": {
|
| 1728 |
+
"base_success": 0.0,
|
| 1729 |
+
"base_utility": 0.6000905632972717,
|
| 1730 |
+
"coverage": 1.0,
|
| 1731 |
+
"execute_generated": 1.0,
|
| 1732 |
+
"fallback_rate": 0.0,
|
| 1733 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1734 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1735 |
+
"outcome_ptr": 0.0,
|
| 1736 |
+
"predicted_margin": 0.4030799603405269,
|
| 1737 |
+
"proposal_oracle_success": 0.0,
|
| 1738 |
+
"proposal_oracle_utility": 0.2115575522184372,
|
| 1739 |
+
"selected_candidate_index": 1.0,
|
| 1740 |
+
"selected_success": 0.0,
|
| 1741 |
+
"selected_success_gain_over_base": 0.0,
|
| 1742 |
+
"selected_utility": 0.20728005468845367,
|
| 1743 |
+
"selected_utility_gain_over_base": -0.39281050860881805,
|
| 1744 |
+
"selector_regret": 0.0042774975299835205,
|
| 1745 |
+
"success_selector_gap": 0.0,
|
| 1746 |
+
"success_support_gap": 1.0,
|
| 1747 |
+
"support_gap": 1.7884424477815628,
|
| 1748 |
+
"tau": 0.38358192370540556
|
| 1749 |
+
},
|
| 1750 |
+
"307068879/train1": {
|
| 1751 |
+
"base_success": 0.0,
|
| 1752 |
+
"base_utility": 0.6000905632972717,
|
| 1753 |
+
"coverage": 0.0,
|
| 1754 |
+
"execute_generated": 0.0,
|
| 1755 |
+
"fallback_rate": 1.0,
|
| 1756 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1757 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1758 |
+
"outcome_ptr": 0.0,
|
| 1759 |
+
"predicted_margin": 0.38358192370540556,
|
| 1760 |
+
"proposal_oracle_success": 0.0,
|
| 1761 |
+
"proposal_oracle_utility": 0.5876073241233826,
|
| 1762 |
+
"selected_candidate_index": 0.0,
|
| 1763 |
+
"selected_success": 0.0,
|
| 1764 |
+
"selected_success_gain_over_base": 0.0,
|
| 1765 |
+
"selected_utility": 0.6000905632972717,
|
| 1766 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1767 |
+
"selector_regret": 0.0,
|
| 1768 |
+
"success_selector_gap": 0.0,
|
| 1769 |
+
"success_support_gap": 1.0,
|
| 1770 |
+
"support_gap": 1.4123926758766174,
|
| 1771 |
+
"tau": 0.38358192370540556
|
| 1772 |
+
},
|
| 1773 |
+
"307068879/train2": {
|
| 1774 |
+
"base_success": 0.0,
|
| 1775 |
+
"base_utility": 0.6000905632972717,
|
| 1776 |
+
"coverage": 1.0,
|
| 1777 |
+
"execute_generated": 1.0,
|
| 1778 |
+
"fallback_rate": 0.0,
|
| 1779 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1780 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1781 |
+
"outcome_ptr": 0.0,
|
| 1782 |
+
"predicted_margin": 0.3857945730136731,
|
| 1783 |
+
"proposal_oracle_success": 0.0,
|
| 1784 |
+
"proposal_oracle_utility": 0.22727864980697632,
|
| 1785 |
+
"selected_candidate_index": 0.0,
|
| 1786 |
+
"selected_success": 0.0,
|
| 1787 |
+
"selected_success_gain_over_base": 0.0,
|
| 1788 |
+
"selected_utility": 0.22035211324691772,
|
| 1789 |
+
"selected_utility_gain_over_base": -0.379738450050354,
|
| 1790 |
+
"selector_regret": 0.006926536560058594,
|
| 1791 |
+
"success_selector_gap": 0.0,
|
| 1792 |
+
"success_support_gap": 1.0,
|
| 1793 |
+
"support_gap": 1.7727213501930237,
|
| 1794 |
+
"tau": 0.38358192370540556
|
| 1795 |
+
},
|
| 1796 |
+
"412102563/train0": {
|
| 1797 |
+
"base_success": 1.0,
|
| 1798 |
+
"base_utility": 2.0,
|
| 1799 |
+
"coverage": 1.0,
|
| 1800 |
+
"execute_generated": 1.0,
|
| 1801 |
+
"fallback_rate": 0.0,
|
| 1802 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1803 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1804 |
+
"outcome_ptr": 0.0,
|
| 1805 |
+
"predicted_margin": 0.4266296552350286,
|
| 1806 |
+
"proposal_oracle_success": 1.0,
|
| 1807 |
+
"proposal_oracle_utility": 2.0,
|
| 1808 |
+
"selected_candidate_index": 1.0,
|
| 1809 |
+
"selected_success": 1.0,
|
| 1810 |
+
"selected_success_gain_over_base": 0.0,
|
| 1811 |
+
"selected_utility": 2.0,
|
| 1812 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1813 |
+
"selector_regret": 0.0,
|
| 1814 |
+
"success_selector_gap": 0.0,
|
| 1815 |
+
"success_support_gap": 0.0,
|
| 1816 |
+
"support_gap": 0.0,
|
| 1817 |
+
"tau": 0.38358192370540556
|
| 1818 |
+
},
|
| 1819 |
+
"412102563/train1": {
|
| 1820 |
+
"base_success": 1.0,
|
| 1821 |
+
"base_utility": 2.0,
|
| 1822 |
+
"coverage": 1.0,
|
| 1823 |
+
"execute_generated": 1.0,
|
| 1824 |
+
"fallback_rate": 0.0,
|
| 1825 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1826 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1827 |
+
"outcome_ptr": 0.0,
|
| 1828 |
+
"predicted_margin": 0.38895499821801166,
|
| 1829 |
+
"proposal_oracle_success": 1.0,
|
| 1830 |
+
"proposal_oracle_utility": 2.0,
|
| 1831 |
+
"selected_candidate_index": 4.0,
|
| 1832 |
+
"selected_success": 1.0,
|
| 1833 |
+
"selected_success_gain_over_base": 0.0,
|
| 1834 |
+
"selected_utility": 2.0,
|
| 1835 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1836 |
+
"selector_regret": 0.0,
|
| 1837 |
+
"success_selector_gap": 0.0,
|
| 1838 |
+
"success_support_gap": 0.0,
|
| 1839 |
+
"support_gap": 0.0,
|
| 1840 |
+
"tau": 0.38358192370540556
|
| 1841 |
+
},
|
| 1842 |
+
"412102563/train2": {
|
| 1843 |
+
"base_success": 1.0,
|
| 1844 |
+
"base_utility": 2.0,
|
| 1845 |
+
"coverage": 1.0,
|
| 1846 |
+
"execute_generated": 1.0,
|
| 1847 |
+
"fallback_rate": 0.0,
|
| 1848 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1849 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1850 |
+
"outcome_ptr": 0.0,
|
| 1851 |
+
"predicted_margin": 0.38895499821801166,
|
| 1852 |
+
"proposal_oracle_success": 1.0,
|
| 1853 |
+
"proposal_oracle_utility": 2.0,
|
| 1854 |
+
"selected_candidate_index": 2.0,
|
| 1855 |
+
"selected_success": 0.0,
|
| 1856 |
+
"selected_success_gain_over_base": -1.0,
|
| 1857 |
+
"selected_utility": 0.18793080747127533,
|
| 1858 |
+
"selected_utility_gain_over_base": -1.8120691925287247,
|
| 1859 |
+
"selector_regret": 1.8120691925287247,
|
| 1860 |
+
"success_selector_gap": 1.0,
|
| 1861 |
+
"success_support_gap": 0.0,
|
| 1862 |
+
"support_gap": 0.0,
|
| 1863 |
+
"tau": 0.38358192370540556
|
| 1864 |
+
},
|
| 1865 |
+
"440577711/train0": {
|
| 1866 |
+
"base_success": 0.0,
|
| 1867 |
+
"base_utility": 0.036152780055999756,
|
| 1868 |
+
"coverage": 1.0,
|
| 1869 |
+
"execute_generated": 1.0,
|
| 1870 |
+
"fallback_rate": 0.0,
|
| 1871 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1872 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1873 |
+
"outcome_ptr": 1.0,
|
| 1874 |
+
"predicted_margin": 0.3980862785873208,
|
| 1875 |
+
"proposal_oracle_success": 1.0,
|
| 1876 |
+
"proposal_oracle_utility": 2.0,
|
| 1877 |
+
"selected_candidate_index": 0.0,
|
| 1878 |
+
"selected_success": 1.0,
|
| 1879 |
+
"selected_success_gain_over_base": 1.0,
|
| 1880 |
+
"selected_utility": 2.0,
|
| 1881 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1882 |
+
"selector_regret": 0.0,
|
| 1883 |
+
"success_selector_gap": 0.0,
|
| 1884 |
+
"success_support_gap": 0.0,
|
| 1885 |
+
"support_gap": 0.0,
|
| 1886 |
+
"tau": 0.38358192370540556
|
| 1887 |
+
},
|
| 1888 |
+
"440577711/train1": {
|
| 1889 |
+
"base_success": 0.0,
|
| 1890 |
+
"base_utility": 0.036152780055999756,
|
| 1891 |
+
"coverage": 0.0,
|
| 1892 |
+
"execute_generated": 0.0,
|
| 1893 |
+
"fallback_rate": 1.0,
|
| 1894 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1895 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1896 |
+
"outcome_ptr": 1.0,
|
| 1897 |
+
"predicted_margin": 0.36264223805353835,
|
| 1898 |
+
"proposal_oracle_success": 1.0,
|
| 1899 |
+
"proposal_oracle_utility": 2.0,
|
| 1900 |
+
"selected_candidate_index": 5.0,
|
| 1901 |
+
"selected_success": 0.0,
|
| 1902 |
+
"selected_success_gain_over_base": 0.0,
|
| 1903 |
+
"selected_utility": 0.036152780055999756,
|
| 1904 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1905 |
+
"selector_regret": 1.9638472199440002,
|
| 1906 |
+
"success_selector_gap": 1.0,
|
| 1907 |
+
"success_support_gap": 0.0,
|
| 1908 |
+
"support_gap": 0.0,
|
| 1909 |
+
"tau": 0.38358192370540556
|
| 1910 |
+
},
|
| 1911 |
+
"440577711/train2": {
|
| 1912 |
+
"base_success": 0.0,
|
| 1913 |
+
"base_utility": 0.036152780055999756,
|
| 1914 |
+
"coverage": 1.0,
|
| 1915 |
+
"execute_generated": 1.0,
|
| 1916 |
+
"fallback_rate": 0.0,
|
| 1917 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1918 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1919 |
+
"outcome_ptr": 1.0,
|
| 1920 |
+
"predicted_margin": 0.3980862785873208,
|
| 1921 |
+
"proposal_oracle_success": 1.0,
|
| 1922 |
+
"proposal_oracle_utility": 2.0,
|
| 1923 |
+
"selected_candidate_index": 0.0,
|
| 1924 |
+
"selected_success": 1.0,
|
| 1925 |
+
"selected_success_gain_over_base": 1.0,
|
| 1926 |
+
"selected_utility": 2.0,
|
| 1927 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1928 |
+
"selector_regret": 0.0,
|
| 1929 |
+
"success_selector_gap": 0.0,
|
| 1930 |
+
"success_support_gap": 0.0,
|
| 1931 |
+
"support_gap": 0.0,
|
| 1932 |
+
"tau": 0.38358192370540556
|
| 1933 |
+
},
|
| 1934 |
+
"441046872/train0": {
|
| 1935 |
+
"base_success": 0.0,
|
| 1936 |
+
"base_utility": 0.6999551653862,
|
| 1937 |
+
"coverage": 1.0,
|
| 1938 |
+
"execute_generated": 1.0,
|
| 1939 |
+
"fallback_rate": 0.0,
|
| 1940 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1941 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1942 |
+
"outcome_ptr": 0.0,
|
| 1943 |
+
"predicted_margin": 0.4063621528211626,
|
| 1944 |
+
"proposal_oracle_success": 0.0,
|
| 1945 |
+
"proposal_oracle_utility": 0.5148025155067444,
|
| 1946 |
+
"selected_candidate_index": 1.0,
|
| 1947 |
+
"selected_success": 0.0,
|
| 1948 |
+
"selected_success_gain_over_base": 0.0,
|
| 1949 |
+
"selected_utility": 0.2092108130455017,
|
| 1950 |
+
"selected_utility_gain_over_base": -0.49074435234069824,
|
| 1951 |
+
"selector_regret": 0.3055917024612427,
|
| 1952 |
+
"success_selector_gap": 0.0,
|
| 1953 |
+
"success_support_gap": 1.0,
|
| 1954 |
+
"support_gap": 1.4851974844932556,
|
| 1955 |
+
"tau": 0.38358192370540556
|
| 1956 |
+
},
|
| 1957 |
+
"441046872/train1": {
|
| 1958 |
+
"base_success": 0.0,
|
| 1959 |
+
"base_utility": 0.6999551653862,
|
| 1960 |
+
"coverage": 0.0,
|
| 1961 |
+
"execute_generated": 0.0,
|
| 1962 |
+
"fallback_rate": 1.0,
|
| 1963 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1964 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1965 |
+
"outcome_ptr": 1.0,
|
| 1966 |
+
"predicted_margin": 0.38358192370540556,
|
| 1967 |
+
"proposal_oracle_success": 0.0,
|
| 1968 |
+
"proposal_oracle_utility": 0.7233588695526123,
|
| 1969 |
+
"selected_candidate_index": 0.0,
|
| 1970 |
+
"selected_success": 0.0,
|
| 1971 |
+
"selected_success_gain_over_base": 0.0,
|
| 1972 |
+
"selected_utility": 0.6999551653862,
|
| 1973 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1974 |
+
"selector_regret": 0.023403704166412354,
|
| 1975 |
+
"success_selector_gap": 0.0,
|
| 1976 |
+
"success_support_gap": 1.0,
|
| 1977 |
+
"support_gap": 1.2766411304473877,
|
| 1978 |
+
"tau": 0.38358192370540556
|
| 1979 |
+
},
|
| 1980 |
+
"441046872/train2": {
|
| 1981 |
+
"base_success": 0.0,
|
| 1982 |
+
"base_utility": 0.6999551653862,
|
| 1983 |
+
"coverage": 1.0,
|
| 1984 |
+
"execute_generated": 1.0,
|
| 1985 |
+
"fallback_rate": 0.0,
|
| 1986 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1987 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1988 |
+
"outcome_ptr": 1.0,
|
| 1989 |
+
"predicted_margin": 0.38895499821801166,
|
| 1990 |
+
"proposal_oracle_success": 0.0,
|
| 1991 |
+
"proposal_oracle_utility": 0.7130289077758789,
|
| 1992 |
+
"selected_candidate_index": 0.0,
|
| 1993 |
+
"selected_success": 0.0,
|
| 1994 |
+
"selected_success_gain_over_base": 0.0,
|
| 1995 |
+
"selected_utility": 0.7130289077758789,
|
| 1996 |
+
"selected_utility_gain_over_base": 0.013073742389678955,
|
| 1997 |
+
"selector_regret": 0.0,
|
| 1998 |
+
"success_selector_gap": 0.0,
|
| 1999 |
+
"success_support_gap": 1.0,
|
| 2000 |
+
"support_gap": 1.286971092224121,
|
| 2001 |
+
"tau": 0.38358192370540556
|
| 2002 |
+
},
|
| 2003 |
+
"509430392/train0": {
|
| 2004 |
+
"base_success": 0.0,
|
| 2005 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2006 |
+
"coverage": 0.0,
|
| 2007 |
+
"execute_generated": 0.0,
|
| 2008 |
+
"fallback_rate": 1.0,
|
| 2009 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2010 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2011 |
+
"outcome_ptr": 1.0,
|
| 2012 |
+
"predicted_margin": 0.34339317826396043,
|
| 2013 |
+
"proposal_oracle_success": 1.0,
|
| 2014 |
+
"proposal_oracle_utility": 2.0,
|
| 2015 |
+
"selected_candidate_index": 1.0,
|
| 2016 |
+
"selected_success": 0.0,
|
| 2017 |
+
"selected_success_gain_over_base": 0.0,
|
| 2018 |
+
"selected_utility": 2.2351741790771484e-07,
|
| 2019 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2020 |
+
"selector_regret": 1.999999776482582,
|
| 2021 |
+
"success_selector_gap": 1.0,
|
| 2022 |
+
"success_support_gap": 0.0,
|
| 2023 |
+
"support_gap": 0.0,
|
| 2024 |
+
"tau": 0.38358192370540556
|
| 2025 |
+
},
|
| 2026 |
+
"509430392/train1": {
|
| 2027 |
+
"base_success": 0.0,
|
| 2028 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2029 |
+
"coverage": 0.0,
|
| 2030 |
+
"execute_generated": 0.0,
|
| 2031 |
+
"fallback_rate": 1.0,
|
| 2032 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2033 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2034 |
+
"outcome_ptr": 1.0,
|
| 2035 |
+
"predicted_margin": 0.3357431214829802,
|
| 2036 |
+
"proposal_oracle_success": 0.0,
|
| 2037 |
+
"proposal_oracle_utility": 6.164610385894775e-05,
|
| 2038 |
+
"selected_candidate_index": 5.0,
|
| 2039 |
+
"selected_success": 0.0,
|
| 2040 |
+
"selected_success_gain_over_base": 0.0,
|
| 2041 |
+
"selected_utility": 2.2351741790771484e-07,
|
| 2042 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2043 |
+
"selector_regret": 6.142258644104004e-05,
|
| 2044 |
+
"success_selector_gap": 0.0,
|
| 2045 |
+
"success_support_gap": 1.0,
|
| 2046 |
+
"support_gap": 1.999938353896141,
|
| 2047 |
+
"tau": 0.38358192370540556
|
| 2048 |
+
},
|
| 2049 |
+
"509430392/train2": {
|
| 2050 |
+
"base_success": 0.0,
|
| 2051 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2052 |
+
"coverage": 0.0,
|
| 2053 |
+
"execute_generated": 0.0,
|
| 2054 |
+
"fallback_rate": 1.0,
|
| 2055 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2056 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2057 |
+
"outcome_ptr": 1.0,
|
| 2058 |
+
"predicted_margin": 0.38358192370540556,
|
| 2059 |
+
"proposal_oracle_success": 0.0,
|
| 2060 |
+
"proposal_oracle_utility": 5.424022674560547e-06,
|
| 2061 |
+
"selected_candidate_index": 1.0,
|
| 2062 |
+
"selected_success": 0.0,
|
| 2063 |
+
"selected_success_gain_over_base": 0.0,
|
| 2064 |
+
"selected_utility": 2.2351741790771484e-07,
|
| 2065 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2066 |
+
"selector_regret": 5.200505256652832e-06,
|
| 2067 |
+
"success_selector_gap": 0.0,
|
| 2068 |
+
"success_support_gap": 1.0,
|
| 2069 |
+
"support_gap": 1.9999945759773254,
|
| 2070 |
+
"tau": 0.38358192370540556
|
| 2071 |
+
},
|
| 2072 |
+
"585904130/train0": {
|
| 2073 |
+
"base_success": 0.0,
|
| 2074 |
+
"base_utility": 0.18171554803848267,
|
| 2075 |
+
"coverage": 0.0,
|
| 2076 |
+
"execute_generated": 0.0,
|
| 2077 |
+
"fallback_rate": 1.0,
|
| 2078 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2079 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2080 |
+
"outcome_ptr": 1.0,
|
| 2081 |
+
"predicted_margin": 0.3414075616846885,
|
| 2082 |
+
"proposal_oracle_success": 1.0,
|
| 2083 |
+
"proposal_oracle_utility": 2.0,
|
| 2084 |
+
"selected_candidate_index": 6.0,
|
| 2085 |
+
"selected_success": 0.0,
|
| 2086 |
+
"selected_success_gain_over_base": 0.0,
|
| 2087 |
+
"selected_utility": 0.18171554803848267,
|
| 2088 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2089 |
+
"selector_regret": 1.8182844519615173,
|
| 2090 |
+
"success_selector_gap": 1.0,
|
| 2091 |
+
"success_support_gap": 0.0,
|
| 2092 |
+
"support_gap": 0.0,
|
| 2093 |
+
"tau": 0.38358192370540556
|
| 2094 |
+
},
|
| 2095 |
+
"585904130/train1": {
|
| 2096 |
+
"base_success": 0.0,
|
| 2097 |
+
"base_utility": 0.18171554803848267,
|
| 2098 |
+
"coverage": 0.0,
|
| 2099 |
+
"execute_generated": 0.0,
|
| 2100 |
+
"fallback_rate": 1.0,
|
| 2101 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2102 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2103 |
+
"outcome_ptr": 1.0,
|
| 2104 |
+
"predicted_margin": 0.30738451498868596,
|
| 2105 |
+
"proposal_oracle_success": 1.0,
|
| 2106 |
+
"proposal_oracle_utility": 2.0,
|
| 2107 |
+
"selected_candidate_index": 0.0,
|
| 2108 |
+
"selected_success": 0.0,
|
| 2109 |
+
"selected_success_gain_over_base": 0.0,
|
| 2110 |
+
"selected_utility": 0.18171554803848267,
|
| 2111 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2112 |
+
"selector_regret": 1.8182844519615173,
|
| 2113 |
+
"success_selector_gap": 1.0,
|
| 2114 |
+
"success_support_gap": 0.0,
|
| 2115 |
+
"support_gap": 0.0,
|
| 2116 |
+
"tau": 0.38358192370540556
|
| 2117 |
+
},
|
| 2118 |
+
"585904130/train2": {
|
| 2119 |
+
"base_success": 0.0,
|
| 2120 |
+
"base_utility": 0.18171554803848267,
|
| 2121 |
+
"coverage": 0.0,
|
| 2122 |
+
"execute_generated": 0.0,
|
| 2123 |
+
"fallback_rate": 1.0,
|
| 2124 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2125 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2126 |
+
"outcome_ptr": 1.0,
|
| 2127 |
+
"predicted_margin": 0.34003810503178633,
|
| 2128 |
+
"proposal_oracle_success": 1.0,
|
| 2129 |
+
"proposal_oracle_utility": 2.0,
|
| 2130 |
+
"selected_candidate_index": 1.0,
|
| 2131 |
+
"selected_success": 0.0,
|
| 2132 |
+
"selected_success_gain_over_base": 0.0,
|
| 2133 |
+
"selected_utility": 0.18171554803848267,
|
| 2134 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2135 |
+
"selector_regret": 1.8182844519615173,
|
| 2136 |
+
"success_selector_gap": 1.0,
|
| 2137 |
+
"success_support_gap": 0.0,
|
| 2138 |
+
"support_gap": 0.0,
|
| 2139 |
+
"tau": 0.38358192370540556
|
| 2140 |
+
},
|
| 2141 |
+
"608016290/train0": {
|
| 2142 |
+
"base_success": 0.0,
|
| 2143 |
+
"base_utility": 0.725701630115509,
|
| 2144 |
+
"coverage": 1.0,
|
| 2145 |
+
"execute_generated": 1.0,
|
| 2146 |
+
"fallback_rate": 0.0,
|
| 2147 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2148 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2149 |
+
"outcome_ptr": 1.0,
|
| 2150 |
+
"predicted_margin": 0.40035915866759314,
|
| 2151 |
+
"proposal_oracle_success": 1.0,
|
| 2152 |
+
"proposal_oracle_utility": 2.0,
|
| 2153 |
+
"selected_candidate_index": 0.0,
|
| 2154 |
+
"selected_success": 0.0,
|
| 2155 |
+
"selected_success_gain_over_base": 0.0,
|
| 2156 |
+
"selected_utility": 0.19838570058345795,
|
| 2157 |
+
"selected_utility_gain_over_base": -0.5273159295320511,
|
| 2158 |
+
"selector_regret": 1.801614299416542,
|
| 2159 |
+
"success_selector_gap": 1.0,
|
| 2160 |
+
"success_support_gap": 0.0,
|
| 2161 |
+
"support_gap": 0.0,
|
| 2162 |
+
"tau": 0.38358192370540556
|
| 2163 |
+
},
|
| 2164 |
+
"608016290/train1": {
|
| 2165 |
+
"base_success": 0.0,
|
| 2166 |
+
"base_utility": 0.725701630115509,
|
| 2167 |
+
"coverage": 0.0,
|
| 2168 |
+
"execute_generated": 0.0,
|
| 2169 |
+
"fallback_rate": 1.0,
|
| 2170 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2171 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2172 |
+
"outcome_ptr": 1.0,
|
| 2173 |
+
"predicted_margin": 0.38358192370540556,
|
| 2174 |
+
"proposal_oracle_success": 1.0,
|
| 2175 |
+
"proposal_oracle_utility": 2.0,
|
| 2176 |
+
"selected_candidate_index": 0.0,
|
| 2177 |
+
"selected_success": 0.0,
|
| 2178 |
+
"selected_success_gain_over_base": 0.0,
|
| 2179 |
+
"selected_utility": 0.725701630115509,
|
| 2180 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2181 |
+
"selector_regret": 1.274298369884491,
|
| 2182 |
+
"success_selector_gap": 1.0,
|
| 2183 |
+
"success_support_gap": 0.0,
|
| 2184 |
+
"support_gap": 0.0,
|
| 2185 |
+
"tau": 0.38358192370540556
|
| 2186 |
+
},
|
| 2187 |
+
"608016290/train2": {
|
| 2188 |
+
"base_success": 0.0,
|
| 2189 |
+
"base_utility": 0.725701630115509,
|
| 2190 |
+
"coverage": 0.0,
|
| 2191 |
+
"execute_generated": 0.0,
|
| 2192 |
+
"fallback_rate": 1.0,
|
| 2193 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2194 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2195 |
+
"outcome_ptr": 0.0,
|
| 2196 |
+
"predicted_margin": 0.3330356097435338,
|
| 2197 |
+
"proposal_oracle_success": 0.0,
|
| 2198 |
+
"proposal_oracle_utility": 0.6825780272483826,
|
| 2199 |
+
"selected_candidate_index": 7.0,
|
| 2200 |
+
"selected_success": 0.0,
|
| 2201 |
+
"selected_success_gain_over_base": 0.0,
|
| 2202 |
+
"selected_utility": 0.725701630115509,
|
| 2203 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2204 |
+
"selector_regret": 0.0,
|
| 2205 |
+
"success_selector_gap": 0.0,
|
| 2206 |
+
"success_support_gap": 1.0,
|
| 2207 |
+
"support_gap": 1.3174219727516174,
|
| 2208 |
+
"tau": 0.38358192370540556
|
| 2209 |
+
},
|
| 2210 |
+
"626486813/train0": {
|
| 2211 |
+
"base_success": 0.0,
|
| 2212 |
+
"base_utility": 0.00509834272088483,
|
| 2213 |
+
"coverage": 0.5,
|
| 2214 |
+
"execute_generated": 0.5,
|
| 2215 |
+
"fallback_rate": 0.5,
|
| 2216 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2217 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2218 |
+
"outcome_ptr": 1.0,
|
| 2219 |
+
"predicted_margin": 0.3657290522633051,
|
| 2220 |
+
"proposal_oracle_success": 0.0,
|
| 2221 |
+
"proposal_oracle_utility": 0.043898362666368484,
|
| 2222 |
+
"selected_candidate_index": 2.0,
|
| 2223 |
+
"selected_success": 0.0,
|
| 2224 |
+
"selected_success_gain_over_base": 0.0,
|
| 2225 |
+
"selected_utility": 0.018930166319478303,
|
| 2226 |
+
"selected_utility_gain_over_base": 0.013831823598593473,
|
| 2227 |
+
"selector_regret": 0.02496819634689018,
|
| 2228 |
+
"success_selector_gap": 0.0,
|
| 2229 |
+
"success_support_gap": 0.0,
|
| 2230 |
+
"support_gap": 0.12241578102111816,
|
| 2231 |
+
"tau": 0.38358192370540556
|
| 2232 |
+
},
|
| 2233 |
+
"626486813/train1": {
|
| 2234 |
+
"base_success": 0.0,
|
| 2235 |
+
"base_utility": 0.00509834272088483,
|
| 2236 |
+
"coverage": 0.5,
|
| 2237 |
+
"execute_generated": 0.5,
|
| 2238 |
+
"fallback_rate": 0.5,
|
| 2239 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2240 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2241 |
+
"outcome_ptr": 1.0,
|
| 2242 |
+
"predicted_margin": 0.3584816132025373,
|
| 2243 |
+
"proposal_oracle_success": 0.0,
|
| 2244 |
+
"proposal_oracle_utility": 0.030555277597159147,
|
| 2245 |
+
"selected_candidate_index": 3.0,
|
| 2246 |
+
"selected_success": 0.0,
|
| 2247 |
+
"selected_success_gain_over_base": 0.0,
|
| 2248 |
+
"selected_utility": 0.011202752881217748,
|
| 2249 |
+
"selected_utility_gain_over_base": 0.006104410160332918,
|
| 2250 |
+
"selector_regret": 0.0193525247159414,
|
| 2251 |
+
"success_selector_gap": 0.0,
|
| 2252 |
+
"success_support_gap": 0.0,
|
| 2253 |
+
"support_gap": 0.13502710359171033,
|
| 2254 |
+
"tau": 0.38358192370540556
|
| 2255 |
+
},
|
| 2256 |
+
"626486813/train2": {
|
| 2257 |
+
"base_success": 0.0,
|
| 2258 |
+
"base_utility": 0.00509834272088483,
|
| 2259 |
+
"coverage": 0.5,
|
| 2260 |
+
"execute_generated": 0.5,
|
| 2261 |
+
"fallback_rate": 0.5,
|
| 2262 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2263 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2264 |
+
"outcome_ptr": 1.0,
|
| 2265 |
+
"predicted_margin": 0.40458299674285936,
|
| 2266 |
+
"proposal_oracle_success": 0.0,
|
| 2267 |
+
"proposal_oracle_utility": 0.03856666944921017,
|
| 2268 |
+
"selected_candidate_index": 0.5,
|
| 2269 |
+
"selected_success": 0.0,
|
| 2270 |
+
"selected_success_gain_over_base": 0.0,
|
| 2271 |
+
"selected_utility": 0.012973218690603971,
|
| 2272 |
+
"selected_utility_gain_over_base": 0.007874875969719142,
|
| 2273 |
+
"selector_regret": 0.025593450758606195,
|
| 2274 |
+
"success_selector_gap": 0.0,
|
| 2275 |
+
"success_support_gap": 0.0,
|
| 2276 |
+
"support_gap": 0.1270157117396593,
|
| 2277 |
+
"tau": 0.38358192370540556
|
| 2278 |
+
},
|
| 2279 |
+
"636680137/train0": {
|
| 2280 |
+
"base_success": 0.0,
|
| 2281 |
+
"base_utility": 0.08313504606485367,
|
| 2282 |
+
"coverage": 0.0,
|
| 2283 |
+
"execute_generated": 0.0,
|
| 2284 |
+
"fallback_rate": 1.0,
|
| 2285 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2286 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2287 |
+
"outcome_ptr": 1.0,
|
| 2288 |
+
"predicted_margin": 0.33446532602731266,
|
| 2289 |
+
"proposal_oracle_success": 0.0,
|
| 2290 |
+
"proposal_oracle_utility": 0.08826130628585815,
|
| 2291 |
+
"selected_candidate_index": 6.0,
|
| 2292 |
+
"selected_success": 0.0,
|
| 2293 |
+
"selected_success_gain_over_base": 0.0,
|
| 2294 |
+
"selected_utility": 0.08313504606485367,
|
| 2295 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2296 |
+
"selector_regret": 0.005126260221004486,
|
| 2297 |
+
"success_selector_gap": 0.0,
|
| 2298 |
+
"success_support_gap": 0.0,
|
| 2299 |
+
"support_gap": 0.0823030173778534,
|
| 2300 |
+
"tau": 0.38358192370540556
|
| 2301 |
+
},
|
| 2302 |
+
"636680137/train1": {
|
| 2303 |
+
"base_success": 0.0,
|
| 2304 |
+
"base_utility": 0.08313504606485367,
|
| 2305 |
+
"coverage": 0.0,
|
| 2306 |
+
"execute_generated": 0.0,
|
| 2307 |
+
"fallback_rate": 1.0,
|
| 2308 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2309 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2310 |
+
"outcome_ptr": 0.0,
|
| 2311 |
+
"predicted_margin": 0.36221896637920825,
|
| 2312 |
+
"proposal_oracle_success": 0.0,
|
| 2313 |
+
"proposal_oracle_utility": 0.06741118431091309,
|
| 2314 |
+
"selected_candidate_index": 1.0,
|
| 2315 |
+
"selected_success": 0.0,
|
| 2316 |
+
"selected_success_gain_over_base": 0.0,
|
| 2317 |
+
"selected_utility": 0.08313504606485367,
|
| 2318 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2319 |
+
"selector_regret": 0.0,
|
| 2320 |
+
"success_selector_gap": 0.0,
|
| 2321 |
+
"success_support_gap": 0.0,
|
| 2322 |
+
"support_gap": 0.10315313935279846,
|
| 2323 |
+
"tau": 0.38358192370540556
|
| 2324 |
+
},
|
| 2325 |
+
"636680137/train2": {
|
| 2326 |
+
"base_success": 0.0,
|
| 2327 |
+
"base_utility": 0.08313504606485367,
|
| 2328 |
+
"coverage": 0.0,
|
| 2329 |
+
"execute_generated": 0.0,
|
| 2330 |
+
"fallback_rate": 1.0,
|
| 2331 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2332 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2333 |
+
"outcome_ptr": 0.0,
|
| 2334 |
+
"predicted_margin": 0.373318150625259,
|
| 2335 |
+
"proposal_oracle_success": 0.0,
|
| 2336 |
+
"proposal_oracle_utility": 0.0756516233086586,
|
| 2337 |
+
"selected_candidate_index": 5.0,
|
| 2338 |
+
"selected_success": 0.0,
|
| 2339 |
+
"selected_success_gain_over_base": 0.0,
|
| 2340 |
+
"selected_utility": 0.08313504606485367,
|
| 2341 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2342 |
+
"selector_regret": 0.0,
|
| 2343 |
+
"success_selector_gap": 0.0,
|
| 2344 |
+
"success_support_gap": 0.0,
|
| 2345 |
+
"support_gap": 0.09491270035505295,
|
| 2346 |
+
"tau": 0.38358192370540556
|
| 2347 |
+
},
|
| 2348 |
+
"655884605/train0": {
|
| 2349 |
+
"base_success": 0.0,
|
| 2350 |
+
"base_utility": 0.16300667822360992,
|
| 2351 |
+
"coverage": 0.0,
|
| 2352 |
+
"execute_generated": 0.0,
|
| 2353 |
+
"fallback_rate": 1.0,
|
| 2354 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2355 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2356 |
+
"outcome_ptr": 0.0,
|
| 2357 |
+
"predicted_margin": 0.25921502689335835,
|
| 2358 |
+
"proposal_oracle_success": 0.0,
|
| 2359 |
+
"proposal_oracle_utility": 0.13732868432998657,
|
| 2360 |
+
"selected_candidate_index": 0.0,
|
| 2361 |
+
"selected_success": 0.0,
|
| 2362 |
+
"selected_success_gain_over_base": 0.0,
|
| 2363 |
+
"selected_utility": 0.16300667822360992,
|
| 2364 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2365 |
+
"selector_regret": 0.0,
|
| 2366 |
+
"success_selector_gap": 0.0,
|
| 2367 |
+
"success_support_gap": 1.0,
|
| 2368 |
+
"support_gap": 1.8626713156700134,
|
| 2369 |
+
"tau": 0.38358192370540556
|
| 2370 |
+
},
|
| 2371 |
+
"655884605/train1": {
|
| 2372 |
+
"base_success": 0.0,
|
| 2373 |
+
"base_utility": 0.16300667822360992,
|
| 2374 |
+
"coverage": 1.0,
|
| 2375 |
+
"execute_generated": 1.0,
|
| 2376 |
+
"fallback_rate": 0.0,
|
| 2377 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2378 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2379 |
+
"outcome_ptr": 1.0,
|
| 2380 |
+
"predicted_margin": 0.3885110983494511,
|
| 2381 |
+
"proposal_oracle_success": 0.0,
|
| 2382 |
+
"proposal_oracle_utility": 0.1651531159877777,
|
| 2383 |
+
"selected_candidate_index": 0.0,
|
| 2384 |
+
"selected_success": 0.0,
|
| 2385 |
+
"selected_success_gain_over_base": 0.0,
|
| 2386 |
+
"selected_utility": 0.11596107482910156,
|
| 2387 |
+
"selected_utility_gain_over_base": -0.04704560339450836,
|
| 2388 |
+
"selector_regret": 0.04919204115867615,
|
| 2389 |
+
"success_selector_gap": 0.0,
|
| 2390 |
+
"success_support_gap": 1.0,
|
| 2391 |
+
"support_gap": 1.8348468840122223,
|
| 2392 |
+
"tau": 0.38358192370540556
|
| 2393 |
+
},
|
| 2394 |
+
"655884605/train2": {
|
| 2395 |
+
"base_success": 0.0,
|
| 2396 |
+
"base_utility": 0.16300667822360992,
|
| 2397 |
+
"coverage": 0.0,
|
| 2398 |
+
"execute_generated": 0.0,
|
| 2399 |
+
"fallback_rate": 1.0,
|
| 2400 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2401 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2402 |
+
"outcome_ptr": 1.0,
|
| 2403 |
+
"predicted_margin": 0.38358192370540556,
|
| 2404 |
+
"proposal_oracle_success": 0.0,
|
| 2405 |
+
"proposal_oracle_utility": 0.21447330713272095,
|
| 2406 |
+
"selected_candidate_index": 0.0,
|
| 2407 |
+
"selected_success": 0.0,
|
| 2408 |
+
"selected_success_gain_over_base": 0.0,
|
| 2409 |
+
"selected_utility": 0.16300667822360992,
|
| 2410 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2411 |
+
"selector_regret": 0.05146662890911102,
|
| 2412 |
+
"success_selector_gap": 0.0,
|
| 2413 |
+
"success_support_gap": 1.0,
|
| 2414 |
+
"support_gap": 1.785526692867279,
|
| 2415 |
+
"tau": 0.38358192370540556
|
| 2416 |
+
},
|
| 2417 |
+
"672328262/train0": {
|
| 2418 |
+
"base_success": 1.0,
|
| 2419 |
+
"base_utility": 2.0,
|
| 2420 |
+
"coverage": 0.0,
|
| 2421 |
+
"execute_generated": 0.0,
|
| 2422 |
+
"fallback_rate": 1.0,
|
| 2423 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2424 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2425 |
+
"outcome_ptr": 0.0,
|
| 2426 |
+
"predicted_margin": 0.3485165888228928,
|
| 2427 |
+
"proposal_oracle_success": 1.0,
|
| 2428 |
+
"proposal_oracle_utility": 2.0,
|
| 2429 |
+
"selected_candidate_index": 0.0,
|
| 2430 |
+
"selected_success": 1.0,
|
| 2431 |
+
"selected_success_gain_over_base": 0.0,
|
| 2432 |
+
"selected_utility": 2.0,
|
| 2433 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2434 |
+
"selector_regret": 0.0,
|
| 2435 |
+
"success_selector_gap": 0.0,
|
| 2436 |
+
"success_support_gap": 0.0,
|
| 2437 |
+
"support_gap": 0.0,
|
| 2438 |
+
"tau": 0.38358192370540556
|
| 2439 |
+
},
|
| 2440 |
+
"672328262/train1": {
|
| 2441 |
+
"base_success": 1.0,
|
| 2442 |
+
"base_utility": 2.0,
|
| 2443 |
+
"coverage": 0.0,
|
| 2444 |
+
"execute_generated": 0.0,
|
| 2445 |
+
"fallback_rate": 1.0,
|
| 2446 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2447 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2448 |
+
"outcome_ptr": 0.0,
|
| 2449 |
+
"predicted_margin": 0.32395056402489136,
|
| 2450 |
+
"proposal_oracle_success": 1.0,
|
| 2451 |
+
"proposal_oracle_utility": 2.0,
|
| 2452 |
+
"selected_candidate_index": 3.0,
|
| 2453 |
+
"selected_success": 1.0,
|
| 2454 |
+
"selected_success_gain_over_base": 0.0,
|
| 2455 |
+
"selected_utility": 2.0,
|
| 2456 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2457 |
+
"selector_regret": 0.0,
|
| 2458 |
+
"success_selector_gap": 0.0,
|
| 2459 |
+
"success_support_gap": 0.0,
|
| 2460 |
+
"support_gap": 0.0,
|
| 2461 |
+
"tau": 0.38358192370540556
|
| 2462 |
+
},
|
| 2463 |
+
"672328262/train2": {
|
| 2464 |
+
"base_success": 1.0,
|
| 2465 |
+
"base_utility": 2.0,
|
| 2466 |
+
"coverage": 0.0,
|
| 2467 |
+
"execute_generated": 0.0,
|
| 2468 |
+
"fallback_rate": 1.0,
|
| 2469 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2470 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2471 |
+
"outcome_ptr": 0.0,
|
| 2472 |
+
"predicted_margin": 0.37314194923808613,
|
| 2473 |
+
"proposal_oracle_success": 1.0,
|
| 2474 |
+
"proposal_oracle_utility": 2.0,
|
| 2475 |
+
"selected_candidate_index": 1.0,
|
| 2476 |
+
"selected_success": 1.0,
|
| 2477 |
+
"selected_success_gain_over_base": 0.0,
|
| 2478 |
+
"selected_utility": 2.0,
|
| 2479 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2480 |
+
"selector_regret": 0.0,
|
| 2481 |
+
"success_selector_gap": 0.0,
|
| 2482 |
+
"success_support_gap": 0.0,
|
| 2483 |
+
"support_gap": 0.0,
|
| 2484 |
+
"tau": 0.38358192370540556
|
| 2485 |
+
},
|
| 2486 |
+
"701667486/train0": {
|
| 2487 |
+
"base_success": 1.0,
|
| 2488 |
+
"base_utility": 2.0,
|
| 2489 |
+
"coverage": 0.0,
|
| 2490 |
+
"execute_generated": 0.0,
|
| 2491 |
+
"fallback_rate": 1.0,
|
| 2492 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2493 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2494 |
+
"outcome_ptr": 0.0,
|
| 2495 |
+
"predicted_margin": 0.36803098356509484,
|
| 2496 |
+
"proposal_oracle_success": 1.0,
|
| 2497 |
+
"proposal_oracle_utility": 2.0,
|
| 2498 |
+
"selected_candidate_index": 0.0,
|
| 2499 |
+
"selected_success": 1.0,
|
| 2500 |
+
"selected_success_gain_over_base": 0.0,
|
| 2501 |
+
"selected_utility": 2.0,
|
| 2502 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2503 |
+
"selector_regret": 0.0,
|
| 2504 |
+
"success_selector_gap": 0.0,
|
| 2505 |
+
"success_support_gap": 0.0,
|
| 2506 |
+
"support_gap": 0.0,
|
| 2507 |
+
"tau": 0.38358192370540556
|
| 2508 |
+
},
|
| 2509 |
+
"701667486/train1": {
|
| 2510 |
+
"base_success": 1.0,
|
| 2511 |
+
"base_utility": 2.0,
|
| 2512 |
+
"coverage": 1.0,
|
| 2513 |
+
"execute_generated": 1.0,
|
| 2514 |
+
"fallback_rate": 0.0,
|
| 2515 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2516 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2517 |
+
"outcome_ptr": 0.0,
|
| 2518 |
+
"predicted_margin": 0.38895499821801166,
|
| 2519 |
+
"proposal_oracle_success": 1.0,
|
| 2520 |
+
"proposal_oracle_utility": 2.0,
|
| 2521 |
+
"selected_candidate_index": 0.0,
|
| 2522 |
+
"selected_success": 1.0,
|
| 2523 |
+
"selected_success_gain_over_base": 0.0,
|
| 2524 |
+
"selected_utility": 2.0,
|
| 2525 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2526 |
+
"selector_regret": 0.0,
|
| 2527 |
+
"success_selector_gap": 0.0,
|
| 2528 |
+
"success_support_gap": 0.0,
|
| 2529 |
+
"support_gap": 0.0,
|
| 2530 |
+
"tau": 0.38358192370540556
|
| 2531 |
+
},
|
| 2532 |
+
"701667486/train2": {
|
| 2533 |
+
"base_success": 1.0,
|
| 2534 |
+
"base_utility": 2.0,
|
| 2535 |
+
"coverage": 1.0,
|
| 2536 |
+
"execute_generated": 1.0,
|
| 2537 |
+
"fallback_rate": 0.0,
|
| 2538 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2539 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2540 |
+
"outcome_ptr": 0.0,
|
| 2541 |
+
"predicted_margin": 0.3980862785873208,
|
| 2542 |
+
"proposal_oracle_success": 1.0,
|
| 2543 |
+
"proposal_oracle_utility": 2.0,
|
| 2544 |
+
"selected_candidate_index": 0.0,
|
| 2545 |
+
"selected_success": 1.0,
|
| 2546 |
+
"selected_success_gain_over_base": 0.0,
|
| 2547 |
+
"selected_utility": 2.0,
|
| 2548 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2549 |
+
"selector_regret": 0.0,
|
| 2550 |
+
"success_selector_gap": 0.0,
|
| 2551 |
+
"success_support_gap": 0.0,
|
| 2552 |
+
"support_gap": 0.0,
|
| 2553 |
+
"tau": 0.38358192370540556
|
| 2554 |
+
},
|
| 2555 |
+
"747260437/train0": {
|
| 2556 |
+
"base_success": 1.0,
|
| 2557 |
+
"base_utility": 2.0,
|
| 2558 |
+
"coverage": 0.0,
|
| 2559 |
+
"execute_generated": 0.0,
|
| 2560 |
+
"fallback_rate": 1.0,
|
| 2561 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2562 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2563 |
+
"outcome_ptr": 0.0,
|
| 2564 |
+
"predicted_margin": 0.2410858021363286,
|
| 2565 |
+
"proposal_oracle_success": 0.0,
|
| 2566 |
+
"proposal_oracle_utility": 0.10839563608169556,
|
| 2567 |
+
"selected_candidate_index": 0.0,
|
| 2568 |
+
"selected_success": 1.0,
|
| 2569 |
+
"selected_success_gain_over_base": 0.0,
|
| 2570 |
+
"selected_utility": 2.0,
|
| 2571 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2572 |
+
"selector_regret": 0.0,
|
| 2573 |
+
"success_selector_gap": 0.0,
|
| 2574 |
+
"success_support_gap": 0.0,
|
| 2575 |
+
"support_gap": 0.17026761174201965,
|
| 2576 |
+
"tau": 0.38358192370540556
|
| 2577 |
+
},
|
| 2578 |
+
"747260437/train1": {
|
| 2579 |
+
"base_success": 1.0,
|
| 2580 |
+
"base_utility": 2.0,
|
| 2581 |
+
"coverage": 1.0,
|
| 2582 |
+
"execute_generated": 1.0,
|
| 2583 |
+
"fallback_rate": 0.0,
|
| 2584 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2585 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2586 |
+
"outcome_ptr": 0.0,
|
| 2587 |
+
"predicted_margin": 0.40682662850481827,
|
| 2588 |
+
"proposal_oracle_success": 0.0,
|
| 2589 |
+
"proposal_oracle_utility": 0.05267423391342163,
|
| 2590 |
+
"selected_candidate_index": 0.0,
|
| 2591 |
+
"selected_success": 0.0,
|
| 2592 |
+
"selected_success_gain_over_base": -1.0,
|
| 2593 |
+
"selected_utility": 0.05267423391342163,
|
| 2594 |
+
"selected_utility_gain_over_base": -1.9473257660865784,
|
| 2595 |
+
"selector_regret": 0.0,
|
| 2596 |
+
"success_selector_gap": 0.0,
|
| 2597 |
+
"success_support_gap": 0.0,
|
| 2598 |
+
"support_gap": 0.22598901391029358,
|
| 2599 |
+
"tau": 0.38358192370540556
|
| 2600 |
+
},
|
| 2601 |
+
"747260437/train2": {
|
| 2602 |
+
"base_success": 1.0,
|
| 2603 |
+
"base_utility": 2.0,
|
| 2604 |
+
"coverage": 0.0,
|
| 2605 |
+
"execute_generated": 0.0,
|
| 2606 |
+
"fallback_rate": 1.0,
|
| 2607 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2608 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2609 |
+
"outcome_ptr": 0.0,
|
| 2610 |
+
"predicted_margin": 0.31915066590256386,
|
| 2611 |
+
"proposal_oracle_success": 0.0,
|
| 2612 |
+
"proposal_oracle_utility": 0.12510187923908234,
|
| 2613 |
+
"selected_candidate_index": 0.0,
|
| 2614 |
+
"selected_success": 1.0,
|
| 2615 |
+
"selected_success_gain_over_base": 0.0,
|
| 2616 |
+
"selected_utility": 2.0,
|
| 2617 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2618 |
+
"selector_regret": 0.0,
|
| 2619 |
+
"success_selector_gap": 0.0,
|
| 2620 |
+
"success_support_gap": 0.0,
|
| 2621 |
+
"support_gap": 0.15356136858463287,
|
| 2622 |
+
"tau": 0.38358192370540556
|
| 2623 |
+
},
|
| 2624 |
+
"750448296/train0": {
|
| 2625 |
+
"base_success": 0.0,
|
| 2626 |
+
"base_utility": 0.11759314934412639,
|
| 2627 |
+
"coverage": 0.6666666666666666,
|
| 2628 |
+
"execute_generated": 0.6666666666666666,
|
| 2629 |
+
"fallback_rate": 0.3333333333333333,
|
| 2630 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2631 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2632 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2633 |
+
"predicted_margin": 0.4657042217121026,
|
| 2634 |
+
"proposal_oracle_success": 0.3333333333333333,
|
| 2635 |
+
"proposal_oracle_utility": 0.7526603279014429,
|
| 2636 |
+
"selected_candidate_index": 4.0,
|
| 2637 |
+
"selected_success": 0.0,
|
| 2638 |
+
"selected_success_gain_over_base": 0.0,
|
| 2639 |
+
"selected_utility": 0.1115991473197937,
|
| 2640 |
+
"selected_utility_gain_over_base": -0.005994002024332683,
|
| 2641 |
+
"selector_regret": 0.6582622130711874,
|
| 2642 |
+
"success_selector_gap": 0.3333333333333333,
|
| 2643 |
+
"success_support_gap": 0.3333333333333333,
|
| 2644 |
+
"support_gap": 0.6553361676633358,
|
| 2645 |
+
"tau": 0.3835819237054056
|
| 2646 |
+
},
|
| 2647 |
+
"750448296/train1": {
|
| 2648 |
+
"base_success": 0.0,
|
| 2649 |
+
"base_utility": 0.11759314934412639,
|
| 2650 |
+
"coverage": 0.6666666666666666,
|
| 2651 |
+
"execute_generated": 0.6666666666666666,
|
| 2652 |
+
"fallback_rate": 0.3333333333333333,
|
| 2653 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2654 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2655 |
+
"outcome_ptr": 1.0,
|
| 2656 |
+
"predicted_margin": 0.45455990122271744,
|
| 2657 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2658 |
+
"proposal_oracle_utility": 1.3705032741030057,
|
| 2659 |
+
"selected_candidate_index": 2.3333333333333335,
|
| 2660 |
+
"selected_success": 0.3333333333333333,
|
| 2661 |
+
"selected_success_gain_over_base": 0.3333333333333333,
|
| 2662 |
+
"selected_utility": 0.717288845529159,
|
| 2663 |
+
"selected_utility_gain_over_base": 0.5996956961850325,
|
| 2664 |
+
"selector_regret": 0.6532144285738468,
|
| 2665 |
+
"success_selector_gap": 0.3333333333333333,
|
| 2666 |
+
"success_support_gap": 0.0,
|
| 2667 |
+
"support_gap": 0.03749322146177292,
|
| 2668 |
+
"tau": 0.3835819237054056
|
| 2669 |
+
},
|
| 2670 |
+
"750448296/train2": {
|
| 2671 |
+
"base_success": 0.0,
|
| 2672 |
+
"base_utility": 0.11759314934412639,
|
| 2673 |
+
"coverage": 0.3333333333333333,
|
| 2674 |
+
"execute_generated": 0.3333333333333333,
|
| 2675 |
+
"fallback_rate": 0.6666666666666666,
|
| 2676 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2677 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2678 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2679 |
+
"predicted_margin": 0.3758869142473165,
|
| 2680 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2681 |
+
"proposal_oracle_utility": 1.349846323331197,
|
| 2682 |
+
"selected_candidate_index": 2.0,
|
| 2683 |
+
"selected_success": 0.0,
|
| 2684 |
+
"selected_success_gain_over_base": 0.0,
|
| 2685 |
+
"selected_utility": 0.09376159558693568,
|
| 2686 |
+
"selected_utility_gain_over_base": -0.023831553757190704,
|
| 2687 |
+
"selector_regret": 1.2705709015329678,
|
| 2688 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2689 |
+
"success_support_gap": 0.0,
|
| 2690 |
+
"support_gap": 0.05815017223358154,
|
| 2691 |
+
"tau": 0.3835819237054056
|
| 2692 |
+
},
|
| 2693 |
+
"767747424/train0": {
|
| 2694 |
+
"base_success": 0.25,
|
| 2695 |
+
"base_utility": 0.5731993420049548,
|
| 2696 |
+
"coverage": 0.25,
|
| 2697 |
+
"execute_generated": 0.25,
|
| 2698 |
+
"fallback_rate": 0.75,
|
| 2699 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2700 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2701 |
+
"outcome_ptr": 0.5,
|
| 2702 |
+
"predicted_margin": 0.360797178408953,
|
| 2703 |
+
"proposal_oracle_success": 0.5,
|
| 2704 |
+
"proposal_oracle_utility": 1.0424291878007352,
|
| 2705 |
+
"selected_candidate_index": 3.25,
|
| 2706 |
+
"selected_success": 0.25,
|
| 2707 |
+
"selected_success_gain_over_base": 0.0,
|
| 2708 |
+
"selected_utility": 0.539273236412555,
|
| 2709 |
+
"selected_utility_gain_over_base": -0.033926105592399836,
|
| 2710 |
+
"selector_regret": 0.5118862283416092,
|
| 2711 |
+
"success_selector_gap": 0.25,
|
| 2712 |
+
"success_support_gap": 0.0,
|
| 2713 |
+
"support_gap": 0.06562284985557199,
|
| 2714 |
+
"tau": 0.38358192370540556
|
| 2715 |
+
},
|
| 2716 |
+
"767747424/train1": {
|
| 2717 |
+
"base_success": 0.25,
|
| 2718 |
+
"base_utility": 0.5731993420049548,
|
| 2719 |
+
"coverage": 0.25,
|
| 2720 |
+
"execute_generated": 0.25,
|
| 2721 |
+
"fallback_rate": 0.75,
|
| 2722 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2723 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2724 |
+
"outcome_ptr": 0.25,
|
| 2725 |
+
"predicted_margin": 0.31904485971917734,
|
| 2726 |
+
"proposal_oracle_success": 0.25,
|
| 2727 |
+
"proposal_oracle_utility": 0.5951075805351138,
|
| 2728 |
+
"selected_candidate_index": 1.0,
|
| 2729 |
+
"selected_success": 0.25,
|
| 2730 |
+
"selected_success_gain_over_base": 0.0,
|
| 2731 |
+
"selected_utility": 0.5592513466253877,
|
| 2732 |
+
"selected_utility_gain_over_base": -0.013947995379567146,
|
| 2733 |
+
"selector_regret": 0.03869148716330528,
|
| 2734 |
+
"success_selector_gap": 0.0,
|
| 2735 |
+
"success_support_gap": 0.25,
|
| 2736 |
+
"support_gap": 0.5129444571211934,
|
| 2737 |
+
"tau": 0.38358192370540556
|
| 2738 |
+
},
|
| 2739 |
+
"767747424/train2": {
|
| 2740 |
+
"base_success": 0.25,
|
| 2741 |
+
"base_utility": 0.5731993420049548,
|
| 2742 |
+
"coverage": 0.0,
|
| 2743 |
+
"execute_generated": 0.0,
|
| 2744 |
+
"fallback_rate": 1.0,
|
| 2745 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2746 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2747 |
+
"outcome_ptr": 0.5,
|
| 2748 |
+
"predicted_margin": 0.21673854625665817,
|
| 2749 |
+
"proposal_oracle_success": 0.25,
|
| 2750 |
+
"proposal_oracle_utility": 0.6134321661666036,
|
| 2751 |
+
"selected_candidate_index": 1.0,
|
| 2752 |
+
"selected_success": 0.25,
|
| 2753 |
+
"selected_success_gain_over_base": 0.0,
|
| 2754 |
+
"selected_utility": 0.5731993420049548,
|
| 2755 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2756 |
+
"selector_regret": 0.04225692339241505,
|
| 2757 |
+
"success_selector_gap": 0.0,
|
| 2758 |
+
"success_support_gap": 0.25,
|
| 2759 |
+
"support_gap": 0.49461987148970366,
|
| 2760 |
+
"tau": 0.38358192370540556
|
| 2761 |
+
}
|
| 2762 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/metrics_by_task.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"LiftPegUpright-v1": {
|
| 3 |
+
"base_success": 0.2,
|
| 4 |
+
"base_utility": 0.9498705387115478,
|
| 5 |
+
"coverage": 0.4666666666666667,
|
| 6 |
+
"execute_generated": 0.4666666666666667,
|
| 7 |
+
"fallback_rate": 0.5333333333333333,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.4666666666666667,
|
| 11 |
+
"predicted_margin": 0.38130294013187815,
|
| 12 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 13 |
+
"proposal_oracle_utility": 1.2244940986235937,
|
| 14 |
+
"selected_candidate_index": 0.8,
|
| 15 |
+
"selected_success": 0.13333333333333333,
|
| 16 |
+
"selected_success_gain_over_base": -0.06666666666666667,
|
| 17 |
+
"selected_utility": 0.7437657197316487,
|
| 18 |
+
"selected_utility_gain_over_base": -0.2061048189798991,
|
| 19 |
+
"selector_regret": 0.5706221928199132,
|
| 20 |
+
"success_selector_gap": 0.4,
|
| 21 |
+
"success_support_gap": 0.5333333333333333,
|
| 22 |
+
"support_gap": 0.7755059013764064,
|
| 23 |
+
"tau": 0.3835819237054056
|
| 24 |
+
},
|
| 25 |
+
"PickCube-v1": {
|
| 26 |
+
"base_success": 0.0,
|
| 27 |
+
"base_utility": 0.5839591026306152,
|
| 28 |
+
"coverage": 1.0,
|
| 29 |
+
"execute_generated": 1.0,
|
| 30 |
+
"fallback_rate": 0.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.5297277370838114,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.13425676027933756,
|
| 37 |
+
"selected_candidate_index": 3.6666666666666665,
|
| 38 |
+
"selected_success": 0.0,
|
| 39 |
+
"selected_success_gain_over_base": 0.0,
|
| 40 |
+
"selected_utility": 0.10052394618590672,
|
| 41 |
+
"selected_utility_gain_over_base": -0.4834351564447085,
|
| 42 |
+
"selector_regret": 0.03373281409343084,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.8657432397206624,
|
| 46 |
+
"tau": 0.3835819237054056
|
| 47 |
+
},
|
| 48 |
+
"PullCube-v1": {
|
| 49 |
+
"base_success": 0.36,
|
| 50 |
+
"base_utility": 0.7751704612234608,
|
| 51 |
+
"coverage": 0.32,
|
| 52 |
+
"execute_generated": 0.32,
|
| 53 |
+
"fallback_rate": 0.68,
|
| 54 |
+
"hidden_chart_oracle_success": 0.52,
|
| 55 |
+
"hidden_chart_oracle_utility": 1.1467878860235214,
|
| 56 |
+
"outcome_ptr": 0.44,
|
| 57 |
+
"predicted_margin": 0.3456744577129766,
|
| 58 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 59 |
+
"proposal_oracle_utility": 0.9816135169876119,
|
| 60 |
+
"selected_candidate_index": 2.2666666666666666,
|
| 61 |
+
"selected_success": 0.3333333333333333,
|
| 62 |
+
"selected_success_gain_over_base": -0.02666666666666667,
|
| 63 |
+
"selected_utility": 0.7155966088124034,
|
| 64 |
+
"selected_utility_gain_over_base": -0.05957385241105738,
|
| 65 |
+
"selector_regret": 0.397877087958364,
|
| 66 |
+
"success_selector_gap": 0.2,
|
| 67 |
+
"success_support_gap": 0.09333333333333334,
|
| 68 |
+
"support_gap": 0.23527305972451965,
|
| 69 |
+
"tau": 0.38358192370540595
|
| 70 |
+
},
|
| 71 |
+
"PushCube-v1": {
|
| 72 |
+
"base_success": 0.16666666666666666,
|
| 73 |
+
"base_utility": 0.3924041787783305,
|
| 74 |
+
"coverage": 0.6111111111111112,
|
| 75 |
+
"execute_generated": 0.6111111111111112,
|
| 76 |
+
"fallback_rate": 0.3888888888888889,
|
| 77 |
+
"hidden_chart_oracle_success": 0.8333333333333334,
|
| 78 |
+
"hidden_chart_oracle_utility": 1.7015800600250561,
|
| 79 |
+
"outcome_ptr": 0.7777777777777778,
|
| 80 |
+
"predicted_margin": 0.3812307027896631,
|
| 81 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 82 |
+
"proposal_oracle_utility": 1.365773618221283,
|
| 83 |
+
"selected_candidate_index": 2.0555555555555554,
|
| 84 |
+
"selected_success": 0.2777777777777778,
|
| 85 |
+
"selected_success_gain_over_base": 0.1111111111111111,
|
| 86 |
+
"selected_utility": 0.6125162500474188,
|
| 87 |
+
"selected_utility_gain_over_base": 0.22011207126908833,
|
| 88 |
+
"selector_regret": 0.7532573681738641,
|
| 89 |
+
"success_selector_gap": 0.3888888888888889,
|
| 90 |
+
"success_support_gap": 0.3333333333333333,
|
| 91 |
+
"support_gap": 0.634226381778717,
|
| 92 |
+
"tau": 0.38358192370540567
|
| 93 |
+
},
|
| 94 |
+
"StackCube-v1": {
|
| 95 |
+
"base_success": 0.2727272727272727,
|
| 96 |
+
"base_utility": 0.7763947045261209,
|
| 97 |
+
"coverage": 0.6363636363636364,
|
| 98 |
+
"execute_generated": 0.6363636363636364,
|
| 99 |
+
"fallback_rate": 0.36363636363636365,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 0.5757575757575758,
|
| 103 |
+
"predicted_margin": 0.3652676517012828,
|
| 104 |
+
"proposal_oracle_success": 0.45454545454545453,
|
| 105 |
+
"proposal_oracle_utility": 1.0546941955884297,
|
| 106 |
+
"selected_candidate_index": 1.5757575757575757,
|
| 107 |
+
"selected_success": 0.21212121212121213,
|
| 108 |
+
"selected_success_gain_over_base": -0.06060606060606061,
|
| 109 |
+
"selected_utility": 0.6180817195863435,
|
| 110 |
+
"selected_utility_gain_over_base": -0.1583129849397775,
|
| 111 |
+
"selector_regret": 0.4407263190457315,
|
| 112 |
+
"success_selector_gap": 0.24242424242424243,
|
| 113 |
+
"success_support_gap": 0.5454545454545454,
|
| 114 |
+
"support_gap": 0.9453058044115702,
|
| 115 |
+
"tau": 0.38358192370540545
|
| 116 |
+
}
|
| 117 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/report.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Nonlinear Train-Calibrated CTT Selector
|
| 2 |
+
|
| 3 |
+
Calibration rows: `432`
|
| 4 |
+
Fit rows: `277`
|
| 5 |
+
Selection rows: `155`
|
| 6 |
+
Eval rows: `144`
|
| 7 |
+
Selected model: `hgb_classifier`
|
| 8 |
+
Selected params: `{"l2_regularization": 0.01, "learning_rate": 0.05, "max_iter": 40, "max_leaf_nodes": 7, "random_state": 0}`
|
| 9 |
+
Tau: `0.383582`
|
| 10 |
+
Feature set: `basic`
|
| 11 |
+
Target: `success`
|
| 12 |
+
|
| 13 |
+
The model is fit on calibration-fit rows, and model/tau are selected on held-out calibration-selection rows only. Eval outcomes are used only for reporting.
|
| 14 |
+
|
| 15 |
+
| Split | Coverage | Fallback | Base success | Selected success | Proposal oracle | OutcomePTR | Success support gap | Success selector gap |
|
| 16 |
+
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 17 |
+
| fit | 0.3791 | 0.6209 | 0.2780 | 0.3394 | 0.4910 | 0.4838 | 0.2058 | 0.2094 |
|
| 18 |
+
| selection | 0.4645 | 0.5355 | 0.2774 | 0.3419 | 0.4387 | 0.5032 | 0.2774 | 0.1484 |
|
| 19 |
+
| eval | 0.4583 | 0.5417 | 0.2917 | 0.2708 | 0.4792 | 0.5069 | 0.2917 | 0.2500 |
|
| 20 |
+
|
| 21 |
+
This is a train-calibrated selector diagnostic over already measured candidates, not a new rollout.
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/split_hash.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_target_index": {
|
| 3 |
+
"content_hash": "67f7b4a692f7c7e71da24378dc71e3399c5d35afc14c494869eba6087b765c42",
|
| 4 |
+
"retrieval_index_allowed": true,
|
| 5 |
+
"split": "train",
|
| 6 |
+
"split_hash": "867a94a1c67686c082765671a7bf8d74a9d633085e1b2619c83197c60bf58372"
|
| 7 |
+
},
|
| 8 |
+
"eval_target_index": {
|
| 9 |
+
"content_hash": "0c38d73dc9bc4ab756e12006671b5d12f1a23358b281e54b3f6a9ae3cbf6e9af",
|
| 10 |
+
"retrieval_index_allowed": false,
|
| 11 |
+
"split": "test",
|
| 12 |
+
"split_hash": "84151df9e88c219b76751677558cc5bbbc19082bf358cea7330158e9e403e25f"
|
| 13 |
+
}
|
| 14 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/table.tex
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
% Auto-generated by scripts/eval_nonlinear_dominance_selector.py
|
| 2 |
+
\begin{tabular}{lrrrrrrrr}
|
| 3 |
+
\toprule
|
| 4 |
+
Rows & Coverage & Fallback & Base succ. & Selected succ. & Oracle succ. & OutcomePTR & Succ. support gap & Succ. selector gap \\
|
| 5 |
+
\midrule
|
| 6 |
+
144 & 0.4583 & 0.5417 & 0.2917 & 0.2708 & 0.4792 & 0.5069 & 0.2917 & 0.2500 \\
|
| 7 |
+
\bottomrule
|
| 8 |
+
\end{tabular}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_basic_success_envclip_train_to_test/train.log
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
trained nonlinear dominance selector on calibration-fit rows only
|
| 2 |
+
selected_model_type=hgb_classifier
|
| 3 |
+
selected_model_params={"l2_regularization": 0.01, "learning_rate": 0.05, "max_iter": 40, "max_leaf_nodes": 7, "random_state": 0}
|
| 4 |
+
tau=0.383582
|
| 5 |
+
calibration_input=runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/command.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
python scripts/eval_nonlinear_dominance_selector.py --calibration-input runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json --calibration-target-index data/cil_charts_rgb_refs/train/index.json --eval-input runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json --eval-target-index data/cil_charts_rgb_refs/test/index.json --checkpoint-template runs/ctt_residual_base_context_obs_seed{seed}/model.pt --out-dir runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test --feature-set context_tangent --target positive_margin --k 8 --bootstrap-samples 1000
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/config.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bootstrap_samples: 1000
|
| 2 |
+
calibration_input: runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
calibration_target_index: data/cil_charts_rgb_refs/train/index.json
|
| 4 |
+
checkpoint_template: runs/ctt_residual_base_context_obs_seed{seed}/model.pt
|
| 5 |
+
eval_input: runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 6 |
+
eval_target_index: data/cil_charts_rgb_refs/test/index.json
|
| 7 |
+
feature_set: context_tangent
|
| 8 |
+
k: 8
|
| 9 |
+
model_types: hgb_classifier,hgb_regressor,rf_regressor
|
| 10 |
+
out_dir: runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test
|
| 11 |
+
seed: 0
|
| 12 |
+
selection_frac: 0.35
|
| 13 |
+
target: positive_margin
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/data_hash.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_input": "06375099001e740a377c402e34b77bf6974be3dc2a468974340ce41eb1b487f0",
|
| 3 |
+
"calibration_target_index": "67973c50072aa87a3b97533b6292b08a8b4d88a95571dc22e91b6e8fd19e0d85",
|
| 4 |
+
"eval_input": "57df43ff4802379dfd60b5209d5a04028d721256406685decededccdbec0d49c",
|
| 5 |
+
"eval_target_index": "dee1b5225485df6624747dd4c5074bcf514685b54017d05e698d2051638fbf36"
|
| 6 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/eval.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
selected model/tau on held-out calibration-selection rows; evaluated on held-out measured rollout rows
|
| 2 |
+
eval_input=runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
num_eval_rows=144
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/git_hash.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
14e81292e2004925f81e0bb4810f6f144bfd87b7
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/metrics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/metrics_by_seed.json
ADDED
|
@@ -0,0 +1,2762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"1073161778/train0": {
|
| 3 |
+
"base_success": 1.0,
|
| 4 |
+
"base_utility": 2.0,
|
| 5 |
+
"coverage": 1.0,
|
| 6 |
+
"execute_generated": 1.0,
|
| 7 |
+
"fallback_rate": 0.0,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.0,
|
| 11 |
+
"predicted_margin": 0.4346372534889307,
|
| 12 |
+
"proposal_oracle_success": 1.0,
|
| 13 |
+
"proposal_oracle_utility": 2.0,
|
| 14 |
+
"selected_candidate_index": 5.0,
|
| 15 |
+
"selected_success": 0.0,
|
| 16 |
+
"selected_success_gain_over_base": -1.0,
|
| 17 |
+
"selected_utility": 0.6875576972961426,
|
| 18 |
+
"selected_utility_gain_over_base": -1.3124423027038574,
|
| 19 |
+
"selector_regret": 1.3124423027038574,
|
| 20 |
+
"success_selector_gap": 1.0,
|
| 21 |
+
"success_support_gap": 0.0,
|
| 22 |
+
"support_gap": 0.0,
|
| 23 |
+
"tau": 0.3922077221501807
|
| 24 |
+
},
|
| 25 |
+
"1073161778/train1": {
|
| 26 |
+
"base_success": 1.0,
|
| 27 |
+
"base_utility": 2.0,
|
| 28 |
+
"coverage": 1.0,
|
| 29 |
+
"execute_generated": 1.0,
|
| 30 |
+
"fallback_rate": 0.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.5057988327780565,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.7071996331214905,
|
| 37 |
+
"selected_candidate_index": 4.0,
|
| 38 |
+
"selected_success": 0.0,
|
| 39 |
+
"selected_success_gain_over_base": -1.0,
|
| 40 |
+
"selected_utility": 0.6947963237762451,
|
| 41 |
+
"selected_utility_gain_over_base": -1.3052036762237549,
|
| 42 |
+
"selector_regret": 0.012403309345245361,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.2928003668785095,
|
| 46 |
+
"tau": 0.3922077221501807
|
| 47 |
+
},
|
| 48 |
+
"1073161778/train2": {
|
| 49 |
+
"base_success": 1.0,
|
| 50 |
+
"base_utility": 2.0,
|
| 51 |
+
"coverage": 1.0,
|
| 52 |
+
"execute_generated": 1.0,
|
| 53 |
+
"fallback_rate": 0.0,
|
| 54 |
+
"hidden_chart_oracle_success": 1.0,
|
| 55 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 56 |
+
"outcome_ptr": 0.0,
|
| 57 |
+
"predicted_margin": 0.5851475971374662,
|
| 58 |
+
"proposal_oracle_success": 1.0,
|
| 59 |
+
"proposal_oracle_utility": 2.0,
|
| 60 |
+
"selected_candidate_index": 7.0,
|
| 61 |
+
"selected_success": 0.0,
|
| 62 |
+
"selected_success_gain_over_base": -1.0,
|
| 63 |
+
"selected_utility": 0.717010498046875,
|
| 64 |
+
"selected_utility_gain_over_base": -1.282989501953125,
|
| 65 |
+
"selector_regret": 1.282989501953125,
|
| 66 |
+
"success_selector_gap": 1.0,
|
| 67 |
+
"success_support_gap": 0.0,
|
| 68 |
+
"support_gap": 0.0,
|
| 69 |
+
"tau": 0.3922077221501807
|
| 70 |
+
},
|
| 71 |
+
"1113371261/train0": {
|
| 72 |
+
"base_success": 0.0,
|
| 73 |
+
"base_utility": 0.15842342376708984,
|
| 74 |
+
"coverage": 0.0,
|
| 75 |
+
"execute_generated": 0.0,
|
| 76 |
+
"fallback_rate": 1.0,
|
| 77 |
+
"hidden_chart_oracle_success": 1.0,
|
| 78 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 79 |
+
"outcome_ptr": 0.0,
|
| 80 |
+
"predicted_margin": 0.11486633896600597,
|
| 81 |
+
"proposal_oracle_success": 0.0,
|
| 82 |
+
"proposal_oracle_utility": 0.10274861752986908,
|
| 83 |
+
"selected_candidate_index": 2.0,
|
| 84 |
+
"selected_success": 0.0,
|
| 85 |
+
"selected_success_gain_over_base": 0.0,
|
| 86 |
+
"selected_utility": 0.15842342376708984,
|
| 87 |
+
"selected_utility_gain_over_base": 0.0,
|
| 88 |
+
"selector_regret": 0.0,
|
| 89 |
+
"success_selector_gap": 0.0,
|
| 90 |
+
"success_support_gap": 1.0,
|
| 91 |
+
"support_gap": 1.897251382470131,
|
| 92 |
+
"tau": 0.3922077221501807
|
| 93 |
+
},
|
| 94 |
+
"1113371261/train1": {
|
| 95 |
+
"base_success": 0.0,
|
| 96 |
+
"base_utility": 0.15842342376708984,
|
| 97 |
+
"coverage": 0.0,
|
| 98 |
+
"execute_generated": 0.0,
|
| 99 |
+
"fallback_rate": 1.0,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 1.0,
|
| 103 |
+
"predicted_margin": 0.20333016356404546,
|
| 104 |
+
"proposal_oracle_success": 0.0,
|
| 105 |
+
"proposal_oracle_utility": 0.18093222379684448,
|
| 106 |
+
"selected_candidate_index": 1.0,
|
| 107 |
+
"selected_success": 0.0,
|
| 108 |
+
"selected_success_gain_over_base": 0.0,
|
| 109 |
+
"selected_utility": 0.15842342376708984,
|
| 110 |
+
"selected_utility_gain_over_base": 0.0,
|
| 111 |
+
"selector_regret": 0.02250880002975464,
|
| 112 |
+
"success_selector_gap": 0.0,
|
| 113 |
+
"success_support_gap": 1.0,
|
| 114 |
+
"support_gap": 1.8190677762031555,
|
| 115 |
+
"tau": 0.3922077221501807
|
| 116 |
+
},
|
| 117 |
+
"1113371261/train2": {
|
| 118 |
+
"base_success": 0.0,
|
| 119 |
+
"base_utility": 0.15842342376708984,
|
| 120 |
+
"coverage": 0.0,
|
| 121 |
+
"execute_generated": 0.0,
|
| 122 |
+
"fallback_rate": 1.0,
|
| 123 |
+
"hidden_chart_oracle_success": 1.0,
|
| 124 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 125 |
+
"outcome_ptr": 1.0,
|
| 126 |
+
"predicted_margin": 0.17854824691390672,
|
| 127 |
+
"proposal_oracle_success": 0.0,
|
| 128 |
+
"proposal_oracle_utility": 0.19527167081832886,
|
| 129 |
+
"selected_candidate_index": 7.0,
|
| 130 |
+
"selected_success": 0.0,
|
| 131 |
+
"selected_success_gain_over_base": 0.0,
|
| 132 |
+
"selected_utility": 0.15842342376708984,
|
| 133 |
+
"selected_utility_gain_over_base": 0.0,
|
| 134 |
+
"selector_regret": 0.036848247051239014,
|
| 135 |
+
"success_selector_gap": 0.0,
|
| 136 |
+
"success_support_gap": 1.0,
|
| 137 |
+
"support_gap": 1.8047283291816711,
|
| 138 |
+
"tau": 0.3922077221501807
|
| 139 |
+
},
|
| 140 |
+
"1151410346/train0": {
|
| 141 |
+
"base_success": 0.0,
|
| 142 |
+
"base_utility": 0.2260012924671173,
|
| 143 |
+
"coverage": 0.0,
|
| 144 |
+
"execute_generated": 0.0,
|
| 145 |
+
"fallback_rate": 1.0,
|
| 146 |
+
"hidden_chart_oracle_success": 1.0,
|
| 147 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 148 |
+
"outcome_ptr": 1.0,
|
| 149 |
+
"predicted_margin": 0.22402749902483893,
|
| 150 |
+
"proposal_oracle_success": 0.0,
|
| 151 |
+
"proposal_oracle_utility": 0.8663521409034729,
|
| 152 |
+
"selected_candidate_index": 5.0,
|
| 153 |
+
"selected_success": 0.0,
|
| 154 |
+
"selected_success_gain_over_base": 0.0,
|
| 155 |
+
"selected_utility": 0.2260012924671173,
|
| 156 |
+
"selected_utility_gain_over_base": 0.0,
|
| 157 |
+
"selector_regret": 0.6403508484363556,
|
| 158 |
+
"success_selector_gap": 0.0,
|
| 159 |
+
"success_support_gap": 1.0,
|
| 160 |
+
"support_gap": 1.133647859096527,
|
| 161 |
+
"tau": 0.3922077221501807
|
| 162 |
+
},
|
| 163 |
+
"1151410346/train1": {
|
| 164 |
+
"base_success": 0.0,
|
| 165 |
+
"base_utility": 0.2260012924671173,
|
| 166 |
+
"coverage": 0.0,
|
| 167 |
+
"execute_generated": 0.0,
|
| 168 |
+
"fallback_rate": 1.0,
|
| 169 |
+
"hidden_chart_oracle_success": 1.0,
|
| 170 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 171 |
+
"outcome_ptr": 1.0,
|
| 172 |
+
"predicted_margin": 0.35019271094143994,
|
| 173 |
+
"proposal_oracle_success": 0.0,
|
| 174 |
+
"proposal_oracle_utility": 0.8138919472694397,
|
| 175 |
+
"selected_candidate_index": 6.0,
|
| 176 |
+
"selected_success": 0.0,
|
| 177 |
+
"selected_success_gain_over_base": 0.0,
|
| 178 |
+
"selected_utility": 0.2260012924671173,
|
| 179 |
+
"selected_utility_gain_over_base": 0.0,
|
| 180 |
+
"selector_regret": 0.5878906548023224,
|
| 181 |
+
"success_selector_gap": 0.0,
|
| 182 |
+
"success_support_gap": 1.0,
|
| 183 |
+
"support_gap": 1.1861080527305603,
|
| 184 |
+
"tau": 0.3922077221501807
|
| 185 |
+
},
|
| 186 |
+
"1151410346/train2": {
|
| 187 |
+
"base_success": 0.0,
|
| 188 |
+
"base_utility": 0.2260012924671173,
|
| 189 |
+
"coverage": 0.0,
|
| 190 |
+
"execute_generated": 0.0,
|
| 191 |
+
"fallback_rate": 1.0,
|
| 192 |
+
"hidden_chart_oracle_success": 1.0,
|
| 193 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 194 |
+
"outcome_ptr": 0.0,
|
| 195 |
+
"predicted_margin": 0.29716110320145944,
|
| 196 |
+
"proposal_oracle_success": 0.0,
|
| 197 |
+
"proposal_oracle_utility": 0.21912741661071777,
|
| 198 |
+
"selected_candidate_index": 2.0,
|
| 199 |
+
"selected_success": 0.0,
|
| 200 |
+
"selected_success_gain_over_base": 0.0,
|
| 201 |
+
"selected_utility": 0.2260012924671173,
|
| 202 |
+
"selected_utility_gain_over_base": 0.0,
|
| 203 |
+
"selector_regret": 0.0,
|
| 204 |
+
"success_selector_gap": 0.0,
|
| 205 |
+
"success_support_gap": 1.0,
|
| 206 |
+
"support_gap": 1.7808725833892822,
|
| 207 |
+
"tau": 0.3922077221501807
|
| 208 |
+
},
|
| 209 |
+
"1261930456/train0": {
|
| 210 |
+
"base_success": 1.0,
|
| 211 |
+
"base_utility": 2.0,
|
| 212 |
+
"coverage": 1.0,
|
| 213 |
+
"execute_generated": 1.0,
|
| 214 |
+
"fallback_rate": 0.0,
|
| 215 |
+
"hidden_chart_oracle_success": 1.0,
|
| 216 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 217 |
+
"outcome_ptr": 0.0,
|
| 218 |
+
"predicted_margin": 0.6177992215925546,
|
| 219 |
+
"proposal_oracle_success": 1.0,
|
| 220 |
+
"proposal_oracle_utility": 2.0,
|
| 221 |
+
"selected_candidate_index": 7.0,
|
| 222 |
+
"selected_success": 1.0,
|
| 223 |
+
"selected_success_gain_over_base": 0.0,
|
| 224 |
+
"selected_utility": 2.0,
|
| 225 |
+
"selected_utility_gain_over_base": 0.0,
|
| 226 |
+
"selector_regret": 0.0,
|
| 227 |
+
"success_selector_gap": 0.0,
|
| 228 |
+
"success_support_gap": 0.0,
|
| 229 |
+
"support_gap": 0.0,
|
| 230 |
+
"tau": 0.3922077221501807
|
| 231 |
+
},
|
| 232 |
+
"1261930456/train1": {
|
| 233 |
+
"base_success": 1.0,
|
| 234 |
+
"base_utility": 2.0,
|
| 235 |
+
"coverage": 1.0,
|
| 236 |
+
"execute_generated": 1.0,
|
| 237 |
+
"fallback_rate": 0.0,
|
| 238 |
+
"hidden_chart_oracle_success": 1.0,
|
| 239 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 240 |
+
"outcome_ptr": 0.0,
|
| 241 |
+
"predicted_margin": 0.6864147979314642,
|
| 242 |
+
"proposal_oracle_success": 1.0,
|
| 243 |
+
"proposal_oracle_utility": 2.0,
|
| 244 |
+
"selected_candidate_index": 0.0,
|
| 245 |
+
"selected_success": 0.0,
|
| 246 |
+
"selected_success_gain_over_base": -1.0,
|
| 247 |
+
"selected_utility": 0.07528233528137207,
|
| 248 |
+
"selected_utility_gain_over_base": -1.924717664718628,
|
| 249 |
+
"selector_regret": 1.924717664718628,
|
| 250 |
+
"success_selector_gap": 1.0,
|
| 251 |
+
"success_support_gap": 0.0,
|
| 252 |
+
"support_gap": 0.0,
|
| 253 |
+
"tau": 0.3922077221501807
|
| 254 |
+
},
|
| 255 |
+
"1261930456/train2": {
|
| 256 |
+
"base_success": 1.0,
|
| 257 |
+
"base_utility": 2.0,
|
| 258 |
+
"coverage": 1.0,
|
| 259 |
+
"execute_generated": 1.0,
|
| 260 |
+
"fallback_rate": 0.0,
|
| 261 |
+
"hidden_chart_oracle_success": 1.0,
|
| 262 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 263 |
+
"outcome_ptr": 0.0,
|
| 264 |
+
"predicted_margin": 0.6528626636266324,
|
| 265 |
+
"proposal_oracle_success": 1.0,
|
| 266 |
+
"proposal_oracle_utility": 2.0,
|
| 267 |
+
"selected_candidate_index": 7.0,
|
| 268 |
+
"selected_success": 0.0,
|
| 269 |
+
"selected_success_gain_over_base": -1.0,
|
| 270 |
+
"selected_utility": 0.06463125348091125,
|
| 271 |
+
"selected_utility_gain_over_base": -1.9353687465190887,
|
| 272 |
+
"selector_regret": 1.9353687465190887,
|
| 273 |
+
"success_selector_gap": 1.0,
|
| 274 |
+
"success_support_gap": 0.0,
|
| 275 |
+
"support_gap": 0.0,
|
| 276 |
+
"tau": 0.3922077221501807
|
| 277 |
+
},
|
| 278 |
+
"1324133122/train0": {
|
| 279 |
+
"base_success": 0.0,
|
| 280 |
+
"base_utility": 0.09220491349697113,
|
| 281 |
+
"coverage": 0.0,
|
| 282 |
+
"execute_generated": 0.0,
|
| 283 |
+
"fallback_rate": 1.0,
|
| 284 |
+
"hidden_chart_oracle_success": 1.0,
|
| 285 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 286 |
+
"outcome_ptr": 0.0,
|
| 287 |
+
"predicted_margin": 0.2067874232185381,
|
| 288 |
+
"proposal_oracle_success": 0.0,
|
| 289 |
+
"proposal_oracle_utility": 0.054989203810691833,
|
| 290 |
+
"selected_candidate_index": 2.0,
|
| 291 |
+
"selected_success": 0.0,
|
| 292 |
+
"selected_success_gain_over_base": 0.0,
|
| 293 |
+
"selected_utility": 0.09220491349697113,
|
| 294 |
+
"selected_utility_gain_over_base": 0.0,
|
| 295 |
+
"selector_regret": 0.0,
|
| 296 |
+
"success_selector_gap": 0.0,
|
| 297 |
+
"success_support_gap": 1.0,
|
| 298 |
+
"support_gap": 1.9450107961893082,
|
| 299 |
+
"tau": 0.3922077221501807
|
| 300 |
+
},
|
| 301 |
+
"1324133122/train1": {
|
| 302 |
+
"base_success": 0.0,
|
| 303 |
+
"base_utility": 0.09220491349697113,
|
| 304 |
+
"coverage": 0.0,
|
| 305 |
+
"execute_generated": 0.0,
|
| 306 |
+
"fallback_rate": 1.0,
|
| 307 |
+
"hidden_chart_oracle_success": 1.0,
|
| 308 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 309 |
+
"outcome_ptr": 1.0,
|
| 310 |
+
"predicted_margin": 0.22312005246677596,
|
| 311 |
+
"proposal_oracle_success": 0.0,
|
| 312 |
+
"proposal_oracle_utility": 0.1324586570262909,
|
| 313 |
+
"selected_candidate_index": 2.0,
|
| 314 |
+
"selected_success": 0.0,
|
| 315 |
+
"selected_success_gain_over_base": 0.0,
|
| 316 |
+
"selected_utility": 0.09220491349697113,
|
| 317 |
+
"selected_utility_gain_over_base": 0.0,
|
| 318 |
+
"selector_regret": 0.04025374352931976,
|
| 319 |
+
"success_selector_gap": 0.0,
|
| 320 |
+
"success_support_gap": 1.0,
|
| 321 |
+
"support_gap": 1.867541342973709,
|
| 322 |
+
"tau": 0.3922077221501807
|
| 323 |
+
},
|
| 324 |
+
"1324133122/train2": {
|
| 325 |
+
"base_success": 0.0,
|
| 326 |
+
"base_utility": 0.09220491349697113,
|
| 327 |
+
"coverage": 0.0,
|
| 328 |
+
"execute_generated": 0.0,
|
| 329 |
+
"fallback_rate": 1.0,
|
| 330 |
+
"hidden_chart_oracle_success": 1.0,
|
| 331 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 332 |
+
"outcome_ptr": 1.0,
|
| 333 |
+
"predicted_margin": 0.1985668073450419,
|
| 334 |
+
"proposal_oracle_success": 0.0,
|
| 335 |
+
"proposal_oracle_utility": 0.19291165471076965,
|
| 336 |
+
"selected_candidate_index": 2.0,
|
| 337 |
+
"selected_success": 0.0,
|
| 338 |
+
"selected_success_gain_over_base": 0.0,
|
| 339 |
+
"selected_utility": 0.09220491349697113,
|
| 340 |
+
"selected_utility_gain_over_base": 0.0,
|
| 341 |
+
"selector_regret": 0.10070674121379852,
|
| 342 |
+
"success_selector_gap": 0.0,
|
| 343 |
+
"success_support_gap": 1.0,
|
| 344 |
+
"support_gap": 1.8070883452892303,
|
| 345 |
+
"tau": 0.3922077221501807
|
| 346 |
+
},
|
| 347 |
+
"1324642411/train0": {
|
| 348 |
+
"base_success": 0.0,
|
| 349 |
+
"base_utility": 0.10647052526473999,
|
| 350 |
+
"coverage": 0.0,
|
| 351 |
+
"execute_generated": 0.0,
|
| 352 |
+
"fallback_rate": 1.0,
|
| 353 |
+
"hidden_chart_oracle_success": 1.0,
|
| 354 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 355 |
+
"outcome_ptr": 1.0,
|
| 356 |
+
"predicted_margin": 0.2039301366121156,
|
| 357 |
+
"proposal_oracle_success": 0.0,
|
| 358 |
+
"proposal_oracle_utility": 0.17193320393562317,
|
| 359 |
+
"selected_candidate_index": 1.0,
|
| 360 |
+
"selected_success": 0.0,
|
| 361 |
+
"selected_success_gain_over_base": 0.0,
|
| 362 |
+
"selected_utility": 0.10647052526473999,
|
| 363 |
+
"selected_utility_gain_over_base": 0.0,
|
| 364 |
+
"selector_regret": 0.06546267867088318,
|
| 365 |
+
"success_selector_gap": 0.0,
|
| 366 |
+
"success_support_gap": 1.0,
|
| 367 |
+
"support_gap": 1.8280667960643768,
|
| 368 |
+
"tau": 0.3922077221501807
|
| 369 |
+
},
|
| 370 |
+
"1324642411/train1": {
|
| 371 |
+
"base_success": 0.0,
|
| 372 |
+
"base_utility": 0.10647052526473999,
|
| 373 |
+
"coverage": 0.0,
|
| 374 |
+
"execute_generated": 0.0,
|
| 375 |
+
"fallback_rate": 1.0,
|
| 376 |
+
"hidden_chart_oracle_success": 1.0,
|
| 377 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 378 |
+
"outcome_ptr": 1.0,
|
| 379 |
+
"predicted_margin": 0.3274997921079787,
|
| 380 |
+
"proposal_oracle_success": 0.0,
|
| 381 |
+
"proposal_oracle_utility": 0.1836909055709839,
|
| 382 |
+
"selected_candidate_index": 5.0,
|
| 383 |
+
"selected_success": 0.0,
|
| 384 |
+
"selected_success_gain_over_base": 0.0,
|
| 385 |
+
"selected_utility": 0.10647052526473999,
|
| 386 |
+
"selected_utility_gain_over_base": 0.0,
|
| 387 |
+
"selector_regret": 0.0772203803062439,
|
| 388 |
+
"success_selector_gap": 0.0,
|
| 389 |
+
"success_support_gap": 1.0,
|
| 390 |
+
"support_gap": 1.8163090944290161,
|
| 391 |
+
"tau": 0.3922077221501807
|
| 392 |
+
},
|
| 393 |
+
"1324642411/train2": {
|
| 394 |
+
"base_success": 0.0,
|
| 395 |
+
"base_utility": 0.10647052526473999,
|
| 396 |
+
"coverage": 0.0,
|
| 397 |
+
"execute_generated": 0.0,
|
| 398 |
+
"fallback_rate": 1.0,
|
| 399 |
+
"hidden_chart_oracle_success": 1.0,
|
| 400 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 401 |
+
"outcome_ptr": 1.0,
|
| 402 |
+
"predicted_margin": 0.2809267077652993,
|
| 403 |
+
"proposal_oracle_success": 1.0,
|
| 404 |
+
"proposal_oracle_utility": 2.0,
|
| 405 |
+
"selected_candidate_index": 3.0,
|
| 406 |
+
"selected_success": 0.0,
|
| 407 |
+
"selected_success_gain_over_base": 0.0,
|
| 408 |
+
"selected_utility": 0.10647052526473999,
|
| 409 |
+
"selected_utility_gain_over_base": 0.0,
|
| 410 |
+
"selector_regret": 1.89352947473526,
|
| 411 |
+
"success_selector_gap": 1.0,
|
| 412 |
+
"success_support_gap": 0.0,
|
| 413 |
+
"support_gap": 0.0,
|
| 414 |
+
"tau": 0.3922077221501807
|
| 415 |
+
},
|
| 416 |
+
"1375492786/train0": {
|
| 417 |
+
"base_success": 1.0,
|
| 418 |
+
"base_utility": 2.0,
|
| 419 |
+
"coverage": 0.0,
|
| 420 |
+
"execute_generated": 0.0,
|
| 421 |
+
"fallback_rate": 1.0,
|
| 422 |
+
"hidden_chart_oracle_success": 1.0,
|
| 423 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 424 |
+
"outcome_ptr": 0.0,
|
| 425 |
+
"predicted_margin": 0.12776527911809626,
|
| 426 |
+
"proposal_oracle_success": 1.0,
|
| 427 |
+
"proposal_oracle_utility": 2.0,
|
| 428 |
+
"selected_candidate_index": 0.0,
|
| 429 |
+
"selected_success": 1.0,
|
| 430 |
+
"selected_success_gain_over_base": 0.0,
|
| 431 |
+
"selected_utility": 2.0,
|
| 432 |
+
"selected_utility_gain_over_base": 0.0,
|
| 433 |
+
"selector_regret": 0.0,
|
| 434 |
+
"success_selector_gap": 0.0,
|
| 435 |
+
"success_support_gap": 0.0,
|
| 436 |
+
"support_gap": 0.0,
|
| 437 |
+
"tau": 0.3922077221501807
|
| 438 |
+
},
|
| 439 |
+
"1375492786/train1": {
|
| 440 |
+
"base_success": 1.0,
|
| 441 |
+
"base_utility": 2.0,
|
| 442 |
+
"coverage": 0.0,
|
| 443 |
+
"execute_generated": 0.0,
|
| 444 |
+
"fallback_rate": 1.0,
|
| 445 |
+
"hidden_chart_oracle_success": 1.0,
|
| 446 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 447 |
+
"outcome_ptr": 0.0,
|
| 448 |
+
"predicted_margin": 0.1046038199543038,
|
| 449 |
+
"proposal_oracle_success": 0.0,
|
| 450 |
+
"proposal_oracle_utility": 0.08251869678497314,
|
| 451 |
+
"selected_candidate_index": 7.0,
|
| 452 |
+
"selected_success": 1.0,
|
| 453 |
+
"selected_success_gain_over_base": 0.0,
|
| 454 |
+
"selected_utility": 2.0,
|
| 455 |
+
"selected_utility_gain_over_base": 0.0,
|
| 456 |
+
"selector_regret": 0.0,
|
| 457 |
+
"success_selector_gap": 0.0,
|
| 458 |
+
"success_support_gap": 1.0,
|
| 459 |
+
"support_gap": 1.9174813032150269,
|
| 460 |
+
"tau": 0.3922077221501807
|
| 461 |
+
},
|
| 462 |
+
"1375492786/train2": {
|
| 463 |
+
"base_success": 1.0,
|
| 464 |
+
"base_utility": 2.0,
|
| 465 |
+
"coverage": 0.0,
|
| 466 |
+
"execute_generated": 0.0,
|
| 467 |
+
"fallback_rate": 1.0,
|
| 468 |
+
"hidden_chart_oracle_success": 1.0,
|
| 469 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 470 |
+
"outcome_ptr": 0.0,
|
| 471 |
+
"predicted_margin": 0.0660669590237109,
|
| 472 |
+
"proposal_oracle_success": 1.0,
|
| 473 |
+
"proposal_oracle_utility": 2.0,
|
| 474 |
+
"selected_candidate_index": 4.0,
|
| 475 |
+
"selected_success": 1.0,
|
| 476 |
+
"selected_success_gain_over_base": 0.0,
|
| 477 |
+
"selected_utility": 2.0,
|
| 478 |
+
"selected_utility_gain_over_base": 0.0,
|
| 479 |
+
"selector_regret": 0.0,
|
| 480 |
+
"success_selector_gap": 0.0,
|
| 481 |
+
"success_support_gap": 0.0,
|
| 482 |
+
"support_gap": 0.0,
|
| 483 |
+
"tau": 0.3922077221501807
|
| 484 |
+
},
|
| 485 |
+
"141984615/train0": {
|
| 486 |
+
"base_success": 0.0,
|
| 487 |
+
"base_utility": 0.10283424705266953,
|
| 488 |
+
"coverage": 0.0,
|
| 489 |
+
"execute_generated": 0.0,
|
| 490 |
+
"fallback_rate": 1.0,
|
| 491 |
+
"hidden_chart_oracle_success": 0.0,
|
| 492 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 493 |
+
"outcome_ptr": 0.0,
|
| 494 |
+
"predicted_margin": 0.013890986859197135,
|
| 495 |
+
"proposal_oracle_success": 0.0,
|
| 496 |
+
"proposal_oracle_utility": 0.007291515823453665,
|
| 497 |
+
"selected_candidate_index": 6.0,
|
| 498 |
+
"selected_success": 0.0,
|
| 499 |
+
"selected_success_gain_over_base": 0.0,
|
| 500 |
+
"selected_utility": 0.10283424705266953,
|
| 501 |
+
"selected_utility_gain_over_base": 0.0,
|
| 502 |
+
"selector_regret": 0.0,
|
| 503 |
+
"success_selector_gap": 0.0,
|
| 504 |
+
"success_support_gap": 0.0,
|
| 505 |
+
"support_gap": 0.27848575497046113,
|
| 506 |
+
"tau": 0.3922077221501807
|
| 507 |
+
},
|
| 508 |
+
"141984615/train1": {
|
| 509 |
+
"base_success": 0.0,
|
| 510 |
+
"base_utility": 0.10283424705266953,
|
| 511 |
+
"coverage": 0.0,
|
| 512 |
+
"execute_generated": 0.0,
|
| 513 |
+
"fallback_rate": 1.0,
|
| 514 |
+
"hidden_chart_oracle_success": 0.0,
|
| 515 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 516 |
+
"outcome_ptr": 0.0,
|
| 517 |
+
"predicted_margin": 0.08493514054789938,
|
| 518 |
+
"proposal_oracle_success": 0.0,
|
| 519 |
+
"proposal_oracle_utility": 0.037011127918958664,
|
| 520 |
+
"selected_candidate_index": 0.0,
|
| 521 |
+
"selected_success": 0.0,
|
| 522 |
+
"selected_success_gain_over_base": 0.0,
|
| 523 |
+
"selected_utility": 0.10283424705266953,
|
| 524 |
+
"selected_utility_gain_over_base": 0.0,
|
| 525 |
+
"selector_regret": 0.0,
|
| 526 |
+
"success_selector_gap": 0.0,
|
| 527 |
+
"success_support_gap": 0.0,
|
| 528 |
+
"support_gap": 0.24876614287495613,
|
| 529 |
+
"tau": 0.3922077221501807
|
| 530 |
+
},
|
| 531 |
+
"141984615/train2": {
|
| 532 |
+
"base_success": 0.0,
|
| 533 |
+
"base_utility": 0.10283424705266953,
|
| 534 |
+
"coverage": 0.0,
|
| 535 |
+
"execute_generated": 0.0,
|
| 536 |
+
"fallback_rate": 1.0,
|
| 537 |
+
"hidden_chart_oracle_success": 0.0,
|
| 538 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 539 |
+
"outcome_ptr": 0.0,
|
| 540 |
+
"predicted_margin": 0.011692573274815495,
|
| 541 |
+
"proposal_oracle_success": 0.0,
|
| 542 |
+
"proposal_oracle_utility": 0.030228236690163612,
|
| 543 |
+
"selected_candidate_index": 0.0,
|
| 544 |
+
"selected_success": 0.0,
|
| 545 |
+
"selected_success_gain_over_base": 0.0,
|
| 546 |
+
"selected_utility": 0.10283424705266953,
|
| 547 |
+
"selected_utility_gain_over_base": 0.0,
|
| 548 |
+
"selector_regret": 0.0,
|
| 549 |
+
"success_selector_gap": 0.0,
|
| 550 |
+
"success_support_gap": 0.0,
|
| 551 |
+
"support_gap": 0.2555490341037512,
|
| 552 |
+
"tau": 0.3922077221501807
|
| 553 |
+
},
|
| 554 |
+
"1461069713/train0": {
|
| 555 |
+
"base_success": 0.0,
|
| 556 |
+
"base_utility": 0.0939030647277832,
|
| 557 |
+
"coverage": 0.0,
|
| 558 |
+
"execute_generated": 0.0,
|
| 559 |
+
"fallback_rate": 1.0,
|
| 560 |
+
"hidden_chart_oracle_success": 0.0,
|
| 561 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 562 |
+
"outcome_ptr": 0.0,
|
| 563 |
+
"predicted_margin": 0.029854794800442567,
|
| 564 |
+
"proposal_oracle_success": 0.0,
|
| 565 |
+
"proposal_oracle_utility": 0.06019836664199829,
|
| 566 |
+
"selected_candidate_index": 7.0,
|
| 567 |
+
"selected_success": 0.0,
|
| 568 |
+
"selected_success_gain_over_base": 0.0,
|
| 569 |
+
"selected_utility": 0.0939030647277832,
|
| 570 |
+
"selected_utility_gain_over_base": 0.0,
|
| 571 |
+
"selector_regret": 0.0,
|
| 572 |
+
"success_selector_gap": 0.0,
|
| 573 |
+
"success_support_gap": 0.0,
|
| 574 |
+
"support_gap": 0.0991440862417221,
|
| 575 |
+
"tau": 0.3922077221501807
|
| 576 |
+
},
|
| 577 |
+
"1461069713/train1": {
|
| 578 |
+
"base_success": 0.0,
|
| 579 |
+
"base_utility": 0.0939030647277832,
|
| 580 |
+
"coverage": 0.0,
|
| 581 |
+
"execute_generated": 0.0,
|
| 582 |
+
"fallback_rate": 1.0,
|
| 583 |
+
"hidden_chart_oracle_success": 0.0,
|
| 584 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 585 |
+
"outcome_ptr": 0.0,
|
| 586 |
+
"predicted_margin": 0.02289721008064745,
|
| 587 |
+
"proposal_oracle_success": 0.0,
|
| 588 |
+
"proposal_oracle_utility": 0.016585012897849083,
|
| 589 |
+
"selected_candidate_index": 3.0,
|
| 590 |
+
"selected_success": 0.0,
|
| 591 |
+
"selected_success_gain_over_base": 0.0,
|
| 592 |
+
"selected_utility": 0.0939030647277832,
|
| 593 |
+
"selected_utility_gain_over_base": 0.0,
|
| 594 |
+
"selector_regret": 0.0,
|
| 595 |
+
"success_selector_gap": 0.0,
|
| 596 |
+
"success_support_gap": 0.0,
|
| 597 |
+
"support_gap": 0.14275743998587132,
|
| 598 |
+
"tau": 0.3922077221501807
|
| 599 |
+
},
|
| 600 |
+
"1461069713/train2": {
|
| 601 |
+
"base_success": 0.0,
|
| 602 |
+
"base_utility": 0.0939030647277832,
|
| 603 |
+
"coverage": 0.0,
|
| 604 |
+
"execute_generated": 0.0,
|
| 605 |
+
"fallback_rate": 1.0,
|
| 606 |
+
"hidden_chart_oracle_success": 0.0,
|
| 607 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 608 |
+
"outcome_ptr": 1.0,
|
| 609 |
+
"predicted_margin": 0.03429488965035381,
|
| 610 |
+
"proposal_oracle_success": 0.0,
|
| 611 |
+
"proposal_oracle_utility": 0.09970339387655258,
|
| 612 |
+
"selected_candidate_index": 5.0,
|
| 613 |
+
"selected_success": 0.0,
|
| 614 |
+
"selected_success_gain_over_base": 0.0,
|
| 615 |
+
"selected_utility": 0.0939030647277832,
|
| 616 |
+
"selected_utility_gain_over_base": 0.0,
|
| 617 |
+
"selector_regret": 0.005800329148769379,
|
| 618 |
+
"success_selector_gap": 0.0,
|
| 619 |
+
"success_support_gap": 0.0,
|
| 620 |
+
"support_gap": 0.059639059007167816,
|
| 621 |
+
"tau": 0.3922077221501807
|
| 622 |
+
},
|
| 623 |
+
"1480856810/train0": {
|
| 624 |
+
"base_success": 0.0,
|
| 625 |
+
"base_utility": 0.08703407645225525,
|
| 626 |
+
"coverage": 0.0,
|
| 627 |
+
"execute_generated": 0.0,
|
| 628 |
+
"fallback_rate": 1.0,
|
| 629 |
+
"hidden_chart_oracle_success": 0.0,
|
| 630 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 631 |
+
"outcome_ptr": 1.0,
|
| 632 |
+
"predicted_margin": 0.3684695668261147,
|
| 633 |
+
"proposal_oracle_success": 1.0,
|
| 634 |
+
"proposal_oracle_utility": 2.0,
|
| 635 |
+
"selected_candidate_index": 2.0,
|
| 636 |
+
"selected_success": 0.0,
|
| 637 |
+
"selected_success_gain_over_base": 0.0,
|
| 638 |
+
"selected_utility": 0.08703407645225525,
|
| 639 |
+
"selected_utility_gain_over_base": 0.0,
|
| 640 |
+
"selector_regret": 1.9129659235477448,
|
| 641 |
+
"success_selector_gap": 1.0,
|
| 642 |
+
"success_support_gap": 0.0,
|
| 643 |
+
"support_gap": 0.0,
|
| 644 |
+
"tau": 0.3922077221501807
|
| 645 |
+
},
|
| 646 |
+
"1480856810/train1": {
|
| 647 |
+
"base_success": 0.0,
|
| 648 |
+
"base_utility": 0.08703407645225525,
|
| 649 |
+
"coverage": 1.0,
|
| 650 |
+
"execute_generated": 1.0,
|
| 651 |
+
"fallback_rate": 0.0,
|
| 652 |
+
"hidden_chart_oracle_success": 0.0,
|
| 653 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 654 |
+
"outcome_ptr": 1.0,
|
| 655 |
+
"predicted_margin": 0.5465640781065289,
|
| 656 |
+
"proposal_oracle_success": 1.0,
|
| 657 |
+
"proposal_oracle_utility": 2.0,
|
| 658 |
+
"selected_candidate_index": 7.0,
|
| 659 |
+
"selected_success": 0.0,
|
| 660 |
+
"selected_success_gain_over_base": 0.0,
|
| 661 |
+
"selected_utility": 0.1887265145778656,
|
| 662 |
+
"selected_utility_gain_over_base": 0.10169243812561035,
|
| 663 |
+
"selector_regret": 1.8112734854221344,
|
| 664 |
+
"success_selector_gap": 1.0,
|
| 665 |
+
"success_support_gap": 0.0,
|
| 666 |
+
"support_gap": 0.0,
|
| 667 |
+
"tau": 0.3922077221501807
|
| 668 |
+
},
|
| 669 |
+
"1480856810/train2": {
|
| 670 |
+
"base_success": 0.0,
|
| 671 |
+
"base_utility": 0.08703407645225525,
|
| 672 |
+
"coverage": 1.0,
|
| 673 |
+
"execute_generated": 1.0,
|
| 674 |
+
"fallback_rate": 0.0,
|
| 675 |
+
"hidden_chart_oracle_success": 0.0,
|
| 676 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 677 |
+
"outcome_ptr": 1.0,
|
| 678 |
+
"predicted_margin": 0.41608334760321053,
|
| 679 |
+
"proposal_oracle_success": 1.0,
|
| 680 |
+
"proposal_oracle_utility": 2.0,
|
| 681 |
+
"selected_candidate_index": 0.0,
|
| 682 |
+
"selected_success": 1.0,
|
| 683 |
+
"selected_success_gain_over_base": 1.0,
|
| 684 |
+
"selected_utility": 2.0,
|
| 685 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 686 |
+
"selector_regret": 0.0,
|
| 687 |
+
"success_selector_gap": 0.0,
|
| 688 |
+
"success_support_gap": 0.0,
|
| 689 |
+
"support_gap": 0.0,
|
| 690 |
+
"tau": 0.3922077221501807
|
| 691 |
+
},
|
| 692 |
+
"1509980664/train0": {
|
| 693 |
+
"base_success": 0.0,
|
| 694 |
+
"base_utility": 0.8334100246429443,
|
| 695 |
+
"coverage": 0.0,
|
| 696 |
+
"execute_generated": 0.0,
|
| 697 |
+
"fallback_rate": 1.0,
|
| 698 |
+
"hidden_chart_oracle_success": 1.0,
|
| 699 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 700 |
+
"outcome_ptr": 1.0,
|
| 701 |
+
"predicted_margin": 0.20387076283728045,
|
| 702 |
+
"proposal_oracle_success": 1.0,
|
| 703 |
+
"proposal_oracle_utility": 2.0,
|
| 704 |
+
"selected_candidate_index": 0.0,
|
| 705 |
+
"selected_success": 0.0,
|
| 706 |
+
"selected_success_gain_over_base": 0.0,
|
| 707 |
+
"selected_utility": 0.8334100246429443,
|
| 708 |
+
"selected_utility_gain_over_base": 0.0,
|
| 709 |
+
"selector_regret": 1.1665899753570557,
|
| 710 |
+
"success_selector_gap": 1.0,
|
| 711 |
+
"success_support_gap": 0.0,
|
| 712 |
+
"support_gap": 0.0,
|
| 713 |
+
"tau": 0.3922077221501807
|
| 714 |
+
},
|
| 715 |
+
"1509980664/train1": {
|
| 716 |
+
"base_success": 0.0,
|
| 717 |
+
"base_utility": 0.8334100246429443,
|
| 718 |
+
"coverage": 1.0,
|
| 719 |
+
"execute_generated": 1.0,
|
| 720 |
+
"fallback_rate": 0.0,
|
| 721 |
+
"hidden_chart_oracle_success": 1.0,
|
| 722 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 723 |
+
"outcome_ptr": 1.0,
|
| 724 |
+
"predicted_margin": 0.5398812579676796,
|
| 725 |
+
"proposal_oracle_success": 1.0,
|
| 726 |
+
"proposal_oracle_utility": 2.0,
|
| 727 |
+
"selected_candidate_index": 0.0,
|
| 728 |
+
"selected_success": 1.0,
|
| 729 |
+
"selected_success_gain_over_base": 1.0,
|
| 730 |
+
"selected_utility": 2.0,
|
| 731 |
+
"selected_utility_gain_over_base": 1.1665899753570557,
|
| 732 |
+
"selector_regret": 0.0,
|
| 733 |
+
"success_selector_gap": 0.0,
|
| 734 |
+
"success_support_gap": 0.0,
|
| 735 |
+
"support_gap": 0.0,
|
| 736 |
+
"tau": 0.3922077221501807
|
| 737 |
+
},
|
| 738 |
+
"1509980664/train2": {
|
| 739 |
+
"base_success": 0.0,
|
| 740 |
+
"base_utility": 0.8334100246429443,
|
| 741 |
+
"coverage": 0.0,
|
| 742 |
+
"execute_generated": 0.0,
|
| 743 |
+
"fallback_rate": 1.0,
|
| 744 |
+
"hidden_chart_oracle_success": 1.0,
|
| 745 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 746 |
+
"outcome_ptr": 0.0,
|
| 747 |
+
"predicted_margin": 0.33920546862707446,
|
| 748 |
+
"proposal_oracle_success": 0.0,
|
| 749 |
+
"proposal_oracle_utility": 0.8162217140197754,
|
| 750 |
+
"selected_candidate_index": 7.0,
|
| 751 |
+
"selected_success": 0.0,
|
| 752 |
+
"selected_success_gain_over_base": 0.0,
|
| 753 |
+
"selected_utility": 0.8334100246429443,
|
| 754 |
+
"selected_utility_gain_over_base": 0.0,
|
| 755 |
+
"selector_regret": 0.0,
|
| 756 |
+
"success_selector_gap": 0.0,
|
| 757 |
+
"success_support_gap": 1.0,
|
| 758 |
+
"support_gap": 1.1837782859802246,
|
| 759 |
+
"tau": 0.3922077221501807
|
| 760 |
+
},
|
| 761 |
+
"1522272686/train0": {
|
| 762 |
+
"base_success": 0.0,
|
| 763 |
+
"base_utility": 0.5839591026306152,
|
| 764 |
+
"coverage": 0.0,
|
| 765 |
+
"execute_generated": 0.0,
|
| 766 |
+
"fallback_rate": 1.0,
|
| 767 |
+
"hidden_chart_oracle_success": 1.0,
|
| 768 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 769 |
+
"outcome_ptr": 0.0,
|
| 770 |
+
"predicted_margin": 0.09979768262139747,
|
| 771 |
+
"proposal_oracle_success": 0.0,
|
| 772 |
+
"proposal_oracle_utility": 0.18325337767601013,
|
| 773 |
+
"selected_candidate_index": 2.0,
|
| 774 |
+
"selected_success": 0.0,
|
| 775 |
+
"selected_success_gain_over_base": 0.0,
|
| 776 |
+
"selected_utility": 0.5839591026306152,
|
| 777 |
+
"selected_utility_gain_over_base": 0.0,
|
| 778 |
+
"selector_regret": 0.0,
|
| 779 |
+
"success_selector_gap": 0.0,
|
| 780 |
+
"success_support_gap": 1.0,
|
| 781 |
+
"support_gap": 1.8167466223239899,
|
| 782 |
+
"tau": 0.3922077221501807
|
| 783 |
+
},
|
| 784 |
+
"1522272686/train1": {
|
| 785 |
+
"base_success": 0.0,
|
| 786 |
+
"base_utility": 0.5839591026306152,
|
| 787 |
+
"coverage": 0.0,
|
| 788 |
+
"execute_generated": 0.0,
|
| 789 |
+
"fallback_rate": 1.0,
|
| 790 |
+
"hidden_chart_oracle_success": 1.0,
|
| 791 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 792 |
+
"outcome_ptr": 0.0,
|
| 793 |
+
"predicted_margin": 0.08957067193853586,
|
| 794 |
+
"proposal_oracle_success": 0.0,
|
| 795 |
+
"proposal_oracle_utility": 0.07014383375644684,
|
| 796 |
+
"selected_candidate_index": 5.0,
|
| 797 |
+
"selected_success": 0.0,
|
| 798 |
+
"selected_success_gain_over_base": 0.0,
|
| 799 |
+
"selected_utility": 0.5839591026306152,
|
| 800 |
+
"selected_utility_gain_over_base": 0.0,
|
| 801 |
+
"selector_regret": 0.0,
|
| 802 |
+
"success_selector_gap": 0.0,
|
| 803 |
+
"success_support_gap": 1.0,
|
| 804 |
+
"support_gap": 1.9298561662435532,
|
| 805 |
+
"tau": 0.3922077221501807
|
| 806 |
+
},
|
| 807 |
+
"1522272686/train2": {
|
| 808 |
+
"base_success": 0.0,
|
| 809 |
+
"base_utility": 0.5839591026306152,
|
| 810 |
+
"coverage": 0.0,
|
| 811 |
+
"execute_generated": 0.0,
|
| 812 |
+
"fallback_rate": 1.0,
|
| 813 |
+
"hidden_chart_oracle_success": 1.0,
|
| 814 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 815 |
+
"outcome_ptr": 0.0,
|
| 816 |
+
"predicted_margin": 0.06827948100898479,
|
| 817 |
+
"proposal_oracle_success": 0.0,
|
| 818 |
+
"proposal_oracle_utility": 0.14937306940555573,
|
| 819 |
+
"selected_candidate_index": 3.0,
|
| 820 |
+
"selected_success": 0.0,
|
| 821 |
+
"selected_success_gain_over_base": 0.0,
|
| 822 |
+
"selected_utility": 0.5839591026306152,
|
| 823 |
+
"selected_utility_gain_over_base": 0.0,
|
| 824 |
+
"selector_regret": 0.0,
|
| 825 |
+
"success_selector_gap": 0.0,
|
| 826 |
+
"success_support_gap": 1.0,
|
| 827 |
+
"support_gap": 1.8506269305944443,
|
| 828 |
+
"tau": 0.3922077221501807
|
| 829 |
+
},
|
| 830 |
+
"1549324805/train0": {
|
| 831 |
+
"base_success": 0.0,
|
| 832 |
+
"base_utility": 0.10451483726501465,
|
| 833 |
+
"coverage": 0.0,
|
| 834 |
+
"execute_generated": 0.0,
|
| 835 |
+
"fallback_rate": 1.0,
|
| 836 |
+
"hidden_chart_oracle_success": 0.0,
|
| 837 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 838 |
+
"outcome_ptr": 0.0,
|
| 839 |
+
"predicted_margin": 0.039192806066983506,
|
| 840 |
+
"proposal_oracle_success": 0.0,
|
| 841 |
+
"proposal_oracle_utility": 0.0415392704308033,
|
| 842 |
+
"selected_candidate_index": 2.0,
|
| 843 |
+
"selected_success": 0.0,
|
| 844 |
+
"selected_success_gain_over_base": 0.0,
|
| 845 |
+
"selected_utility": 0.10451483726501465,
|
| 846 |
+
"selected_utility_gain_over_base": 0.0,
|
| 847 |
+
"selector_regret": 0.0,
|
| 848 |
+
"success_selector_gap": 0.0,
|
| 849 |
+
"success_support_gap": 0.0,
|
| 850 |
+
"support_gap": 0.255916815251112,
|
| 851 |
+
"tau": 0.3922077221501807
|
| 852 |
+
},
|
| 853 |
+
"1549324805/train1": {
|
| 854 |
+
"base_success": 0.0,
|
| 855 |
+
"base_utility": 0.10451483726501465,
|
| 856 |
+
"coverage": 1.0,
|
| 857 |
+
"execute_generated": 1.0,
|
| 858 |
+
"fallback_rate": 0.0,
|
| 859 |
+
"hidden_chart_oracle_success": 0.0,
|
| 860 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 861 |
+
"outcome_ptr": 1.0,
|
| 862 |
+
"predicted_margin": 0.5575600320011339,
|
| 863 |
+
"proposal_oracle_success": 0.0,
|
| 864 |
+
"proposal_oracle_utility": 0.19892151653766632,
|
| 865 |
+
"selected_candidate_index": 4.0,
|
| 866 |
+
"selected_success": 0.0,
|
| 867 |
+
"selected_success_gain_over_base": 0.0,
|
| 868 |
+
"selected_utility": 0.19892151653766632,
|
| 869 |
+
"selected_utility_gain_over_base": 0.09440667927265167,
|
| 870 |
+
"selector_regret": 0.0,
|
| 871 |
+
"success_selector_gap": 0.0,
|
| 872 |
+
"success_support_gap": 0.0,
|
| 873 |
+
"support_gap": 0.09853456914424896,
|
| 874 |
+
"tau": 0.3922077221501807
|
| 875 |
+
},
|
| 876 |
+
"1549324805/train2": {
|
| 877 |
+
"base_success": 0.0,
|
| 878 |
+
"base_utility": 0.10451483726501465,
|
| 879 |
+
"coverage": 1.0,
|
| 880 |
+
"execute_generated": 1.0,
|
| 881 |
+
"fallback_rate": 0.0,
|
| 882 |
+
"hidden_chart_oracle_success": 0.0,
|
| 883 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 884 |
+
"outcome_ptr": 0.0,
|
| 885 |
+
"predicted_margin": 0.7735504166786987,
|
| 886 |
+
"proposal_oracle_success": 0.0,
|
| 887 |
+
"proposal_oracle_utility": 0.09092829376459122,
|
| 888 |
+
"selected_candidate_index": 6.0,
|
| 889 |
+
"selected_success": 0.0,
|
| 890 |
+
"selected_success_gain_over_base": 0.0,
|
| 891 |
+
"selected_utility": 0.04110288619995117,
|
| 892 |
+
"selected_utility_gain_over_base": -0.06341195106506348,
|
| 893 |
+
"selector_regret": 0.049825407564640045,
|
| 894 |
+
"success_selector_gap": 0.0,
|
| 895 |
+
"success_support_gap": 0.0,
|
| 896 |
+
"support_gap": 0.20652779191732407,
|
| 897 |
+
"tau": 0.3922077221501807
|
| 898 |
+
},
|
| 899 |
+
"1578990937/train0": {
|
| 900 |
+
"base_success": 0.0,
|
| 901 |
+
"base_utility": 0.82413649559021,
|
| 902 |
+
"coverage": 0.0,
|
| 903 |
+
"execute_generated": 0.0,
|
| 904 |
+
"fallback_rate": 1.0,
|
| 905 |
+
"hidden_chart_oracle_success": 1.0,
|
| 906 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 907 |
+
"outcome_ptr": 1.0,
|
| 908 |
+
"predicted_margin": 0.3274095780617745,
|
| 909 |
+
"proposal_oracle_success": 1.0,
|
| 910 |
+
"proposal_oracle_utility": 2.0,
|
| 911 |
+
"selected_candidate_index": 7.0,
|
| 912 |
+
"selected_success": 0.0,
|
| 913 |
+
"selected_success_gain_over_base": 0.0,
|
| 914 |
+
"selected_utility": 0.82413649559021,
|
| 915 |
+
"selected_utility_gain_over_base": 0.0,
|
| 916 |
+
"selector_regret": 1.17586350440979,
|
| 917 |
+
"success_selector_gap": 1.0,
|
| 918 |
+
"success_support_gap": 0.0,
|
| 919 |
+
"support_gap": 0.0,
|
| 920 |
+
"tau": 0.3922077221501807
|
| 921 |
+
},
|
| 922 |
+
"1578990937/train1": {
|
| 923 |
+
"base_success": 0.0,
|
| 924 |
+
"base_utility": 0.82413649559021,
|
| 925 |
+
"coverage": 0.0,
|
| 926 |
+
"execute_generated": 0.0,
|
| 927 |
+
"fallback_rate": 1.0,
|
| 928 |
+
"hidden_chart_oracle_success": 1.0,
|
| 929 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 930 |
+
"outcome_ptr": 1.0,
|
| 931 |
+
"predicted_margin": 0.37821832461585203,
|
| 932 |
+
"proposal_oracle_success": 1.0,
|
| 933 |
+
"proposal_oracle_utility": 2.0,
|
| 934 |
+
"selected_candidate_index": 6.0,
|
| 935 |
+
"selected_success": 0.0,
|
| 936 |
+
"selected_success_gain_over_base": 0.0,
|
| 937 |
+
"selected_utility": 0.82413649559021,
|
| 938 |
+
"selected_utility_gain_over_base": 0.0,
|
| 939 |
+
"selector_regret": 1.17586350440979,
|
| 940 |
+
"success_selector_gap": 1.0,
|
| 941 |
+
"success_support_gap": 0.0,
|
| 942 |
+
"support_gap": 0.0,
|
| 943 |
+
"tau": 0.3922077221501807
|
| 944 |
+
},
|
| 945 |
+
"1578990937/train2": {
|
| 946 |
+
"base_success": 0.0,
|
| 947 |
+
"base_utility": 0.82413649559021,
|
| 948 |
+
"coverage": 0.0,
|
| 949 |
+
"execute_generated": 0.0,
|
| 950 |
+
"fallback_rate": 1.0,
|
| 951 |
+
"hidden_chart_oracle_success": 1.0,
|
| 952 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 953 |
+
"outcome_ptr": 1.0,
|
| 954 |
+
"predicted_margin": 0.34068516108292074,
|
| 955 |
+
"proposal_oracle_success": 1.0,
|
| 956 |
+
"proposal_oracle_utility": 2.0,
|
| 957 |
+
"selected_candidate_index": 6.0,
|
| 958 |
+
"selected_success": 0.0,
|
| 959 |
+
"selected_success_gain_over_base": 0.0,
|
| 960 |
+
"selected_utility": 0.82413649559021,
|
| 961 |
+
"selected_utility_gain_over_base": 0.0,
|
| 962 |
+
"selector_regret": 1.17586350440979,
|
| 963 |
+
"success_selector_gap": 1.0,
|
| 964 |
+
"success_support_gap": 0.0,
|
| 965 |
+
"support_gap": 0.0,
|
| 966 |
+
"tau": 0.3922077221501807
|
| 967 |
+
},
|
| 968 |
+
"1747178030/train0": {
|
| 969 |
+
"base_success": 1.0,
|
| 970 |
+
"base_utility": 2.0,
|
| 971 |
+
"coverage": 1.0,
|
| 972 |
+
"execute_generated": 1.0,
|
| 973 |
+
"fallback_rate": 0.0,
|
| 974 |
+
"hidden_chart_oracle_success": 1.0,
|
| 975 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 976 |
+
"outcome_ptr": 0.0,
|
| 977 |
+
"predicted_margin": 0.9365813789082288,
|
| 978 |
+
"proposal_oracle_success": 1.0,
|
| 979 |
+
"proposal_oracle_utility": 2.0,
|
| 980 |
+
"selected_candidate_index": 6.0,
|
| 981 |
+
"selected_success": 1.0,
|
| 982 |
+
"selected_success_gain_over_base": 0.0,
|
| 983 |
+
"selected_utility": 2.0,
|
| 984 |
+
"selected_utility_gain_over_base": 0.0,
|
| 985 |
+
"selector_regret": 0.0,
|
| 986 |
+
"success_selector_gap": 0.0,
|
| 987 |
+
"success_support_gap": 0.0,
|
| 988 |
+
"support_gap": 0.0,
|
| 989 |
+
"tau": 0.3922077221501807
|
| 990 |
+
},
|
| 991 |
+
"1747178030/train1": {
|
| 992 |
+
"base_success": 1.0,
|
| 993 |
+
"base_utility": 2.0,
|
| 994 |
+
"coverage": 1.0,
|
| 995 |
+
"execute_generated": 1.0,
|
| 996 |
+
"fallback_rate": 0.0,
|
| 997 |
+
"hidden_chart_oracle_success": 1.0,
|
| 998 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 999 |
+
"outcome_ptr": 0.0,
|
| 1000 |
+
"predicted_margin": 0.9505009462380627,
|
| 1001 |
+
"proposal_oracle_success": 1.0,
|
| 1002 |
+
"proposal_oracle_utility": 2.0,
|
| 1003 |
+
"selected_candidate_index": 3.0,
|
| 1004 |
+
"selected_success": 1.0,
|
| 1005 |
+
"selected_success_gain_over_base": 0.0,
|
| 1006 |
+
"selected_utility": 2.0,
|
| 1007 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1008 |
+
"selector_regret": 0.0,
|
| 1009 |
+
"success_selector_gap": 0.0,
|
| 1010 |
+
"success_support_gap": 0.0,
|
| 1011 |
+
"support_gap": 0.0,
|
| 1012 |
+
"tau": 0.3922077221501807
|
| 1013 |
+
},
|
| 1014 |
+
"1747178030/train2": {
|
| 1015 |
+
"base_success": 1.0,
|
| 1016 |
+
"base_utility": 2.0,
|
| 1017 |
+
"coverage": 1.0,
|
| 1018 |
+
"execute_generated": 1.0,
|
| 1019 |
+
"fallback_rate": 0.0,
|
| 1020 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1021 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1022 |
+
"outcome_ptr": 0.0,
|
| 1023 |
+
"predicted_margin": 0.9178881400438326,
|
| 1024 |
+
"proposal_oracle_success": 1.0,
|
| 1025 |
+
"proposal_oracle_utility": 2.0,
|
| 1026 |
+
"selected_candidate_index": 2.0,
|
| 1027 |
+
"selected_success": 1.0,
|
| 1028 |
+
"selected_success_gain_over_base": 0.0,
|
| 1029 |
+
"selected_utility": 2.0,
|
| 1030 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1031 |
+
"selector_regret": 0.0,
|
| 1032 |
+
"success_selector_gap": 0.0,
|
| 1033 |
+
"success_support_gap": 0.0,
|
| 1034 |
+
"support_gap": 0.0,
|
| 1035 |
+
"tau": 0.3922077221501807
|
| 1036 |
+
},
|
| 1037 |
+
"1790188787/train0": {
|
| 1038 |
+
"base_success": 0.0,
|
| 1039 |
+
"base_utility": 0.12476746737957001,
|
| 1040 |
+
"coverage": 1.0,
|
| 1041 |
+
"execute_generated": 1.0,
|
| 1042 |
+
"fallback_rate": 0.0,
|
| 1043 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1044 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1045 |
+
"outcome_ptr": 0.0,
|
| 1046 |
+
"predicted_margin": 0.610448511026168,
|
| 1047 |
+
"proposal_oracle_success": 0.0,
|
| 1048 |
+
"proposal_oracle_utility": 0.09791924059391022,
|
| 1049 |
+
"selected_candidate_index": 1.0,
|
| 1050 |
+
"selected_success": 0.0,
|
| 1051 |
+
"selected_success_gain_over_base": 0.0,
|
| 1052 |
+
"selected_utility": 0.06047999858856201,
|
| 1053 |
+
"selected_utility_gain_over_base": -0.064287468791008,
|
| 1054 |
+
"selector_regret": 0.037439242005348206,
|
| 1055 |
+
"success_selector_gap": 0.0,
|
| 1056 |
+
"success_support_gap": 1.0,
|
| 1057 |
+
"support_gap": 1.9020807594060898,
|
| 1058 |
+
"tau": 0.3922077221501807
|
| 1059 |
+
},
|
| 1060 |
+
"1790188787/train1": {
|
| 1061 |
+
"base_success": 0.0,
|
| 1062 |
+
"base_utility": 0.12476746737957001,
|
| 1063 |
+
"coverage": 1.0,
|
| 1064 |
+
"execute_generated": 1.0,
|
| 1065 |
+
"fallback_rate": 0.0,
|
| 1066 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1067 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1068 |
+
"outcome_ptr": 1.0,
|
| 1069 |
+
"predicted_margin": 0.6322289901835425,
|
| 1070 |
+
"proposal_oracle_success": 0.0,
|
| 1071 |
+
"proposal_oracle_utility": 0.13031470775604248,
|
| 1072 |
+
"selected_candidate_index": 0.0,
|
| 1073 |
+
"selected_success": 0.0,
|
| 1074 |
+
"selected_success_gain_over_base": 0.0,
|
| 1075 |
+
"selected_utility": 0.1146477460861206,
|
| 1076 |
+
"selected_utility_gain_over_base": -0.010119721293449402,
|
| 1077 |
+
"selector_regret": 0.015666961669921875,
|
| 1078 |
+
"success_selector_gap": 0.0,
|
| 1079 |
+
"success_support_gap": 1.0,
|
| 1080 |
+
"support_gap": 1.8696852922439575,
|
| 1081 |
+
"tau": 0.3922077221501807
|
| 1082 |
+
},
|
| 1083 |
+
"1790188787/train2": {
|
| 1084 |
+
"base_success": 0.0,
|
| 1085 |
+
"base_utility": 0.12476746737957001,
|
| 1086 |
+
"coverage": 1.0,
|
| 1087 |
+
"execute_generated": 1.0,
|
| 1088 |
+
"fallback_rate": 0.0,
|
| 1089 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1090 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1091 |
+
"outcome_ptr": 1.0,
|
| 1092 |
+
"predicted_margin": 0.7224323051086542,
|
| 1093 |
+
"proposal_oracle_success": 1.0,
|
| 1094 |
+
"proposal_oracle_utility": 2.0,
|
| 1095 |
+
"selected_candidate_index": 3.0,
|
| 1096 |
+
"selected_success": 1.0,
|
| 1097 |
+
"selected_success_gain_over_base": 1.0,
|
| 1098 |
+
"selected_utility": 2.0,
|
| 1099 |
+
"selected_utility_gain_over_base": 1.87523253262043,
|
| 1100 |
+
"selector_regret": 0.0,
|
| 1101 |
+
"success_selector_gap": 0.0,
|
| 1102 |
+
"success_support_gap": 0.0,
|
| 1103 |
+
"support_gap": 0.0,
|
| 1104 |
+
"tau": 0.3922077221501807
|
| 1105 |
+
},
|
| 1106 |
+
"1822210471/train0": {
|
| 1107 |
+
"base_success": 0.0,
|
| 1108 |
+
"base_utility": 0.07191530615091324,
|
| 1109 |
+
"coverage": 0.0,
|
| 1110 |
+
"execute_generated": 0.0,
|
| 1111 |
+
"fallback_rate": 1.0,
|
| 1112 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1113 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1114 |
+
"outcome_ptr": 1.0,
|
| 1115 |
+
"predicted_margin": 0.26476739579345127,
|
| 1116 |
+
"proposal_oracle_success": 1.0,
|
| 1117 |
+
"proposal_oracle_utility": 2.0,
|
| 1118 |
+
"selected_candidate_index": 4.0,
|
| 1119 |
+
"selected_success": 0.0,
|
| 1120 |
+
"selected_success_gain_over_base": 0.0,
|
| 1121 |
+
"selected_utility": 0.07191530615091324,
|
| 1122 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1123 |
+
"selector_regret": 1.9280846938490868,
|
| 1124 |
+
"success_selector_gap": 1.0,
|
| 1125 |
+
"success_support_gap": 0.0,
|
| 1126 |
+
"support_gap": 0.0,
|
| 1127 |
+
"tau": 0.3922077221501807
|
| 1128 |
+
},
|
| 1129 |
+
"1822210471/train1": {
|
| 1130 |
+
"base_success": 0.0,
|
| 1131 |
+
"base_utility": 0.07191530615091324,
|
| 1132 |
+
"coverage": 0.0,
|
| 1133 |
+
"execute_generated": 0.0,
|
| 1134 |
+
"fallback_rate": 1.0,
|
| 1135 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1136 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1137 |
+
"outcome_ptr": 1.0,
|
| 1138 |
+
"predicted_margin": 0.26339046982340003,
|
| 1139 |
+
"proposal_oracle_success": 1.0,
|
| 1140 |
+
"proposal_oracle_utility": 2.0,
|
| 1141 |
+
"selected_candidate_index": 3.0,
|
| 1142 |
+
"selected_success": 0.0,
|
| 1143 |
+
"selected_success_gain_over_base": 0.0,
|
| 1144 |
+
"selected_utility": 0.07191530615091324,
|
| 1145 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1146 |
+
"selector_regret": 1.9280846938490868,
|
| 1147 |
+
"success_selector_gap": 1.0,
|
| 1148 |
+
"success_support_gap": 0.0,
|
| 1149 |
+
"support_gap": 0.0,
|
| 1150 |
+
"tau": 0.3922077221501807
|
| 1151 |
+
},
|
| 1152 |
+
"1822210471/train2": {
|
| 1153 |
+
"base_success": 0.0,
|
| 1154 |
+
"base_utility": 0.07191530615091324,
|
| 1155 |
+
"coverage": 0.0,
|
| 1156 |
+
"execute_generated": 0.0,
|
| 1157 |
+
"fallback_rate": 1.0,
|
| 1158 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1159 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1160 |
+
"outcome_ptr": 1.0,
|
| 1161 |
+
"predicted_margin": 0.2764825012988947,
|
| 1162 |
+
"proposal_oracle_success": 1.0,
|
| 1163 |
+
"proposal_oracle_utility": 2.0,
|
| 1164 |
+
"selected_candidate_index": 2.0,
|
| 1165 |
+
"selected_success": 0.0,
|
| 1166 |
+
"selected_success_gain_over_base": 0.0,
|
| 1167 |
+
"selected_utility": 0.07191530615091324,
|
| 1168 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1169 |
+
"selector_regret": 1.9280846938490868,
|
| 1170 |
+
"success_selector_gap": 1.0,
|
| 1171 |
+
"success_support_gap": 0.0,
|
| 1172 |
+
"support_gap": 0.0,
|
| 1173 |
+
"tau": 0.3922077221501807
|
| 1174 |
+
},
|
| 1175 |
+
"1845489013/train0": {
|
| 1176 |
+
"base_success": 1.0,
|
| 1177 |
+
"base_utility": 2.0,
|
| 1178 |
+
"coverage": 0.0,
|
| 1179 |
+
"execute_generated": 0.0,
|
| 1180 |
+
"fallback_rate": 1.0,
|
| 1181 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1182 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1183 |
+
"outcome_ptr": 0.0,
|
| 1184 |
+
"predicted_margin": 0.32943668699513484,
|
| 1185 |
+
"proposal_oracle_success": 1.0,
|
| 1186 |
+
"proposal_oracle_utility": 2.0,
|
| 1187 |
+
"selected_candidate_index": 5.0,
|
| 1188 |
+
"selected_success": 1.0,
|
| 1189 |
+
"selected_success_gain_over_base": 0.0,
|
| 1190 |
+
"selected_utility": 2.0,
|
| 1191 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1192 |
+
"selector_regret": 0.0,
|
| 1193 |
+
"success_selector_gap": 0.0,
|
| 1194 |
+
"success_support_gap": 0.0,
|
| 1195 |
+
"support_gap": 0.0,
|
| 1196 |
+
"tau": 0.3922077221501807
|
| 1197 |
+
},
|
| 1198 |
+
"1845489013/train1": {
|
| 1199 |
+
"base_success": 1.0,
|
| 1200 |
+
"base_utility": 2.0,
|
| 1201 |
+
"coverage": 0.0,
|
| 1202 |
+
"execute_generated": 0.0,
|
| 1203 |
+
"fallback_rate": 1.0,
|
| 1204 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1205 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1206 |
+
"outcome_ptr": 0.0,
|
| 1207 |
+
"predicted_margin": 0.222420099383246,
|
| 1208 |
+
"proposal_oracle_success": 1.0,
|
| 1209 |
+
"proposal_oracle_utility": 2.0,
|
| 1210 |
+
"selected_candidate_index": 1.0,
|
| 1211 |
+
"selected_success": 1.0,
|
| 1212 |
+
"selected_success_gain_over_base": 0.0,
|
| 1213 |
+
"selected_utility": 2.0,
|
| 1214 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1215 |
+
"selector_regret": 0.0,
|
| 1216 |
+
"success_selector_gap": 0.0,
|
| 1217 |
+
"success_support_gap": 0.0,
|
| 1218 |
+
"support_gap": 0.0,
|
| 1219 |
+
"tau": 0.3922077221501807
|
| 1220 |
+
},
|
| 1221 |
+
"1845489013/train2": {
|
| 1222 |
+
"base_success": 1.0,
|
| 1223 |
+
"base_utility": 2.0,
|
| 1224 |
+
"coverage": 0.0,
|
| 1225 |
+
"execute_generated": 0.0,
|
| 1226 |
+
"fallback_rate": 1.0,
|
| 1227 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1228 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1229 |
+
"outcome_ptr": 0.0,
|
| 1230 |
+
"predicted_margin": 0.17821372087166212,
|
| 1231 |
+
"proposal_oracle_success": 1.0,
|
| 1232 |
+
"proposal_oracle_utility": 2.0,
|
| 1233 |
+
"selected_candidate_index": 1.0,
|
| 1234 |
+
"selected_success": 1.0,
|
| 1235 |
+
"selected_success_gain_over_base": 0.0,
|
| 1236 |
+
"selected_utility": 2.0,
|
| 1237 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1238 |
+
"selector_regret": 0.0,
|
| 1239 |
+
"success_selector_gap": 0.0,
|
| 1240 |
+
"success_support_gap": 0.0,
|
| 1241 |
+
"support_gap": 0.0,
|
| 1242 |
+
"tau": 0.3922077221501807
|
| 1243 |
+
},
|
| 1244 |
+
"1999022574/train0": {
|
| 1245 |
+
"base_success": 1.0,
|
| 1246 |
+
"base_utility": 2.0,
|
| 1247 |
+
"coverage": 0.0,
|
| 1248 |
+
"execute_generated": 0.0,
|
| 1249 |
+
"fallback_rate": 1.0,
|
| 1250 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1251 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1252 |
+
"outcome_ptr": 0.0,
|
| 1253 |
+
"predicted_margin": 0.24758478631005407,
|
| 1254 |
+
"proposal_oracle_success": 1.0,
|
| 1255 |
+
"proposal_oracle_utility": 2.0,
|
| 1256 |
+
"selected_candidate_index": 4.0,
|
| 1257 |
+
"selected_success": 1.0,
|
| 1258 |
+
"selected_success_gain_over_base": 0.0,
|
| 1259 |
+
"selected_utility": 2.0,
|
| 1260 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1261 |
+
"selector_regret": 0.0,
|
| 1262 |
+
"success_selector_gap": 0.0,
|
| 1263 |
+
"success_support_gap": 0.0,
|
| 1264 |
+
"support_gap": 0.0,
|
| 1265 |
+
"tau": 0.3922077221501807
|
| 1266 |
+
},
|
| 1267 |
+
"1999022574/train1": {
|
| 1268 |
+
"base_success": 1.0,
|
| 1269 |
+
"base_utility": 2.0,
|
| 1270 |
+
"coverage": 0.0,
|
| 1271 |
+
"execute_generated": 0.0,
|
| 1272 |
+
"fallback_rate": 1.0,
|
| 1273 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1274 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1275 |
+
"outcome_ptr": 0.0,
|
| 1276 |
+
"predicted_margin": 0.26724437053746436,
|
| 1277 |
+
"proposal_oracle_success": 1.0,
|
| 1278 |
+
"proposal_oracle_utility": 2.0,
|
| 1279 |
+
"selected_candidate_index": 3.0,
|
| 1280 |
+
"selected_success": 1.0,
|
| 1281 |
+
"selected_success_gain_over_base": 0.0,
|
| 1282 |
+
"selected_utility": 2.0,
|
| 1283 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1284 |
+
"selector_regret": 0.0,
|
| 1285 |
+
"success_selector_gap": 0.0,
|
| 1286 |
+
"success_support_gap": 0.0,
|
| 1287 |
+
"support_gap": 0.0,
|
| 1288 |
+
"tau": 0.3922077221501807
|
| 1289 |
+
},
|
| 1290 |
+
"1999022574/train2": {
|
| 1291 |
+
"base_success": 1.0,
|
| 1292 |
+
"base_utility": 2.0,
|
| 1293 |
+
"coverage": 0.0,
|
| 1294 |
+
"execute_generated": 0.0,
|
| 1295 |
+
"fallback_rate": 1.0,
|
| 1296 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1297 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1298 |
+
"outcome_ptr": 0.0,
|
| 1299 |
+
"predicted_margin": 0.1884254987224037,
|
| 1300 |
+
"proposal_oracle_success": 1.0,
|
| 1301 |
+
"proposal_oracle_utility": 2.0,
|
| 1302 |
+
"selected_candidate_index": 2.0,
|
| 1303 |
+
"selected_success": 1.0,
|
| 1304 |
+
"selected_success_gain_over_base": 0.0,
|
| 1305 |
+
"selected_utility": 2.0,
|
| 1306 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1307 |
+
"selector_regret": 0.0,
|
| 1308 |
+
"success_selector_gap": 0.0,
|
| 1309 |
+
"success_support_gap": 0.0,
|
| 1310 |
+
"support_gap": 0.0,
|
| 1311 |
+
"tau": 0.3922077221501807
|
| 1312 |
+
},
|
| 1313 |
+
"2012211287/train0": {
|
| 1314 |
+
"base_success": 0.0,
|
| 1315 |
+
"base_utility": 0.7236053347587585,
|
| 1316 |
+
"coverage": 1.0,
|
| 1317 |
+
"execute_generated": 1.0,
|
| 1318 |
+
"fallback_rate": 0.0,
|
| 1319 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1320 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1321 |
+
"outcome_ptr": 1.0,
|
| 1322 |
+
"predicted_margin": 0.4750392109884963,
|
| 1323 |
+
"proposal_oracle_success": 1.0,
|
| 1324 |
+
"proposal_oracle_utility": 2.0,
|
| 1325 |
+
"selected_candidate_index": 0.0,
|
| 1326 |
+
"selected_success": 0.0,
|
| 1327 |
+
"selected_success_gain_over_base": 0.0,
|
| 1328 |
+
"selected_utility": 0.7064330577850342,
|
| 1329 |
+
"selected_utility_gain_over_base": -0.017172276973724365,
|
| 1330 |
+
"selector_regret": 1.2935669422149658,
|
| 1331 |
+
"success_selector_gap": 1.0,
|
| 1332 |
+
"success_support_gap": 0.0,
|
| 1333 |
+
"support_gap": 0.0,
|
| 1334 |
+
"tau": 0.3922077221501807
|
| 1335 |
+
},
|
| 1336 |
+
"2012211287/train1": {
|
| 1337 |
+
"base_success": 0.0,
|
| 1338 |
+
"base_utility": 0.7236053347587585,
|
| 1339 |
+
"coverage": 1.0,
|
| 1340 |
+
"execute_generated": 1.0,
|
| 1341 |
+
"fallback_rate": 0.0,
|
| 1342 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1343 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1344 |
+
"outcome_ptr": 1.0,
|
| 1345 |
+
"predicted_margin": 0.46475672413410773,
|
| 1346 |
+
"proposal_oracle_success": 1.0,
|
| 1347 |
+
"proposal_oracle_utility": 2.0,
|
| 1348 |
+
"selected_candidate_index": 0.0,
|
| 1349 |
+
"selected_success": 0.0,
|
| 1350 |
+
"selected_success_gain_over_base": 0.0,
|
| 1351 |
+
"selected_utility": 0.3287457525730133,
|
| 1352 |
+
"selected_utility_gain_over_base": -0.39485958218574524,
|
| 1353 |
+
"selector_regret": 1.6712542474269867,
|
| 1354 |
+
"success_selector_gap": 1.0,
|
| 1355 |
+
"success_support_gap": 0.0,
|
| 1356 |
+
"support_gap": 0.0,
|
| 1357 |
+
"tau": 0.3922077221501807
|
| 1358 |
+
},
|
| 1359 |
+
"2012211287/train2": {
|
| 1360 |
+
"base_success": 0.0,
|
| 1361 |
+
"base_utility": 0.7236053347587585,
|
| 1362 |
+
"coverage": 1.0,
|
| 1363 |
+
"execute_generated": 1.0,
|
| 1364 |
+
"fallback_rate": 0.0,
|
| 1365 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1366 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1367 |
+
"outcome_ptr": 1.0,
|
| 1368 |
+
"predicted_margin": 0.4298441742374278,
|
| 1369 |
+
"proposal_oracle_success": 1.0,
|
| 1370 |
+
"proposal_oracle_utility": 2.0,
|
| 1371 |
+
"selected_candidate_index": 0.0,
|
| 1372 |
+
"selected_success": 0.0,
|
| 1373 |
+
"selected_success_gain_over_base": 0.0,
|
| 1374 |
+
"selected_utility": 0.7255895137786865,
|
| 1375 |
+
"selected_utility_gain_over_base": 0.0019841790199279785,
|
| 1376 |
+
"selector_regret": 1.2744104862213135,
|
| 1377 |
+
"success_selector_gap": 1.0,
|
| 1378 |
+
"success_support_gap": 0.0,
|
| 1379 |
+
"support_gap": 0.0,
|
| 1380 |
+
"tau": 0.3922077221501807
|
| 1381 |
+
},
|
| 1382 |
+
"2038594191/train0": {
|
| 1383 |
+
"base_success": 1.0,
|
| 1384 |
+
"base_utility": 2.0,
|
| 1385 |
+
"coverage": 0.0,
|
| 1386 |
+
"execute_generated": 0.0,
|
| 1387 |
+
"fallback_rate": 1.0,
|
| 1388 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1389 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1390 |
+
"outcome_ptr": 0.0,
|
| 1391 |
+
"predicted_margin": 0.16493003734275938,
|
| 1392 |
+
"proposal_oracle_success": 1.0,
|
| 1393 |
+
"proposal_oracle_utility": 2.0,
|
| 1394 |
+
"selected_candidate_index": 5.0,
|
| 1395 |
+
"selected_success": 1.0,
|
| 1396 |
+
"selected_success_gain_over_base": 0.0,
|
| 1397 |
+
"selected_utility": 2.0,
|
| 1398 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1399 |
+
"selector_regret": 0.0,
|
| 1400 |
+
"success_selector_gap": 0.0,
|
| 1401 |
+
"success_support_gap": 0.0,
|
| 1402 |
+
"support_gap": 0.0,
|
| 1403 |
+
"tau": 0.3922077221501807
|
| 1404 |
+
},
|
| 1405 |
+
"2038594191/train1": {
|
| 1406 |
+
"base_success": 1.0,
|
| 1407 |
+
"base_utility": 2.0,
|
| 1408 |
+
"coverage": 0.0,
|
| 1409 |
+
"execute_generated": 0.0,
|
| 1410 |
+
"fallback_rate": 1.0,
|
| 1411 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1412 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1413 |
+
"outcome_ptr": 0.0,
|
| 1414 |
+
"predicted_margin": 0.20622891573521596,
|
| 1415 |
+
"proposal_oracle_success": 1.0,
|
| 1416 |
+
"proposal_oracle_utility": 2.0,
|
| 1417 |
+
"selected_candidate_index": 5.0,
|
| 1418 |
+
"selected_success": 1.0,
|
| 1419 |
+
"selected_success_gain_over_base": 0.0,
|
| 1420 |
+
"selected_utility": 2.0,
|
| 1421 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1422 |
+
"selector_regret": 0.0,
|
| 1423 |
+
"success_selector_gap": 0.0,
|
| 1424 |
+
"success_support_gap": 0.0,
|
| 1425 |
+
"support_gap": 0.0,
|
| 1426 |
+
"tau": 0.3922077221501807
|
| 1427 |
+
},
|
| 1428 |
+
"2038594191/train2": {
|
| 1429 |
+
"base_success": 1.0,
|
| 1430 |
+
"base_utility": 2.0,
|
| 1431 |
+
"coverage": 0.0,
|
| 1432 |
+
"execute_generated": 0.0,
|
| 1433 |
+
"fallback_rate": 1.0,
|
| 1434 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1435 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1436 |
+
"outcome_ptr": 0.0,
|
| 1437 |
+
"predicted_margin": 0.13154580143657454,
|
| 1438 |
+
"proposal_oracle_success": 1.0,
|
| 1439 |
+
"proposal_oracle_utility": 2.0,
|
| 1440 |
+
"selected_candidate_index": 6.0,
|
| 1441 |
+
"selected_success": 1.0,
|
| 1442 |
+
"selected_success_gain_over_base": 0.0,
|
| 1443 |
+
"selected_utility": 2.0,
|
| 1444 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1445 |
+
"selector_regret": 0.0,
|
| 1446 |
+
"success_selector_gap": 0.0,
|
| 1447 |
+
"success_support_gap": 0.0,
|
| 1448 |
+
"support_gap": 0.0,
|
| 1449 |
+
"tau": 0.3922077221501807
|
| 1450 |
+
},
|
| 1451 |
+
"2054899126/train0": {
|
| 1452 |
+
"base_success": 1.0,
|
| 1453 |
+
"base_utility": 2.0,
|
| 1454 |
+
"coverage": 0.5,
|
| 1455 |
+
"execute_generated": 0.5,
|
| 1456 |
+
"fallback_rate": 0.5,
|
| 1457 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1458 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1459 |
+
"outcome_ptr": 0.0,
|
| 1460 |
+
"predicted_margin": 0.6037632760689768,
|
| 1461 |
+
"proposal_oracle_success": 0.5,
|
| 1462 |
+
"proposal_oracle_utility": 1.077283151447773,
|
| 1463 |
+
"selected_candidate_index": 2.0,
|
| 1464 |
+
"selected_success": 0.5,
|
| 1465 |
+
"selected_success_gain_over_base": -0.5,
|
| 1466 |
+
"selected_utility": 1.0714938417077065,
|
| 1467 |
+
"selected_utility_gain_over_base": -0.9285061582922935,
|
| 1468 |
+
"selector_regret": 0.005789309740066528,
|
| 1469 |
+
"success_selector_gap": 0.0,
|
| 1470 |
+
"success_support_gap": 0.5,
|
| 1471 |
+
"support_gap": 0.922716848552227,
|
| 1472 |
+
"tau": 0.3922077221501807
|
| 1473 |
+
},
|
| 1474 |
+
"2054899126/train1": {
|
| 1475 |
+
"base_success": 1.0,
|
| 1476 |
+
"base_utility": 2.0,
|
| 1477 |
+
"coverage": 0.5,
|
| 1478 |
+
"execute_generated": 0.5,
|
| 1479 |
+
"fallback_rate": 0.5,
|
| 1480 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1481 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1482 |
+
"outcome_ptr": 0.0,
|
| 1483 |
+
"predicted_margin": 0.5658006665175064,
|
| 1484 |
+
"proposal_oracle_success": 0.5,
|
| 1485 |
+
"proposal_oracle_utility": 1.0696808770298958,
|
| 1486 |
+
"selected_candidate_index": 4.0,
|
| 1487 |
+
"selected_success": 0.5,
|
| 1488 |
+
"selected_success_gain_over_base": -0.5,
|
| 1489 |
+
"selected_utility": 1.0562344379723072,
|
| 1490 |
+
"selected_utility_gain_over_base": -0.9437655620276928,
|
| 1491 |
+
"selector_regret": 0.013446439057588577,
|
| 1492 |
+
"success_selector_gap": 0.0,
|
| 1493 |
+
"success_support_gap": 0.5,
|
| 1494 |
+
"support_gap": 0.9303191229701042,
|
| 1495 |
+
"tau": 0.3922077221501807
|
| 1496 |
+
},
|
| 1497 |
+
"2054899126/train2": {
|
| 1498 |
+
"base_success": 1.0,
|
| 1499 |
+
"base_utility": 2.0,
|
| 1500 |
+
"coverage": 0.5,
|
| 1501 |
+
"execute_generated": 0.5,
|
| 1502 |
+
"fallback_rate": 0.5,
|
| 1503 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1504 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1505 |
+
"outcome_ptr": 0.0,
|
| 1506 |
+
"predicted_margin": 0.2952537323577487,
|
| 1507 |
+
"proposal_oracle_success": 0.5,
|
| 1508 |
+
"proposal_oracle_utility": 1.0455262660980225,
|
| 1509 |
+
"selected_candidate_index": 2.0,
|
| 1510 |
+
"selected_success": 0.5,
|
| 1511 |
+
"selected_success_gain_over_base": -0.5,
|
| 1512 |
+
"selected_utility": 1.0276100430637598,
|
| 1513 |
+
"selected_utility_gain_over_base": -0.9723899569362402,
|
| 1514 |
+
"selector_regret": 0.017916223034262657,
|
| 1515 |
+
"success_selector_gap": 0.0,
|
| 1516 |
+
"success_support_gap": 0.5,
|
| 1517 |
+
"support_gap": 0.9544737339019775,
|
| 1518 |
+
"tau": 0.3922077221501807
|
| 1519 |
+
},
|
| 1520 |
+
"2061635888/train0": {
|
| 1521 |
+
"base_success": 0.0,
|
| 1522 |
+
"base_utility": 0.05225050449371338,
|
| 1523 |
+
"coverage": 0.0,
|
| 1524 |
+
"execute_generated": 0.0,
|
| 1525 |
+
"fallback_rate": 1.0,
|
| 1526 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1527 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1528 |
+
"outcome_ptr": 1.0,
|
| 1529 |
+
"predicted_margin": 0.11780254150747602,
|
| 1530 |
+
"proposal_oracle_success": 0.0,
|
| 1531 |
+
"proposal_oracle_utility": 0.09799930453300476,
|
| 1532 |
+
"selected_candidate_index": 5.0,
|
| 1533 |
+
"selected_success": 0.0,
|
| 1534 |
+
"selected_success_gain_over_base": 0.0,
|
| 1535 |
+
"selected_utility": 0.05225050449371338,
|
| 1536 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1537 |
+
"selector_regret": 0.04574880003929138,
|
| 1538 |
+
"success_selector_gap": 0.0,
|
| 1539 |
+
"success_support_gap": 1.0,
|
| 1540 |
+
"support_gap": 1.9020006954669952,
|
| 1541 |
+
"tau": 0.3922077221501807
|
| 1542 |
+
},
|
| 1543 |
+
"2061635888/train1": {
|
| 1544 |
+
"base_success": 0.0,
|
| 1545 |
+
"base_utility": 0.05225050449371338,
|
| 1546 |
+
"coverage": 0.0,
|
| 1547 |
+
"execute_generated": 0.0,
|
| 1548 |
+
"fallback_rate": 1.0,
|
| 1549 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1550 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1551 |
+
"outcome_ptr": 1.0,
|
| 1552 |
+
"predicted_margin": 0.19908779608709384,
|
| 1553 |
+
"proposal_oracle_success": 0.0,
|
| 1554 |
+
"proposal_oracle_utility": 0.07580336928367615,
|
| 1555 |
+
"selected_candidate_index": 4.0,
|
| 1556 |
+
"selected_success": 0.0,
|
| 1557 |
+
"selected_success_gain_over_base": 0.0,
|
| 1558 |
+
"selected_utility": 0.05225050449371338,
|
| 1559 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1560 |
+
"selector_regret": 0.02355286478996277,
|
| 1561 |
+
"success_selector_gap": 0.0,
|
| 1562 |
+
"success_support_gap": 1.0,
|
| 1563 |
+
"support_gap": 1.9241966307163239,
|
| 1564 |
+
"tau": 0.3922077221501807
|
| 1565 |
+
},
|
| 1566 |
+
"2061635888/train2": {
|
| 1567 |
+
"base_success": 0.0,
|
| 1568 |
+
"base_utility": 0.05225050449371338,
|
| 1569 |
+
"coverage": 0.0,
|
| 1570 |
+
"execute_generated": 0.0,
|
| 1571 |
+
"fallback_rate": 1.0,
|
| 1572 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1573 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1574 |
+
"outcome_ptr": 1.0,
|
| 1575 |
+
"predicted_margin": 0.09766805763930311,
|
| 1576 |
+
"proposal_oracle_success": 0.0,
|
| 1577 |
+
"proposal_oracle_utility": 0.11105132102966309,
|
| 1578 |
+
"selected_candidate_index": 6.0,
|
| 1579 |
+
"selected_success": 0.0,
|
| 1580 |
+
"selected_success_gain_over_base": 0.0,
|
| 1581 |
+
"selected_utility": 0.05225050449371338,
|
| 1582 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1583 |
+
"selector_regret": 0.05880081653594971,
|
| 1584 |
+
"success_selector_gap": 0.0,
|
| 1585 |
+
"success_support_gap": 1.0,
|
| 1586 |
+
"support_gap": 1.888948678970337,
|
| 1587 |
+
"tau": 0.3922077221501807
|
| 1588 |
+
},
|
| 1589 |
+
"211245842/train0": {
|
| 1590 |
+
"base_success": 0.0,
|
| 1591 |
+
"base_utility": 0.19090841710567474,
|
| 1592 |
+
"coverage": 0.0,
|
| 1593 |
+
"execute_generated": 0.0,
|
| 1594 |
+
"fallback_rate": 1.0,
|
| 1595 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1596 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1597 |
+
"outcome_ptr": 1.0,
|
| 1598 |
+
"predicted_margin": 0.18352922780958533,
|
| 1599 |
+
"proposal_oracle_success": 1.0,
|
| 1600 |
+
"proposal_oracle_utility": 2.0,
|
| 1601 |
+
"selected_candidate_index": 5.0,
|
| 1602 |
+
"selected_success": 0.0,
|
| 1603 |
+
"selected_success_gain_over_base": 0.0,
|
| 1604 |
+
"selected_utility": 0.19090841710567474,
|
| 1605 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1606 |
+
"selector_regret": 1.8090915828943253,
|
| 1607 |
+
"success_selector_gap": 1.0,
|
| 1608 |
+
"success_support_gap": 0.0,
|
| 1609 |
+
"support_gap": 0.0,
|
| 1610 |
+
"tau": 0.3922077221501807
|
| 1611 |
+
},
|
| 1612 |
+
"211245842/train1": {
|
| 1613 |
+
"base_success": 0.0,
|
| 1614 |
+
"base_utility": 0.19090841710567474,
|
| 1615 |
+
"coverage": 0.0,
|
| 1616 |
+
"execute_generated": 0.0,
|
| 1617 |
+
"fallback_rate": 1.0,
|
| 1618 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1619 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1620 |
+
"outcome_ptr": 1.0,
|
| 1621 |
+
"predicted_margin": 0.320375224821534,
|
| 1622 |
+
"proposal_oracle_success": 0.0,
|
| 1623 |
+
"proposal_oracle_utility": 0.21295717358589172,
|
| 1624 |
+
"selected_candidate_index": 5.0,
|
| 1625 |
+
"selected_success": 0.0,
|
| 1626 |
+
"selected_success_gain_over_base": 0.0,
|
| 1627 |
+
"selected_utility": 0.19090841710567474,
|
| 1628 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1629 |
+
"selector_regret": 0.02204875648021698,
|
| 1630 |
+
"success_selector_gap": 0.0,
|
| 1631 |
+
"success_support_gap": 1.0,
|
| 1632 |
+
"support_gap": 1.7870428264141083,
|
| 1633 |
+
"tau": 0.3922077221501807
|
| 1634 |
+
},
|
| 1635 |
+
"211245842/train2": {
|
| 1636 |
+
"base_success": 0.0,
|
| 1637 |
+
"base_utility": 0.19090841710567474,
|
| 1638 |
+
"coverage": 0.0,
|
| 1639 |
+
"execute_generated": 0.0,
|
| 1640 |
+
"fallback_rate": 1.0,
|
| 1641 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1642 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1643 |
+
"outcome_ptr": 1.0,
|
| 1644 |
+
"predicted_margin": 0.31018841407580483,
|
| 1645 |
+
"proposal_oracle_success": 0.0,
|
| 1646 |
+
"proposal_oracle_utility": 0.21523693203926086,
|
| 1647 |
+
"selected_candidate_index": 2.0,
|
| 1648 |
+
"selected_success": 0.0,
|
| 1649 |
+
"selected_success_gain_over_base": 0.0,
|
| 1650 |
+
"selected_utility": 0.19090841710567474,
|
| 1651 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1652 |
+
"selector_regret": 0.02432851493358612,
|
| 1653 |
+
"success_selector_gap": 0.0,
|
| 1654 |
+
"success_support_gap": 1.0,
|
| 1655 |
+
"support_gap": 1.7847630679607391,
|
| 1656 |
+
"tau": 0.3922077221501807
|
| 1657 |
+
},
|
| 1658 |
+
"278008524/train0": {
|
| 1659 |
+
"base_success": 0.0,
|
| 1660 |
+
"base_utility": 0.042734989896416664,
|
| 1661 |
+
"coverage": 1.0,
|
| 1662 |
+
"execute_generated": 1.0,
|
| 1663 |
+
"fallback_rate": 0.0,
|
| 1664 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1665 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1666 |
+
"outcome_ptr": 1.0,
|
| 1667 |
+
"predicted_margin": 0.4575022616390392,
|
| 1668 |
+
"proposal_oracle_success": 0.5,
|
| 1669 |
+
"proposal_oracle_utility": 1.0287093725055456,
|
| 1670 |
+
"selected_candidate_index": 2.0,
|
| 1671 |
+
"selected_success": 0.0,
|
| 1672 |
+
"selected_success_gain_over_base": 0.0,
|
| 1673 |
+
"selected_utility": 0.0722394697368145,
|
| 1674 |
+
"selected_utility_gain_over_base": 0.029504479840397835,
|
| 1675 |
+
"selector_regret": 0.9564699027687311,
|
| 1676 |
+
"success_selector_gap": 0.5,
|
| 1677 |
+
"success_support_gap": 0.0,
|
| 1678 |
+
"support_gap": 0.08519926853477955,
|
| 1679 |
+
"tau": 0.3922077221501807
|
| 1680 |
+
},
|
| 1681 |
+
"278008524/train1": {
|
| 1682 |
+
"base_success": 0.0,
|
| 1683 |
+
"base_utility": 0.042734989896416664,
|
| 1684 |
+
"coverage": 1.0,
|
| 1685 |
+
"execute_generated": 1.0,
|
| 1686 |
+
"fallback_rate": 0.0,
|
| 1687 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1688 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1689 |
+
"outcome_ptr": 1.0,
|
| 1690 |
+
"predicted_margin": 0.7449561702068546,
|
| 1691 |
+
"proposal_oracle_success": 0.5,
|
| 1692 |
+
"proposal_oracle_utility": 1.0376745946705341,
|
| 1693 |
+
"selected_candidate_index": 4.0,
|
| 1694 |
+
"selected_success": 0.0,
|
| 1695 |
+
"selected_success_gain_over_base": 0.0,
|
| 1696 |
+
"selected_utility": 0.04607116058468819,
|
| 1697 |
+
"selected_utility_gain_over_base": 0.0033361706882715225,
|
| 1698 |
+
"selector_regret": 0.991603434085846,
|
| 1699 |
+
"success_selector_gap": 0.5,
|
| 1700 |
+
"success_support_gap": 0.0,
|
| 1701 |
+
"support_gap": 0.07623404636979103,
|
| 1702 |
+
"tau": 0.3922077221501807
|
| 1703 |
+
},
|
| 1704 |
+
"278008524/train2": {
|
| 1705 |
+
"base_success": 0.0,
|
| 1706 |
+
"base_utility": 0.042734989896416664,
|
| 1707 |
+
"coverage": 1.0,
|
| 1708 |
+
"execute_generated": 1.0,
|
| 1709 |
+
"fallback_rate": 0.0,
|
| 1710 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1711 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1712 |
+
"outcome_ptr": 1.0,
|
| 1713 |
+
"predicted_margin": 0.6895189343802417,
|
| 1714 |
+
"proposal_oracle_success": 0.5,
|
| 1715 |
+
"proposal_oracle_utility": 1.1359489113092422,
|
| 1716 |
+
"selected_candidate_index": 5.0,
|
| 1717 |
+
"selected_success": 0.5,
|
| 1718 |
+
"selected_success_gain_over_base": 0.5,
|
| 1719 |
+
"selected_utility": 1.1359489113092422,
|
| 1720 |
+
"selected_utility_gain_over_base": 1.0932139214128256,
|
| 1721 |
+
"selector_regret": 0.0,
|
| 1722 |
+
"success_selector_gap": 0.0,
|
| 1723 |
+
"success_support_gap": 0.0,
|
| 1724 |
+
"support_gap": 0.0,
|
| 1725 |
+
"tau": 0.3922077221501807
|
| 1726 |
+
},
|
| 1727 |
+
"307068879/train0": {
|
| 1728 |
+
"base_success": 0.0,
|
| 1729 |
+
"base_utility": 0.6000905632972717,
|
| 1730 |
+
"coverage": 1.0,
|
| 1731 |
+
"execute_generated": 1.0,
|
| 1732 |
+
"fallback_rate": 0.0,
|
| 1733 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1734 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1735 |
+
"outcome_ptr": 0.0,
|
| 1736 |
+
"predicted_margin": 0.5443095032644824,
|
| 1737 |
+
"proposal_oracle_success": 0.0,
|
| 1738 |
+
"proposal_oracle_utility": 0.2115575522184372,
|
| 1739 |
+
"selected_candidate_index": 6.0,
|
| 1740 |
+
"selected_success": 0.0,
|
| 1741 |
+
"selected_success_gain_over_base": 0.0,
|
| 1742 |
+
"selected_utility": 0.2115575522184372,
|
| 1743 |
+
"selected_utility_gain_over_base": -0.38853301107883453,
|
| 1744 |
+
"selector_regret": 0.0,
|
| 1745 |
+
"success_selector_gap": 0.0,
|
| 1746 |
+
"success_support_gap": 1.0,
|
| 1747 |
+
"support_gap": 1.7884424477815628,
|
| 1748 |
+
"tau": 0.3922077221501807
|
| 1749 |
+
},
|
| 1750 |
+
"307068879/train1": {
|
| 1751 |
+
"base_success": 0.0,
|
| 1752 |
+
"base_utility": 0.6000905632972717,
|
| 1753 |
+
"coverage": 1.0,
|
| 1754 |
+
"execute_generated": 1.0,
|
| 1755 |
+
"fallback_rate": 0.0,
|
| 1756 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1757 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1758 |
+
"outcome_ptr": 0.0,
|
| 1759 |
+
"predicted_margin": 0.7081736037597779,
|
| 1760 |
+
"proposal_oracle_success": 0.0,
|
| 1761 |
+
"proposal_oracle_utility": 0.5876073241233826,
|
| 1762 |
+
"selected_candidate_index": 0.0,
|
| 1763 |
+
"selected_success": 0.0,
|
| 1764 |
+
"selected_success_gain_over_base": 0.0,
|
| 1765 |
+
"selected_utility": 0.20245832204818726,
|
| 1766 |
+
"selected_utility_gain_over_base": -0.3976322412490845,
|
| 1767 |
+
"selector_regret": 0.3851490020751953,
|
| 1768 |
+
"success_selector_gap": 0.0,
|
| 1769 |
+
"success_support_gap": 1.0,
|
| 1770 |
+
"support_gap": 1.4123926758766174,
|
| 1771 |
+
"tau": 0.3922077221501807
|
| 1772 |
+
},
|
| 1773 |
+
"307068879/train2": {
|
| 1774 |
+
"base_success": 0.0,
|
| 1775 |
+
"base_utility": 0.6000905632972717,
|
| 1776 |
+
"coverage": 1.0,
|
| 1777 |
+
"execute_generated": 1.0,
|
| 1778 |
+
"fallback_rate": 0.0,
|
| 1779 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1780 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1781 |
+
"outcome_ptr": 0.0,
|
| 1782 |
+
"predicted_margin": 0.6965632302376273,
|
| 1783 |
+
"proposal_oracle_success": 0.0,
|
| 1784 |
+
"proposal_oracle_utility": 0.22727864980697632,
|
| 1785 |
+
"selected_candidate_index": 2.0,
|
| 1786 |
+
"selected_success": 0.0,
|
| 1787 |
+
"selected_success_gain_over_base": 0.0,
|
| 1788 |
+
"selected_utility": 0.20841218531131744,
|
| 1789 |
+
"selected_utility_gain_over_base": -0.3916783779859543,
|
| 1790 |
+
"selector_regret": 0.018866464495658875,
|
| 1791 |
+
"success_selector_gap": 0.0,
|
| 1792 |
+
"success_support_gap": 1.0,
|
| 1793 |
+
"support_gap": 1.7727213501930237,
|
| 1794 |
+
"tau": 0.3922077221501807
|
| 1795 |
+
},
|
| 1796 |
+
"412102563/train0": {
|
| 1797 |
+
"base_success": 1.0,
|
| 1798 |
+
"base_utility": 2.0,
|
| 1799 |
+
"coverage": 0.0,
|
| 1800 |
+
"execute_generated": 0.0,
|
| 1801 |
+
"fallback_rate": 1.0,
|
| 1802 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1803 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1804 |
+
"outcome_ptr": 0.0,
|
| 1805 |
+
"predicted_margin": 0.31369013099266946,
|
| 1806 |
+
"proposal_oracle_success": 1.0,
|
| 1807 |
+
"proposal_oracle_utility": 2.0,
|
| 1808 |
+
"selected_candidate_index": 5.0,
|
| 1809 |
+
"selected_success": 1.0,
|
| 1810 |
+
"selected_success_gain_over_base": 0.0,
|
| 1811 |
+
"selected_utility": 2.0,
|
| 1812 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1813 |
+
"selector_regret": 0.0,
|
| 1814 |
+
"success_selector_gap": 0.0,
|
| 1815 |
+
"success_support_gap": 0.0,
|
| 1816 |
+
"support_gap": 0.0,
|
| 1817 |
+
"tau": 0.3922077221501807
|
| 1818 |
+
},
|
| 1819 |
+
"412102563/train1": {
|
| 1820 |
+
"base_success": 1.0,
|
| 1821 |
+
"base_utility": 2.0,
|
| 1822 |
+
"coverage": 1.0,
|
| 1823 |
+
"execute_generated": 1.0,
|
| 1824 |
+
"fallback_rate": 0.0,
|
| 1825 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1826 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1827 |
+
"outcome_ptr": 0.0,
|
| 1828 |
+
"predicted_margin": 0.4221573728268961,
|
| 1829 |
+
"proposal_oracle_success": 1.0,
|
| 1830 |
+
"proposal_oracle_utility": 2.0,
|
| 1831 |
+
"selected_candidate_index": 6.0,
|
| 1832 |
+
"selected_success": 1.0,
|
| 1833 |
+
"selected_success_gain_over_base": 0.0,
|
| 1834 |
+
"selected_utility": 2.0,
|
| 1835 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1836 |
+
"selector_regret": 0.0,
|
| 1837 |
+
"success_selector_gap": 0.0,
|
| 1838 |
+
"success_support_gap": 0.0,
|
| 1839 |
+
"support_gap": 0.0,
|
| 1840 |
+
"tau": 0.3922077221501807
|
| 1841 |
+
},
|
| 1842 |
+
"412102563/train2": {
|
| 1843 |
+
"base_success": 1.0,
|
| 1844 |
+
"base_utility": 2.0,
|
| 1845 |
+
"coverage": 0.0,
|
| 1846 |
+
"execute_generated": 0.0,
|
| 1847 |
+
"fallback_rate": 1.0,
|
| 1848 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1849 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1850 |
+
"outcome_ptr": 0.0,
|
| 1851 |
+
"predicted_margin": 0.2468909213849416,
|
| 1852 |
+
"proposal_oracle_success": 1.0,
|
| 1853 |
+
"proposal_oracle_utility": 2.0,
|
| 1854 |
+
"selected_candidate_index": 6.0,
|
| 1855 |
+
"selected_success": 1.0,
|
| 1856 |
+
"selected_success_gain_over_base": 0.0,
|
| 1857 |
+
"selected_utility": 2.0,
|
| 1858 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1859 |
+
"selector_regret": 0.0,
|
| 1860 |
+
"success_selector_gap": 0.0,
|
| 1861 |
+
"success_support_gap": 0.0,
|
| 1862 |
+
"support_gap": 0.0,
|
| 1863 |
+
"tau": 0.3922077221501807
|
| 1864 |
+
},
|
| 1865 |
+
"440577711/train0": {
|
| 1866 |
+
"base_success": 0.0,
|
| 1867 |
+
"base_utility": 0.036152780055999756,
|
| 1868 |
+
"coverage": 1.0,
|
| 1869 |
+
"execute_generated": 1.0,
|
| 1870 |
+
"fallback_rate": 0.0,
|
| 1871 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1872 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1873 |
+
"outcome_ptr": 1.0,
|
| 1874 |
+
"predicted_margin": 0.6446552646547107,
|
| 1875 |
+
"proposal_oracle_success": 1.0,
|
| 1876 |
+
"proposal_oracle_utility": 2.0,
|
| 1877 |
+
"selected_candidate_index": 1.0,
|
| 1878 |
+
"selected_success": 1.0,
|
| 1879 |
+
"selected_success_gain_over_base": 1.0,
|
| 1880 |
+
"selected_utility": 2.0,
|
| 1881 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1882 |
+
"selector_regret": 0.0,
|
| 1883 |
+
"success_selector_gap": 0.0,
|
| 1884 |
+
"success_support_gap": 0.0,
|
| 1885 |
+
"support_gap": 0.0,
|
| 1886 |
+
"tau": 0.3922077221501807
|
| 1887 |
+
},
|
| 1888 |
+
"440577711/train1": {
|
| 1889 |
+
"base_success": 0.0,
|
| 1890 |
+
"base_utility": 0.036152780055999756,
|
| 1891 |
+
"coverage": 1.0,
|
| 1892 |
+
"execute_generated": 1.0,
|
| 1893 |
+
"fallback_rate": 0.0,
|
| 1894 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1895 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1896 |
+
"outcome_ptr": 1.0,
|
| 1897 |
+
"predicted_margin": 0.7093346738311889,
|
| 1898 |
+
"proposal_oracle_success": 1.0,
|
| 1899 |
+
"proposal_oracle_utility": 2.0,
|
| 1900 |
+
"selected_candidate_index": 5.0,
|
| 1901 |
+
"selected_success": 1.0,
|
| 1902 |
+
"selected_success_gain_over_base": 1.0,
|
| 1903 |
+
"selected_utility": 2.0,
|
| 1904 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1905 |
+
"selector_regret": 0.0,
|
| 1906 |
+
"success_selector_gap": 0.0,
|
| 1907 |
+
"success_support_gap": 0.0,
|
| 1908 |
+
"support_gap": 0.0,
|
| 1909 |
+
"tau": 0.3922077221501807
|
| 1910 |
+
},
|
| 1911 |
+
"440577711/train2": {
|
| 1912 |
+
"base_success": 0.0,
|
| 1913 |
+
"base_utility": 0.036152780055999756,
|
| 1914 |
+
"coverage": 1.0,
|
| 1915 |
+
"execute_generated": 1.0,
|
| 1916 |
+
"fallback_rate": 0.0,
|
| 1917 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1918 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1919 |
+
"outcome_ptr": 1.0,
|
| 1920 |
+
"predicted_margin": 0.7444011950212143,
|
| 1921 |
+
"proposal_oracle_success": 1.0,
|
| 1922 |
+
"proposal_oracle_utility": 2.0,
|
| 1923 |
+
"selected_candidate_index": 1.0,
|
| 1924 |
+
"selected_success": 1.0,
|
| 1925 |
+
"selected_success_gain_over_base": 1.0,
|
| 1926 |
+
"selected_utility": 2.0,
|
| 1927 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1928 |
+
"selector_regret": 0.0,
|
| 1929 |
+
"success_selector_gap": 0.0,
|
| 1930 |
+
"success_support_gap": 0.0,
|
| 1931 |
+
"support_gap": 0.0,
|
| 1932 |
+
"tau": 0.3922077221501807
|
| 1933 |
+
},
|
| 1934 |
+
"441046872/train0": {
|
| 1935 |
+
"base_success": 0.0,
|
| 1936 |
+
"base_utility": 0.6999551653862,
|
| 1937 |
+
"coverage": 1.0,
|
| 1938 |
+
"execute_generated": 1.0,
|
| 1939 |
+
"fallback_rate": 0.0,
|
| 1940 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1941 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1942 |
+
"outcome_ptr": 0.0,
|
| 1943 |
+
"predicted_margin": 0.6760407205809709,
|
| 1944 |
+
"proposal_oracle_success": 0.0,
|
| 1945 |
+
"proposal_oracle_utility": 0.5148025155067444,
|
| 1946 |
+
"selected_candidate_index": 7.0,
|
| 1947 |
+
"selected_success": 0.0,
|
| 1948 |
+
"selected_success_gain_over_base": 0.0,
|
| 1949 |
+
"selected_utility": 0.5148025155067444,
|
| 1950 |
+
"selected_utility_gain_over_base": -0.18515264987945557,
|
| 1951 |
+
"selector_regret": 0.0,
|
| 1952 |
+
"success_selector_gap": 0.0,
|
| 1953 |
+
"success_support_gap": 1.0,
|
| 1954 |
+
"support_gap": 1.4851974844932556,
|
| 1955 |
+
"tau": 0.3922077221501807
|
| 1956 |
+
},
|
| 1957 |
+
"441046872/train1": {
|
| 1958 |
+
"base_success": 0.0,
|
| 1959 |
+
"base_utility": 0.6999551653862,
|
| 1960 |
+
"coverage": 1.0,
|
| 1961 |
+
"execute_generated": 1.0,
|
| 1962 |
+
"fallback_rate": 0.0,
|
| 1963 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1964 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1965 |
+
"outcome_ptr": 1.0,
|
| 1966 |
+
"predicted_margin": 0.7685891939989689,
|
| 1967 |
+
"proposal_oracle_success": 0.0,
|
| 1968 |
+
"proposal_oracle_utility": 0.7233588695526123,
|
| 1969 |
+
"selected_candidate_index": 5.0,
|
| 1970 |
+
"selected_success": 0.0,
|
| 1971 |
+
"selected_success_gain_over_base": 0.0,
|
| 1972 |
+
"selected_utility": 0.5762415528297424,
|
| 1973 |
+
"selected_utility_gain_over_base": -0.12371361255645752,
|
| 1974 |
+
"selector_regret": 0.14711731672286987,
|
| 1975 |
+
"success_selector_gap": 0.0,
|
| 1976 |
+
"success_support_gap": 1.0,
|
| 1977 |
+
"support_gap": 1.2766411304473877,
|
| 1978 |
+
"tau": 0.3922077221501807
|
| 1979 |
+
},
|
| 1980 |
+
"441046872/train2": {
|
| 1981 |
+
"base_success": 0.0,
|
| 1982 |
+
"base_utility": 0.6999551653862,
|
| 1983 |
+
"coverage": 1.0,
|
| 1984 |
+
"execute_generated": 1.0,
|
| 1985 |
+
"fallback_rate": 0.0,
|
| 1986 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1987 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1988 |
+
"outcome_ptr": 1.0,
|
| 1989 |
+
"predicted_margin": 0.6925863328147198,
|
| 1990 |
+
"proposal_oracle_success": 0.0,
|
| 1991 |
+
"proposal_oracle_utility": 0.7130289077758789,
|
| 1992 |
+
"selected_candidate_index": 5.0,
|
| 1993 |
+
"selected_success": 0.0,
|
| 1994 |
+
"selected_success_gain_over_base": 0.0,
|
| 1995 |
+
"selected_utility": 0.6454772353172302,
|
| 1996 |
+
"selected_utility_gain_over_base": -0.05447793006896973,
|
| 1997 |
+
"selector_regret": 0.06755167245864868,
|
| 1998 |
+
"success_selector_gap": 0.0,
|
| 1999 |
+
"success_support_gap": 1.0,
|
| 2000 |
+
"support_gap": 1.286971092224121,
|
| 2001 |
+
"tau": 0.3922077221501807
|
| 2002 |
+
},
|
| 2003 |
+
"509430392/train0": {
|
| 2004 |
+
"base_success": 0.0,
|
| 2005 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2006 |
+
"coverage": 0.0,
|
| 2007 |
+
"execute_generated": 0.0,
|
| 2008 |
+
"fallback_rate": 1.0,
|
| 2009 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2010 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2011 |
+
"outcome_ptr": 1.0,
|
| 2012 |
+
"predicted_margin": 0.2460083281337516,
|
| 2013 |
+
"proposal_oracle_success": 1.0,
|
| 2014 |
+
"proposal_oracle_utility": 2.0,
|
| 2015 |
+
"selected_candidate_index": 3.0,
|
| 2016 |
+
"selected_success": 0.0,
|
| 2017 |
+
"selected_success_gain_over_base": 0.0,
|
| 2018 |
+
"selected_utility": 2.2351741790771484e-07,
|
| 2019 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2020 |
+
"selector_regret": 1.999999776482582,
|
| 2021 |
+
"success_selector_gap": 1.0,
|
| 2022 |
+
"success_support_gap": 0.0,
|
| 2023 |
+
"support_gap": 0.0,
|
| 2024 |
+
"tau": 0.3922077221501807
|
| 2025 |
+
},
|
| 2026 |
+
"509430392/train1": {
|
| 2027 |
+
"base_success": 0.0,
|
| 2028 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2029 |
+
"coverage": 1.0,
|
| 2030 |
+
"execute_generated": 1.0,
|
| 2031 |
+
"fallback_rate": 0.0,
|
| 2032 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2033 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2034 |
+
"outcome_ptr": 1.0,
|
| 2035 |
+
"predicted_margin": 0.48095661365481673,
|
| 2036 |
+
"proposal_oracle_success": 0.0,
|
| 2037 |
+
"proposal_oracle_utility": 6.164610385894775e-05,
|
| 2038 |
+
"selected_candidate_index": 1.0,
|
| 2039 |
+
"selected_success": 0.0,
|
| 2040 |
+
"selected_success_gain_over_base": 0.0,
|
| 2041 |
+
"selected_utility": 3.859400749206543e-06,
|
| 2042 |
+
"selected_utility_gain_over_base": 3.635883331298828e-06,
|
| 2043 |
+
"selector_regret": 5.778670310974121e-05,
|
| 2044 |
+
"success_selector_gap": 0.0,
|
| 2045 |
+
"success_support_gap": 1.0,
|
| 2046 |
+
"support_gap": 1.999938353896141,
|
| 2047 |
+
"tau": 0.3922077221501807
|
| 2048 |
+
},
|
| 2049 |
+
"509430392/train2": {
|
| 2050 |
+
"base_success": 0.0,
|
| 2051 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2052 |
+
"coverage": 1.0,
|
| 2053 |
+
"execute_generated": 1.0,
|
| 2054 |
+
"fallback_rate": 0.0,
|
| 2055 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2056 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2057 |
+
"outcome_ptr": 1.0,
|
| 2058 |
+
"predicted_margin": 0.4130661343747538,
|
| 2059 |
+
"proposal_oracle_success": 0.0,
|
| 2060 |
+
"proposal_oracle_utility": 5.424022674560547e-06,
|
| 2061 |
+
"selected_candidate_index": 1.0,
|
| 2062 |
+
"selected_success": 0.0,
|
| 2063 |
+
"selected_success_gain_over_base": 0.0,
|
| 2064 |
+
"selected_utility": 2.086162567138672e-07,
|
| 2065 |
+
"selected_utility_gain_over_base": -1.4901161193847656e-08,
|
| 2066 |
+
"selector_regret": 5.21540641784668e-06,
|
| 2067 |
+
"success_selector_gap": 0.0,
|
| 2068 |
+
"success_support_gap": 1.0,
|
| 2069 |
+
"support_gap": 1.9999945759773254,
|
| 2070 |
+
"tau": 0.3922077221501807
|
| 2071 |
+
},
|
| 2072 |
+
"585904130/train0": {
|
| 2073 |
+
"base_success": 0.0,
|
| 2074 |
+
"base_utility": 0.18171554803848267,
|
| 2075 |
+
"coverage": 0.0,
|
| 2076 |
+
"execute_generated": 0.0,
|
| 2077 |
+
"fallback_rate": 1.0,
|
| 2078 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2079 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2080 |
+
"outcome_ptr": 1.0,
|
| 2081 |
+
"predicted_margin": 0.14570795144295595,
|
| 2082 |
+
"proposal_oracle_success": 1.0,
|
| 2083 |
+
"proposal_oracle_utility": 2.0,
|
| 2084 |
+
"selected_candidate_index": 6.0,
|
| 2085 |
+
"selected_success": 0.0,
|
| 2086 |
+
"selected_success_gain_over_base": 0.0,
|
| 2087 |
+
"selected_utility": 0.18171554803848267,
|
| 2088 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2089 |
+
"selector_regret": 1.8182844519615173,
|
| 2090 |
+
"success_selector_gap": 1.0,
|
| 2091 |
+
"success_support_gap": 0.0,
|
| 2092 |
+
"support_gap": 0.0,
|
| 2093 |
+
"tau": 0.3922077221501807
|
| 2094 |
+
},
|
| 2095 |
+
"585904130/train1": {
|
| 2096 |
+
"base_success": 0.0,
|
| 2097 |
+
"base_utility": 0.18171554803848267,
|
| 2098 |
+
"coverage": 0.0,
|
| 2099 |
+
"execute_generated": 0.0,
|
| 2100 |
+
"fallback_rate": 1.0,
|
| 2101 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2102 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2103 |
+
"outcome_ptr": 1.0,
|
| 2104 |
+
"predicted_margin": 0.13025881718454488,
|
| 2105 |
+
"proposal_oracle_success": 1.0,
|
| 2106 |
+
"proposal_oracle_utility": 2.0,
|
| 2107 |
+
"selected_candidate_index": 6.0,
|
| 2108 |
+
"selected_success": 0.0,
|
| 2109 |
+
"selected_success_gain_over_base": 0.0,
|
| 2110 |
+
"selected_utility": 0.18171554803848267,
|
| 2111 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2112 |
+
"selector_regret": 1.8182844519615173,
|
| 2113 |
+
"success_selector_gap": 1.0,
|
| 2114 |
+
"success_support_gap": 0.0,
|
| 2115 |
+
"support_gap": 0.0,
|
| 2116 |
+
"tau": 0.3922077221501807
|
| 2117 |
+
},
|
| 2118 |
+
"585904130/train2": {
|
| 2119 |
+
"base_success": 0.0,
|
| 2120 |
+
"base_utility": 0.18171554803848267,
|
| 2121 |
+
"coverage": 0.0,
|
| 2122 |
+
"execute_generated": 0.0,
|
| 2123 |
+
"fallback_rate": 1.0,
|
| 2124 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2125 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2126 |
+
"outcome_ptr": 1.0,
|
| 2127 |
+
"predicted_margin": 0.13670900583373838,
|
| 2128 |
+
"proposal_oracle_success": 1.0,
|
| 2129 |
+
"proposal_oracle_utility": 2.0,
|
| 2130 |
+
"selected_candidate_index": 2.0,
|
| 2131 |
+
"selected_success": 0.0,
|
| 2132 |
+
"selected_success_gain_over_base": 0.0,
|
| 2133 |
+
"selected_utility": 0.18171554803848267,
|
| 2134 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2135 |
+
"selector_regret": 1.8182844519615173,
|
| 2136 |
+
"success_selector_gap": 1.0,
|
| 2137 |
+
"success_support_gap": 0.0,
|
| 2138 |
+
"support_gap": 0.0,
|
| 2139 |
+
"tau": 0.3922077221501807
|
| 2140 |
+
},
|
| 2141 |
+
"608016290/train0": {
|
| 2142 |
+
"base_success": 0.0,
|
| 2143 |
+
"base_utility": 0.725701630115509,
|
| 2144 |
+
"coverage": 1.0,
|
| 2145 |
+
"execute_generated": 1.0,
|
| 2146 |
+
"fallback_rate": 0.0,
|
| 2147 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2148 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2149 |
+
"outcome_ptr": 1.0,
|
| 2150 |
+
"predicted_margin": 0.48980866861669325,
|
| 2151 |
+
"proposal_oracle_success": 1.0,
|
| 2152 |
+
"proposal_oracle_utility": 2.0,
|
| 2153 |
+
"selected_candidate_index": 5.0,
|
| 2154 |
+
"selected_success": 1.0,
|
| 2155 |
+
"selected_success_gain_over_base": 1.0,
|
| 2156 |
+
"selected_utility": 2.0,
|
| 2157 |
+
"selected_utility_gain_over_base": 1.274298369884491,
|
| 2158 |
+
"selector_regret": 0.0,
|
| 2159 |
+
"success_selector_gap": 0.0,
|
| 2160 |
+
"success_support_gap": 0.0,
|
| 2161 |
+
"support_gap": 0.0,
|
| 2162 |
+
"tau": 0.3922077221501807
|
| 2163 |
+
},
|
| 2164 |
+
"608016290/train1": {
|
| 2165 |
+
"base_success": 0.0,
|
| 2166 |
+
"base_utility": 0.725701630115509,
|
| 2167 |
+
"coverage": 1.0,
|
| 2168 |
+
"execute_generated": 1.0,
|
| 2169 |
+
"fallback_rate": 0.0,
|
| 2170 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2171 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2172 |
+
"outcome_ptr": 1.0,
|
| 2173 |
+
"predicted_margin": 0.5371887230564292,
|
| 2174 |
+
"proposal_oracle_success": 1.0,
|
| 2175 |
+
"proposal_oracle_utility": 2.0,
|
| 2176 |
+
"selected_candidate_index": 5.0,
|
| 2177 |
+
"selected_success": 0.0,
|
| 2178 |
+
"selected_success_gain_over_base": 0.0,
|
| 2179 |
+
"selected_utility": 0.7106016278266907,
|
| 2180 |
+
"selected_utility_gain_over_base": -0.01510000228881836,
|
| 2181 |
+
"selector_regret": 1.2893983721733093,
|
| 2182 |
+
"success_selector_gap": 1.0,
|
| 2183 |
+
"success_support_gap": 0.0,
|
| 2184 |
+
"support_gap": 0.0,
|
| 2185 |
+
"tau": 0.3922077221501807
|
| 2186 |
+
},
|
| 2187 |
+
"608016290/train2": {
|
| 2188 |
+
"base_success": 0.0,
|
| 2189 |
+
"base_utility": 0.725701630115509,
|
| 2190 |
+
"coverage": 0.0,
|
| 2191 |
+
"execute_generated": 0.0,
|
| 2192 |
+
"fallback_rate": 1.0,
|
| 2193 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2194 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2195 |
+
"outcome_ptr": 0.0,
|
| 2196 |
+
"predicted_margin": 0.36071199999780773,
|
| 2197 |
+
"proposal_oracle_success": 0.0,
|
| 2198 |
+
"proposal_oracle_utility": 0.6825780272483826,
|
| 2199 |
+
"selected_candidate_index": 6.0,
|
| 2200 |
+
"selected_success": 0.0,
|
| 2201 |
+
"selected_success_gain_over_base": 0.0,
|
| 2202 |
+
"selected_utility": 0.725701630115509,
|
| 2203 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2204 |
+
"selector_regret": 0.0,
|
| 2205 |
+
"success_selector_gap": 0.0,
|
| 2206 |
+
"success_support_gap": 1.0,
|
| 2207 |
+
"support_gap": 1.3174219727516174,
|
| 2208 |
+
"tau": 0.3922077221501807
|
| 2209 |
+
},
|
| 2210 |
+
"626486813/train0": {
|
| 2211 |
+
"base_success": 0.0,
|
| 2212 |
+
"base_utility": 0.00509834272088483,
|
| 2213 |
+
"coverage": 0.0,
|
| 2214 |
+
"execute_generated": 0.0,
|
| 2215 |
+
"fallback_rate": 1.0,
|
| 2216 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2217 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2218 |
+
"outcome_ptr": 1.0,
|
| 2219 |
+
"predicted_margin": 0.15951591915273888,
|
| 2220 |
+
"proposal_oracle_success": 0.0,
|
| 2221 |
+
"proposal_oracle_utility": 0.043898362666368484,
|
| 2222 |
+
"selected_candidate_index": 3.5,
|
| 2223 |
+
"selected_success": 0.0,
|
| 2224 |
+
"selected_success_gain_over_base": 0.0,
|
| 2225 |
+
"selected_utility": 0.00509834272088483,
|
| 2226 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2227 |
+
"selector_regret": 0.038800019945483655,
|
| 2228 |
+
"success_selector_gap": 0.0,
|
| 2229 |
+
"success_support_gap": 0.0,
|
| 2230 |
+
"support_gap": 0.12241578102111816,
|
| 2231 |
+
"tau": 0.3922077221501807
|
| 2232 |
+
},
|
| 2233 |
+
"626486813/train1": {
|
| 2234 |
+
"base_success": 0.0,
|
| 2235 |
+
"base_utility": 0.00509834272088483,
|
| 2236 |
+
"coverage": 1.0,
|
| 2237 |
+
"execute_generated": 1.0,
|
| 2238 |
+
"fallback_rate": 0.0,
|
| 2239 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2240 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2241 |
+
"outcome_ptr": 1.0,
|
| 2242 |
+
"predicted_margin": 0.5225744758159157,
|
| 2243 |
+
"proposal_oracle_success": 0.0,
|
| 2244 |
+
"proposal_oracle_utility": 0.030555277597159147,
|
| 2245 |
+
"selected_candidate_index": 0.5,
|
| 2246 |
+
"selected_success": 0.0,
|
| 2247 |
+
"selected_success_gain_over_base": 0.0,
|
| 2248 |
+
"selected_utility": 0.014558643568307161,
|
| 2249 |
+
"selected_utility_gain_over_base": 0.009460300847422332,
|
| 2250 |
+
"selector_regret": 0.015996634028851986,
|
| 2251 |
+
"success_selector_gap": 0.0,
|
| 2252 |
+
"success_support_gap": 0.0,
|
| 2253 |
+
"support_gap": 0.13502710359171033,
|
| 2254 |
+
"tau": 0.3922077221501807
|
| 2255 |
+
},
|
| 2256 |
+
"626486813/train2": {
|
| 2257 |
+
"base_success": 0.0,
|
| 2258 |
+
"base_utility": 0.00509834272088483,
|
| 2259 |
+
"coverage": 0.5,
|
| 2260 |
+
"execute_generated": 0.5,
|
| 2261 |
+
"fallback_rate": 0.5,
|
| 2262 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2263 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2264 |
+
"outcome_ptr": 1.0,
|
| 2265 |
+
"predicted_margin": 0.6387208599736448,
|
| 2266 |
+
"proposal_oracle_success": 0.0,
|
| 2267 |
+
"proposal_oracle_utility": 0.03856666944921017,
|
| 2268 |
+
"selected_candidate_index": 3.5,
|
| 2269 |
+
"selected_success": 0.0,
|
| 2270 |
+
"selected_success_gain_over_base": 0.0,
|
| 2271 |
+
"selected_utility": 0.01586466981098056,
|
| 2272 |
+
"selected_utility_gain_over_base": 0.010766327090095729,
|
| 2273 |
+
"selector_regret": 0.02270199963822961,
|
| 2274 |
+
"success_selector_gap": 0.0,
|
| 2275 |
+
"success_support_gap": 0.0,
|
| 2276 |
+
"support_gap": 0.1270157117396593,
|
| 2277 |
+
"tau": 0.3922077221501807
|
| 2278 |
+
},
|
| 2279 |
+
"636680137/train0": {
|
| 2280 |
+
"base_success": 0.0,
|
| 2281 |
+
"base_utility": 0.08313504606485367,
|
| 2282 |
+
"coverage": 0.0,
|
| 2283 |
+
"execute_generated": 0.0,
|
| 2284 |
+
"fallback_rate": 1.0,
|
| 2285 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2286 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2287 |
+
"outcome_ptr": 1.0,
|
| 2288 |
+
"predicted_margin": 0.23786709945842635,
|
| 2289 |
+
"proposal_oracle_success": 0.0,
|
| 2290 |
+
"proposal_oracle_utility": 0.08826130628585815,
|
| 2291 |
+
"selected_candidate_index": 1.0,
|
| 2292 |
+
"selected_success": 0.0,
|
| 2293 |
+
"selected_success_gain_over_base": 0.0,
|
| 2294 |
+
"selected_utility": 0.08313504606485367,
|
| 2295 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2296 |
+
"selector_regret": 0.005126260221004486,
|
| 2297 |
+
"success_selector_gap": 0.0,
|
| 2298 |
+
"success_support_gap": 0.0,
|
| 2299 |
+
"support_gap": 0.0823030173778534,
|
| 2300 |
+
"tau": 0.3922077221501807
|
| 2301 |
+
},
|
| 2302 |
+
"636680137/train1": {
|
| 2303 |
+
"base_success": 0.0,
|
| 2304 |
+
"base_utility": 0.08313504606485367,
|
| 2305 |
+
"coverage": 0.0,
|
| 2306 |
+
"execute_generated": 0.0,
|
| 2307 |
+
"fallback_rate": 1.0,
|
| 2308 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2309 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2310 |
+
"outcome_ptr": 0.0,
|
| 2311 |
+
"predicted_margin": 0.028828471726532103,
|
| 2312 |
+
"proposal_oracle_success": 0.0,
|
| 2313 |
+
"proposal_oracle_utility": 0.06741118431091309,
|
| 2314 |
+
"selected_candidate_index": 0.0,
|
| 2315 |
+
"selected_success": 0.0,
|
| 2316 |
+
"selected_success_gain_over_base": 0.0,
|
| 2317 |
+
"selected_utility": 0.08313504606485367,
|
| 2318 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2319 |
+
"selector_regret": 0.0,
|
| 2320 |
+
"success_selector_gap": 0.0,
|
| 2321 |
+
"success_support_gap": 0.0,
|
| 2322 |
+
"support_gap": 0.10315313935279846,
|
| 2323 |
+
"tau": 0.3922077221501807
|
| 2324 |
+
},
|
| 2325 |
+
"636680137/train2": {
|
| 2326 |
+
"base_success": 0.0,
|
| 2327 |
+
"base_utility": 0.08313504606485367,
|
| 2328 |
+
"coverage": 0.0,
|
| 2329 |
+
"execute_generated": 0.0,
|
| 2330 |
+
"fallback_rate": 1.0,
|
| 2331 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2332 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2333 |
+
"outcome_ptr": 0.0,
|
| 2334 |
+
"predicted_margin": 0.03447268272608085,
|
| 2335 |
+
"proposal_oracle_success": 0.0,
|
| 2336 |
+
"proposal_oracle_utility": 0.0756516233086586,
|
| 2337 |
+
"selected_candidate_index": 7.0,
|
| 2338 |
+
"selected_success": 0.0,
|
| 2339 |
+
"selected_success_gain_over_base": 0.0,
|
| 2340 |
+
"selected_utility": 0.08313504606485367,
|
| 2341 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2342 |
+
"selector_regret": 0.0,
|
| 2343 |
+
"success_selector_gap": 0.0,
|
| 2344 |
+
"success_support_gap": 0.0,
|
| 2345 |
+
"support_gap": 0.09491270035505295,
|
| 2346 |
+
"tau": 0.3922077221501807
|
| 2347 |
+
},
|
| 2348 |
+
"655884605/train0": {
|
| 2349 |
+
"base_success": 0.0,
|
| 2350 |
+
"base_utility": 0.16300667822360992,
|
| 2351 |
+
"coverage": 0.0,
|
| 2352 |
+
"execute_generated": 0.0,
|
| 2353 |
+
"fallback_rate": 1.0,
|
| 2354 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2355 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2356 |
+
"outcome_ptr": 0.0,
|
| 2357 |
+
"predicted_margin": 0.11644412243113883,
|
| 2358 |
+
"proposal_oracle_success": 0.0,
|
| 2359 |
+
"proposal_oracle_utility": 0.13732868432998657,
|
| 2360 |
+
"selected_candidate_index": 7.0,
|
| 2361 |
+
"selected_success": 0.0,
|
| 2362 |
+
"selected_success_gain_over_base": 0.0,
|
| 2363 |
+
"selected_utility": 0.16300667822360992,
|
| 2364 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2365 |
+
"selector_regret": 0.0,
|
| 2366 |
+
"success_selector_gap": 0.0,
|
| 2367 |
+
"success_support_gap": 1.0,
|
| 2368 |
+
"support_gap": 1.8626713156700134,
|
| 2369 |
+
"tau": 0.3922077221501807
|
| 2370 |
+
},
|
| 2371 |
+
"655884605/train1": {
|
| 2372 |
+
"base_success": 0.0,
|
| 2373 |
+
"base_utility": 0.16300667822360992,
|
| 2374 |
+
"coverage": 0.0,
|
| 2375 |
+
"execute_generated": 0.0,
|
| 2376 |
+
"fallback_rate": 1.0,
|
| 2377 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2378 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2379 |
+
"outcome_ptr": 1.0,
|
| 2380 |
+
"predicted_margin": 0.3313079469073425,
|
| 2381 |
+
"proposal_oracle_success": 0.0,
|
| 2382 |
+
"proposal_oracle_utility": 0.1651531159877777,
|
| 2383 |
+
"selected_candidate_index": 3.0,
|
| 2384 |
+
"selected_success": 0.0,
|
| 2385 |
+
"selected_success_gain_over_base": 0.0,
|
| 2386 |
+
"selected_utility": 0.16300667822360992,
|
| 2387 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2388 |
+
"selector_regret": 0.0021464377641677856,
|
| 2389 |
+
"success_selector_gap": 0.0,
|
| 2390 |
+
"success_support_gap": 1.0,
|
| 2391 |
+
"support_gap": 1.8348468840122223,
|
| 2392 |
+
"tau": 0.3922077221501807
|
| 2393 |
+
},
|
| 2394 |
+
"655884605/train2": {
|
| 2395 |
+
"base_success": 0.0,
|
| 2396 |
+
"base_utility": 0.16300667822360992,
|
| 2397 |
+
"coverage": 0.0,
|
| 2398 |
+
"execute_generated": 0.0,
|
| 2399 |
+
"fallback_rate": 1.0,
|
| 2400 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2401 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2402 |
+
"outcome_ptr": 1.0,
|
| 2403 |
+
"predicted_margin": 0.13703413820966903,
|
| 2404 |
+
"proposal_oracle_success": 0.0,
|
| 2405 |
+
"proposal_oracle_utility": 0.21447330713272095,
|
| 2406 |
+
"selected_candidate_index": 1.0,
|
| 2407 |
+
"selected_success": 0.0,
|
| 2408 |
+
"selected_success_gain_over_base": 0.0,
|
| 2409 |
+
"selected_utility": 0.16300667822360992,
|
| 2410 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2411 |
+
"selector_regret": 0.05146662890911102,
|
| 2412 |
+
"success_selector_gap": 0.0,
|
| 2413 |
+
"success_support_gap": 1.0,
|
| 2414 |
+
"support_gap": 1.785526692867279,
|
| 2415 |
+
"tau": 0.3922077221501807
|
| 2416 |
+
},
|
| 2417 |
+
"672328262/train0": {
|
| 2418 |
+
"base_success": 1.0,
|
| 2419 |
+
"base_utility": 2.0,
|
| 2420 |
+
"coverage": 0.0,
|
| 2421 |
+
"execute_generated": 0.0,
|
| 2422 |
+
"fallback_rate": 1.0,
|
| 2423 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2424 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2425 |
+
"outcome_ptr": 0.0,
|
| 2426 |
+
"predicted_margin": 0.013741725805362232,
|
| 2427 |
+
"proposal_oracle_success": 1.0,
|
| 2428 |
+
"proposal_oracle_utility": 2.0,
|
| 2429 |
+
"selected_candidate_index": 1.0,
|
| 2430 |
+
"selected_success": 1.0,
|
| 2431 |
+
"selected_success_gain_over_base": 0.0,
|
| 2432 |
+
"selected_utility": 2.0,
|
| 2433 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2434 |
+
"selector_regret": 0.0,
|
| 2435 |
+
"success_selector_gap": 0.0,
|
| 2436 |
+
"success_support_gap": 0.0,
|
| 2437 |
+
"support_gap": 0.0,
|
| 2438 |
+
"tau": 0.3922077221501807
|
| 2439 |
+
},
|
| 2440 |
+
"672328262/train1": {
|
| 2441 |
+
"base_success": 1.0,
|
| 2442 |
+
"base_utility": 2.0,
|
| 2443 |
+
"coverage": 0.0,
|
| 2444 |
+
"execute_generated": 0.0,
|
| 2445 |
+
"fallback_rate": 1.0,
|
| 2446 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2447 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2448 |
+
"outcome_ptr": 0.0,
|
| 2449 |
+
"predicted_margin": 0.02329630246988514,
|
| 2450 |
+
"proposal_oracle_success": 1.0,
|
| 2451 |
+
"proposal_oracle_utility": 2.0,
|
| 2452 |
+
"selected_candidate_index": 7.0,
|
| 2453 |
+
"selected_success": 1.0,
|
| 2454 |
+
"selected_success_gain_over_base": 0.0,
|
| 2455 |
+
"selected_utility": 2.0,
|
| 2456 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2457 |
+
"selector_regret": 0.0,
|
| 2458 |
+
"success_selector_gap": 0.0,
|
| 2459 |
+
"success_support_gap": 0.0,
|
| 2460 |
+
"support_gap": 0.0,
|
| 2461 |
+
"tau": 0.3922077221501807
|
| 2462 |
+
},
|
| 2463 |
+
"672328262/train2": {
|
| 2464 |
+
"base_success": 1.0,
|
| 2465 |
+
"base_utility": 2.0,
|
| 2466 |
+
"coverage": 0.0,
|
| 2467 |
+
"execute_generated": 0.0,
|
| 2468 |
+
"fallback_rate": 1.0,
|
| 2469 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2470 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2471 |
+
"outcome_ptr": 0.0,
|
| 2472 |
+
"predicted_margin": 0.09143350660756332,
|
| 2473 |
+
"proposal_oracle_success": 1.0,
|
| 2474 |
+
"proposal_oracle_utility": 2.0,
|
| 2475 |
+
"selected_candidate_index": 2.0,
|
| 2476 |
+
"selected_success": 1.0,
|
| 2477 |
+
"selected_success_gain_over_base": 0.0,
|
| 2478 |
+
"selected_utility": 2.0,
|
| 2479 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2480 |
+
"selector_regret": 0.0,
|
| 2481 |
+
"success_selector_gap": 0.0,
|
| 2482 |
+
"success_support_gap": 0.0,
|
| 2483 |
+
"support_gap": 0.0,
|
| 2484 |
+
"tau": 0.3922077221501807
|
| 2485 |
+
},
|
| 2486 |
+
"701667486/train0": {
|
| 2487 |
+
"base_success": 1.0,
|
| 2488 |
+
"base_utility": 2.0,
|
| 2489 |
+
"coverage": 0.0,
|
| 2490 |
+
"execute_generated": 0.0,
|
| 2491 |
+
"fallback_rate": 1.0,
|
| 2492 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2493 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2494 |
+
"outcome_ptr": 0.0,
|
| 2495 |
+
"predicted_margin": 0.3623892596852855,
|
| 2496 |
+
"proposal_oracle_success": 1.0,
|
| 2497 |
+
"proposal_oracle_utility": 2.0,
|
| 2498 |
+
"selected_candidate_index": 6.0,
|
| 2499 |
+
"selected_success": 1.0,
|
| 2500 |
+
"selected_success_gain_over_base": 0.0,
|
| 2501 |
+
"selected_utility": 2.0,
|
| 2502 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2503 |
+
"selector_regret": 0.0,
|
| 2504 |
+
"success_selector_gap": 0.0,
|
| 2505 |
+
"success_support_gap": 0.0,
|
| 2506 |
+
"support_gap": 0.0,
|
| 2507 |
+
"tau": 0.3922077221501807
|
| 2508 |
+
},
|
| 2509 |
+
"701667486/train1": {
|
| 2510 |
+
"base_success": 1.0,
|
| 2511 |
+
"base_utility": 2.0,
|
| 2512 |
+
"coverage": 1.0,
|
| 2513 |
+
"execute_generated": 1.0,
|
| 2514 |
+
"fallback_rate": 0.0,
|
| 2515 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2516 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2517 |
+
"outcome_ptr": 0.0,
|
| 2518 |
+
"predicted_margin": 0.49759192030497695,
|
| 2519 |
+
"proposal_oracle_success": 1.0,
|
| 2520 |
+
"proposal_oracle_utility": 2.0,
|
| 2521 |
+
"selected_candidate_index": 3.0,
|
| 2522 |
+
"selected_success": 1.0,
|
| 2523 |
+
"selected_success_gain_over_base": 0.0,
|
| 2524 |
+
"selected_utility": 2.0,
|
| 2525 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2526 |
+
"selector_regret": 0.0,
|
| 2527 |
+
"success_selector_gap": 0.0,
|
| 2528 |
+
"success_support_gap": 0.0,
|
| 2529 |
+
"support_gap": 0.0,
|
| 2530 |
+
"tau": 0.3922077221501807
|
| 2531 |
+
},
|
| 2532 |
+
"701667486/train2": {
|
| 2533 |
+
"base_success": 1.0,
|
| 2534 |
+
"base_utility": 2.0,
|
| 2535 |
+
"coverage": 1.0,
|
| 2536 |
+
"execute_generated": 1.0,
|
| 2537 |
+
"fallback_rate": 0.0,
|
| 2538 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2539 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2540 |
+
"outcome_ptr": 0.0,
|
| 2541 |
+
"predicted_margin": 0.5318850101332178,
|
| 2542 |
+
"proposal_oracle_success": 1.0,
|
| 2543 |
+
"proposal_oracle_utility": 2.0,
|
| 2544 |
+
"selected_candidate_index": 2.0,
|
| 2545 |
+
"selected_success": 1.0,
|
| 2546 |
+
"selected_success_gain_over_base": 0.0,
|
| 2547 |
+
"selected_utility": 2.0,
|
| 2548 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2549 |
+
"selector_regret": 0.0,
|
| 2550 |
+
"success_selector_gap": 0.0,
|
| 2551 |
+
"success_support_gap": 0.0,
|
| 2552 |
+
"support_gap": 0.0,
|
| 2553 |
+
"tau": 0.3922077221501807
|
| 2554 |
+
},
|
| 2555 |
+
"747260437/train0": {
|
| 2556 |
+
"base_success": 1.0,
|
| 2557 |
+
"base_utility": 2.0,
|
| 2558 |
+
"coverage": 0.0,
|
| 2559 |
+
"execute_generated": 0.0,
|
| 2560 |
+
"fallback_rate": 1.0,
|
| 2561 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2562 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2563 |
+
"outcome_ptr": 0.0,
|
| 2564 |
+
"predicted_margin": 0.09061742718972163,
|
| 2565 |
+
"proposal_oracle_success": 0.0,
|
| 2566 |
+
"proposal_oracle_utility": 0.10839563608169556,
|
| 2567 |
+
"selected_candidate_index": 6.0,
|
| 2568 |
+
"selected_success": 1.0,
|
| 2569 |
+
"selected_success_gain_over_base": 0.0,
|
| 2570 |
+
"selected_utility": 2.0,
|
| 2571 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2572 |
+
"selector_regret": 0.0,
|
| 2573 |
+
"success_selector_gap": 0.0,
|
| 2574 |
+
"success_support_gap": 0.0,
|
| 2575 |
+
"support_gap": 0.17026761174201965,
|
| 2576 |
+
"tau": 0.3922077221501807
|
| 2577 |
+
},
|
| 2578 |
+
"747260437/train1": {
|
| 2579 |
+
"base_success": 1.0,
|
| 2580 |
+
"base_utility": 2.0,
|
| 2581 |
+
"coverage": 0.0,
|
| 2582 |
+
"execute_generated": 0.0,
|
| 2583 |
+
"fallback_rate": 1.0,
|
| 2584 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2585 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2586 |
+
"outcome_ptr": 0.0,
|
| 2587 |
+
"predicted_margin": 0.11304511097648247,
|
| 2588 |
+
"proposal_oracle_success": 0.0,
|
| 2589 |
+
"proposal_oracle_utility": 0.05267423391342163,
|
| 2590 |
+
"selected_candidate_index": 7.0,
|
| 2591 |
+
"selected_success": 1.0,
|
| 2592 |
+
"selected_success_gain_over_base": 0.0,
|
| 2593 |
+
"selected_utility": 2.0,
|
| 2594 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2595 |
+
"selector_regret": 0.0,
|
| 2596 |
+
"success_selector_gap": 0.0,
|
| 2597 |
+
"success_support_gap": 0.0,
|
| 2598 |
+
"support_gap": 0.22598901391029358,
|
| 2599 |
+
"tau": 0.3922077221501807
|
| 2600 |
+
},
|
| 2601 |
+
"747260437/train2": {
|
| 2602 |
+
"base_success": 1.0,
|
| 2603 |
+
"base_utility": 2.0,
|
| 2604 |
+
"coverage": 0.0,
|
| 2605 |
+
"execute_generated": 0.0,
|
| 2606 |
+
"fallback_rate": 1.0,
|
| 2607 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2608 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2609 |
+
"outcome_ptr": 0.0,
|
| 2610 |
+
"predicted_margin": 0.0956815945055245,
|
| 2611 |
+
"proposal_oracle_success": 0.0,
|
| 2612 |
+
"proposal_oracle_utility": 0.12510187923908234,
|
| 2613 |
+
"selected_candidate_index": 7.0,
|
| 2614 |
+
"selected_success": 1.0,
|
| 2615 |
+
"selected_success_gain_over_base": 0.0,
|
| 2616 |
+
"selected_utility": 2.0,
|
| 2617 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2618 |
+
"selector_regret": 0.0,
|
| 2619 |
+
"success_selector_gap": 0.0,
|
| 2620 |
+
"success_support_gap": 0.0,
|
| 2621 |
+
"support_gap": 0.15356136858463287,
|
| 2622 |
+
"tau": 0.3922077221501807
|
| 2623 |
+
},
|
| 2624 |
+
"750448296/train0": {
|
| 2625 |
+
"base_success": 0.0,
|
| 2626 |
+
"base_utility": 0.11759314934412639,
|
| 2627 |
+
"coverage": 0.0,
|
| 2628 |
+
"execute_generated": 0.0,
|
| 2629 |
+
"fallback_rate": 1.0,
|
| 2630 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2631 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2632 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2633 |
+
"predicted_margin": 0.12788608286667172,
|
| 2634 |
+
"proposal_oracle_success": 0.3333333333333333,
|
| 2635 |
+
"proposal_oracle_utility": 0.7526603279014429,
|
| 2636 |
+
"selected_candidate_index": 2.0,
|
| 2637 |
+
"selected_success": 0.0,
|
| 2638 |
+
"selected_success_gain_over_base": 0.0,
|
| 2639 |
+
"selected_utility": 0.11759314934412639,
|
| 2640 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2641 |
+
"selector_regret": 0.6522682110468546,
|
| 2642 |
+
"success_selector_gap": 0.3333333333333333,
|
| 2643 |
+
"success_support_gap": 0.3333333333333333,
|
| 2644 |
+
"support_gap": 0.6553361676633358,
|
| 2645 |
+
"tau": 0.3922077221501807
|
| 2646 |
+
},
|
| 2647 |
+
"750448296/train1": {
|
| 2648 |
+
"base_success": 0.0,
|
| 2649 |
+
"base_utility": 0.11759314934412639,
|
| 2650 |
+
"coverage": 0.3333333333333333,
|
| 2651 |
+
"execute_generated": 0.3333333333333333,
|
| 2652 |
+
"fallback_rate": 0.6666666666666666,
|
| 2653 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2654 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2655 |
+
"outcome_ptr": 1.0,
|
| 2656 |
+
"predicted_margin": 0.3189696928758093,
|
| 2657 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2658 |
+
"proposal_oracle_utility": 1.3705032741030057,
|
| 2659 |
+
"selected_candidate_index": 2.3333333333333335,
|
| 2660 |
+
"selected_success": 0.0,
|
| 2661 |
+
"selected_success_gain_over_base": 0.0,
|
| 2662 |
+
"selected_utility": 0.11618362615505855,
|
| 2663 |
+
"selected_utility_gain_over_base": -0.0014095231890678406,
|
| 2664 |
+
"selector_regret": 1.2543196479479473,
|
| 2665 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2666 |
+
"success_support_gap": 0.0,
|
| 2667 |
+
"support_gap": 0.03749322146177292,
|
| 2668 |
+
"tau": 0.3922077221501807
|
| 2669 |
+
},
|
| 2670 |
+
"750448296/train2": {
|
| 2671 |
+
"base_success": 0.0,
|
| 2672 |
+
"base_utility": 0.11759314934412639,
|
| 2673 |
+
"coverage": 0.3333333333333333,
|
| 2674 |
+
"execute_generated": 0.3333333333333333,
|
| 2675 |
+
"fallback_rate": 0.6666666666666666,
|
| 2676 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2677 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2678 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2679 |
+
"predicted_margin": 0.40623008140503125,
|
| 2680 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2681 |
+
"proposal_oracle_utility": 1.349846323331197,
|
| 2682 |
+
"selected_candidate_index": 2.3333333333333335,
|
| 2683 |
+
"selected_success": 0.0,
|
| 2684 |
+
"selected_success_gain_over_base": 0.0,
|
| 2685 |
+
"selected_utility": 0.10310697555541992,
|
| 2686 |
+
"selected_utility_gain_over_base": -0.014486173788706461,
|
| 2687 |
+
"selector_regret": 1.246739347775777,
|
| 2688 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2689 |
+
"success_support_gap": 0.0,
|
| 2690 |
+
"support_gap": 0.05815017223358154,
|
| 2691 |
+
"tau": 0.3922077221501807
|
| 2692 |
+
},
|
| 2693 |
+
"767747424/train0": {
|
| 2694 |
+
"base_success": 0.25,
|
| 2695 |
+
"base_utility": 0.5731993420049548,
|
| 2696 |
+
"coverage": 0.25,
|
| 2697 |
+
"execute_generated": 0.25,
|
| 2698 |
+
"fallback_rate": 0.75,
|
| 2699 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2700 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2701 |
+
"outcome_ptr": 0.5,
|
| 2702 |
+
"predicted_margin": 0.18007551437475325,
|
| 2703 |
+
"proposal_oracle_success": 0.5,
|
| 2704 |
+
"proposal_oracle_utility": 1.0424291878007352,
|
| 2705 |
+
"selected_candidate_index": 4.0,
|
| 2706 |
+
"selected_success": 0.25,
|
| 2707 |
+
"selected_success_gain_over_base": 0.0,
|
| 2708 |
+
"selected_utility": 0.5665665380656719,
|
| 2709 |
+
"selected_utility_gain_over_base": -0.006632803939282894,
|
| 2710 |
+
"selector_regret": 0.4845929266884923,
|
| 2711 |
+
"success_selector_gap": 0.25,
|
| 2712 |
+
"success_support_gap": 0.0,
|
| 2713 |
+
"support_gap": 0.06562284985557199,
|
| 2714 |
+
"tau": 0.3922077221501807
|
| 2715 |
+
},
|
| 2716 |
+
"767747424/train1": {
|
| 2717 |
+
"base_success": 0.25,
|
| 2718 |
+
"base_utility": 0.5731993420049548,
|
| 2719 |
+
"coverage": 0.5,
|
| 2720 |
+
"execute_generated": 0.5,
|
| 2721 |
+
"fallback_rate": 0.5,
|
| 2722 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2723 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2724 |
+
"outcome_ptr": 0.25,
|
| 2725 |
+
"predicted_margin": 0.34189408216351075,
|
| 2726 |
+
"proposal_oracle_success": 0.25,
|
| 2727 |
+
"proposal_oracle_utility": 0.5951075805351138,
|
| 2728 |
+
"selected_candidate_index": 3.0,
|
| 2729 |
+
"selected_success": 0.25,
|
| 2730 |
+
"selected_success_gain_over_base": 0.0,
|
| 2731 |
+
"selected_utility": 0.5778386716265231,
|
| 2732 |
+
"selected_utility_gain_over_base": 0.004639329621568322,
|
| 2733 |
+
"selector_regret": 0.025535901775583625,
|
| 2734 |
+
"success_selector_gap": 0.0,
|
| 2735 |
+
"success_support_gap": 0.25,
|
| 2736 |
+
"support_gap": 0.5129444571211934,
|
| 2737 |
+
"tau": 0.3922077221501807
|
| 2738 |
+
},
|
| 2739 |
+
"767747424/train2": {
|
| 2740 |
+
"base_success": 0.25,
|
| 2741 |
+
"base_utility": 0.5731993420049548,
|
| 2742 |
+
"coverage": 0.25,
|
| 2743 |
+
"execute_generated": 0.25,
|
| 2744 |
+
"fallback_rate": 0.75,
|
| 2745 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2746 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2747 |
+
"outcome_ptr": 0.5,
|
| 2748 |
+
"predicted_margin": 0.2562974649152649,
|
| 2749 |
+
"proposal_oracle_success": 0.25,
|
| 2750 |
+
"proposal_oracle_utility": 0.6134321661666036,
|
| 2751 |
+
"selected_candidate_index": 2.5,
|
| 2752 |
+
"selected_success": 0.25,
|
| 2753 |
+
"selected_success_gain_over_base": 0.0,
|
| 2754 |
+
"selected_utility": 0.6018061237409711,
|
| 2755 |
+
"selected_utility_gain_over_base": 0.028606781736016273,
|
| 2756 |
+
"selector_regret": 0.013650141656398773,
|
| 2757 |
+
"success_selector_gap": 0.0,
|
| 2758 |
+
"success_support_gap": 0.25,
|
| 2759 |
+
"support_gap": 0.49461987148970366,
|
| 2760 |
+
"tau": 0.3922077221501807
|
| 2761 |
+
}
|
| 2762 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/metrics_by_task.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"LiftPegUpright-v1": {
|
| 3 |
+
"base_success": 0.2,
|
| 4 |
+
"base_utility": 0.9498705387115478,
|
| 5 |
+
"coverage": 0.9333333333333333,
|
| 6 |
+
"execute_generated": 0.9333333333333333,
|
| 7 |
+
"fallback_rate": 0.06666666666666667,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.4666666666666667,
|
| 11 |
+
"predicted_margin": 0.557946384606131,
|
| 12 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 13 |
+
"proposal_oracle_utility": 1.2244940986235937,
|
| 14 |
+
"selected_candidate_index": 3.8,
|
| 15 |
+
"selected_success": 0.06666666666666667,
|
| 16 |
+
"selected_success_gain_over_base": -0.13333333333333333,
|
| 17 |
+
"selected_utility": 0.6436923642953237,
|
| 18 |
+
"selected_utility_gain_over_base": -0.30617817441622414,
|
| 19 |
+
"selector_regret": 0.5836766411860784,
|
| 20 |
+
"success_selector_gap": 0.4,
|
| 21 |
+
"success_support_gap": 0.5333333333333333,
|
| 22 |
+
"support_gap": 0.7755059013764064,
|
| 23 |
+
"tau": 0.39220772215018057
|
| 24 |
+
},
|
| 25 |
+
"PickCube-v1": {
|
| 26 |
+
"base_success": 0.0,
|
| 27 |
+
"base_utility": 0.5839591026306152,
|
| 28 |
+
"coverage": 0.0,
|
| 29 |
+
"execute_generated": 0.0,
|
| 30 |
+
"fallback_rate": 1.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.08588261185630604,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.13425676027933756,
|
| 37 |
+
"selected_candidate_index": 3.3333333333333335,
|
| 38 |
+
"selected_success": 0.0,
|
| 39 |
+
"selected_success_gain_over_base": 0.0,
|
| 40 |
+
"selected_utility": 0.5839591026306152,
|
| 41 |
+
"selected_utility_gain_over_base": 0.0,
|
| 42 |
+
"selector_regret": 0.0,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.8657432397206624,
|
| 46 |
+
"tau": 0.3922077221501807
|
| 47 |
+
},
|
| 48 |
+
"PullCube-v1": {
|
| 49 |
+
"base_success": 0.36,
|
| 50 |
+
"base_utility": 0.7751704612234608,
|
| 51 |
+
"coverage": 0.30666666666666664,
|
| 52 |
+
"execute_generated": 0.30666666666666664,
|
| 53 |
+
"fallback_rate": 0.6933333333333334,
|
| 54 |
+
"hidden_chart_oracle_success": 0.52,
|
| 55 |
+
"hidden_chart_oracle_utility": 1.1467878860235214,
|
| 56 |
+
"outcome_ptr": 0.44,
|
| 57 |
+
"predicted_margin": 0.3050385214311406,
|
| 58 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 59 |
+
"proposal_oracle_utility": 0.9816135169876119,
|
| 60 |
+
"selected_candidate_index": 3.3333333333333335,
|
| 61 |
+
"selected_success": 0.3333333333333333,
|
| 62 |
+
"selected_success_gain_over_base": -0.02666666666666667,
|
| 63 |
+
"selected_utility": 0.731077126719368,
|
| 64 |
+
"selected_utility_gain_over_base": -0.04409333450409273,
|
| 65 |
+
"selector_regret": 0.35973873146343976,
|
| 66 |
+
"success_selector_gap": 0.18666666666666668,
|
| 67 |
+
"success_support_gap": 0.09333333333333334,
|
| 68 |
+
"support_gap": 0.23527305972451965,
|
| 69 |
+
"tau": 0.39220772215018135
|
| 70 |
+
},
|
| 71 |
+
"PushCube-v1": {
|
| 72 |
+
"base_success": 0.16666666666666666,
|
| 73 |
+
"base_utility": 0.3924041787783305,
|
| 74 |
+
"coverage": 0.7222222222222222,
|
| 75 |
+
"execute_generated": 0.7222222222222222,
|
| 76 |
+
"fallback_rate": 0.2777777777777778,
|
| 77 |
+
"hidden_chart_oracle_success": 0.8333333333333334,
|
| 78 |
+
"hidden_chart_oracle_utility": 1.7015800600250561,
|
| 79 |
+
"outcome_ptr": 0.7777777777777778,
|
| 80 |
+
"predicted_margin": 0.5168934626755944,
|
| 81 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 82 |
+
"proposal_oracle_utility": 1.365773618221283,
|
| 83 |
+
"selected_candidate_index": 2.6666666666666665,
|
| 84 |
+
"selected_success": 0.3333333333333333,
|
| 85 |
+
"selected_success_gain_over_base": 0.16666666666666666,
|
| 86 |
+
"selected_utility": 0.7172343217664294,
|
| 87 |
+
"selected_utility_gain_over_base": 0.324830142988099,
|
| 88 |
+
"selector_regret": 0.6485392964548535,
|
| 89 |
+
"success_selector_gap": 0.3333333333333333,
|
| 90 |
+
"success_support_gap": 0.3333333333333333,
|
| 91 |
+
"support_gap": 0.634226381778717,
|
| 92 |
+
"tau": 0.39220772215018057
|
| 93 |
+
},
|
| 94 |
+
"StackCube-v1": {
|
| 95 |
+
"base_success": 0.2727272727272727,
|
| 96 |
+
"base_utility": 0.7763947045261209,
|
| 97 |
+
"coverage": 0.12121212121212122,
|
| 98 |
+
"execute_generated": 0.12121212121212122,
|
| 99 |
+
"fallback_rate": 0.8787878787878788,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 0.5757575757575758,
|
| 103 |
+
"predicted_margin": 0.2732475042188331,
|
| 104 |
+
"proposal_oracle_success": 0.45454545454545453,
|
| 105 |
+
"proposal_oracle_utility": 1.0546941955884297,
|
| 106 |
+
"selected_candidate_index": 3.9393939393939394,
|
| 107 |
+
"selected_success": 0.30303030303030304,
|
| 108 |
+
"selected_success_gain_over_base": 0.030303030303030304,
|
| 109 |
+
"selected_utility": 0.8117459159005772,
|
| 110 |
+
"selected_utility_gain_over_base": 0.03535121137445623,
|
| 111 |
+
"selector_regret": 0.24727042199987354,
|
| 112 |
+
"success_selector_gap": 0.15151515151515152,
|
| 113 |
+
"success_support_gap": 0.5454545454545454,
|
| 114 |
+
"support_gap": 0.9453058044115702,
|
| 115 |
+
"tau": 0.39220772215018057
|
| 116 |
+
}
|
| 117 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/report.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Nonlinear Train-Calibrated CTT Selector
|
| 2 |
+
|
| 3 |
+
Calibration rows: `432`
|
| 4 |
+
Fit rows: `277`
|
| 5 |
+
Selection rows: `155`
|
| 6 |
+
Eval rows: `144`
|
| 7 |
+
Selected model: `hgb_classifier`
|
| 8 |
+
Selected params: `{"l2_regularization": 0.01, "learning_rate": 0.05, "max_iter": 80, "max_leaf_nodes": 15, "random_state": 0}`
|
| 9 |
+
Tau: `0.392208`
|
| 10 |
+
Feature set: `context_tangent`
|
| 11 |
+
Target: `positive_margin`
|
| 12 |
+
|
| 13 |
+
The model is fit on calibration-fit rows, and model/tau are selected on held-out calibration-selection rows only. Eval outcomes are used only for reporting.
|
| 14 |
+
|
| 15 |
+
| Split | Coverage | Fallback | Base success | Selected success | Proposal oracle | OutcomePTR | Success support gap | Success selector gap |
|
| 16 |
+
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 17 |
+
| fit | 0.4477 | 0.5523 | 0.2780 | 0.4838 | 0.4910 | 0.4838 | 0.2058 | 0.0722 |
|
| 18 |
+
| selection | 0.4065 | 0.5935 | 0.2774 | 0.3677 | 0.4387 | 0.5032 | 0.2774 | 0.1290 |
|
| 19 |
+
| eval | 0.3750 | 0.6250 | 0.2917 | 0.2917 | 0.4792 | 0.5069 | 0.2917 | 0.2153 |
|
| 20 |
+
|
| 21 |
+
This is a train-calibrated selector diagnostic over already measured candidates, not a new rollout.
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/split_hash.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_target_index": {
|
| 3 |
+
"content_hash": "67f7b4a692f7c7e71da24378dc71e3399c5d35afc14c494869eba6087b765c42",
|
| 4 |
+
"retrieval_index_allowed": true,
|
| 5 |
+
"split": "train",
|
| 6 |
+
"split_hash": "867a94a1c67686c082765671a7bf8d74a9d633085e1b2619c83197c60bf58372"
|
| 7 |
+
},
|
| 8 |
+
"eval_target_index": {
|
| 9 |
+
"content_hash": "0c38d73dc9bc4ab756e12006671b5d12f1a23358b281e54b3f6a9ae3cbf6e9af",
|
| 10 |
+
"retrieval_index_allowed": false,
|
| 11 |
+
"split": "test",
|
| 12 |
+
"split_hash": "84151df9e88c219b76751677558cc5bbbc19082bf358cea7330158e9e403e25f"
|
| 13 |
+
}
|
| 14 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/table.tex
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
% Auto-generated by scripts/eval_nonlinear_dominance_selector.py
|
| 2 |
+
\begin{tabular}{lrrrrrrrr}
|
| 3 |
+
\toprule
|
| 4 |
+
Rows & Coverage & Fallback & Base succ. & Selected succ. & Oracle succ. & OutcomePTR & Succ. support gap & Succ. selector gap \\
|
| 5 |
+
\midrule
|
| 6 |
+
144 & 0.3750 & 0.6250 & 0.2917 & 0.2917 & 0.4792 & 0.5069 & 0.2917 & 0.2153 \\
|
| 7 |
+
\bottomrule
|
| 8 |
+
\end{tabular}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_positive_envclip_train_to_test/train.log
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
trained nonlinear dominance selector on calibration-fit rows only
|
| 2 |
+
selected_model_type=hgb_classifier
|
| 3 |
+
selected_model_params={"l2_regularization": 0.01, "learning_rate": 0.05, "max_iter": 80, "max_leaf_nodes": 15, "random_state": 0}
|
| 4 |
+
tau=0.392208
|
| 5 |
+
calibration_input=runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/command.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
python scripts/eval_nonlinear_dominance_selector.py --calibration-input runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json --calibration-target-index data/cil_charts_rgb_refs/train/index.json --eval-input runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json --eval-target-index data/cil_charts_rgb_refs/test/index.json --checkpoint-template runs/ctt_residual_base_context_obs_seed{seed}/model.pt --out-dir runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test --feature-set context_tangent --target success --k 8 --bootstrap-samples 1000
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/config.yaml
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
bootstrap_samples: 1000
|
| 2 |
+
calibration_input: runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
calibration_target_index: data/cil_charts_rgb_refs/train/index.json
|
| 4 |
+
checkpoint_template: runs/ctt_residual_base_context_obs_seed{seed}/model.pt
|
| 5 |
+
eval_input: runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 6 |
+
eval_target_index: data/cil_charts_rgb_refs/test/index.json
|
| 7 |
+
feature_set: context_tangent
|
| 8 |
+
k: 8
|
| 9 |
+
model_types: hgb_classifier,hgb_regressor,rf_regressor
|
| 10 |
+
out_dir: runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test
|
| 11 |
+
seed: 0
|
| 12 |
+
selection_frac: 0.35
|
| 13 |
+
target: success
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/data_hash.txt
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_input": "06375099001e740a377c402e34b77bf6974be3dc2a468974340ce41eb1b487f0",
|
| 3 |
+
"calibration_target_index": "67973c50072aa87a3b97533b6292b08a8b4d88a95571dc22e91b6e8fd19e0d85",
|
| 4 |
+
"eval_input": "57df43ff4802379dfd60b5209d5a04028d721256406685decededccdbec0d49c",
|
| 5 |
+
"eval_target_index": "dee1b5225485df6624747dd4c5074bcf514685b54017d05e698d2051638fbf36"
|
| 6 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/eval.log
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
selected model/tau on held-out calibration-selection rows; evaluated on held-out measured rollout rows
|
| 2 |
+
eval_input=runs/ctt_base_context_obs_test_envclip_rollout_comparison/combined_measured_candidates.json
|
| 3 |
+
num_eval_rows=144
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/git_hash.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
14e81292e2004925f81e0bb4810f6f144bfd87b7
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/metrics.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/metrics_by_seed.json
ADDED
|
@@ -0,0 +1,2762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"1073161778/train0": {
|
| 3 |
+
"base_success": 1.0,
|
| 4 |
+
"base_utility": 2.0,
|
| 5 |
+
"coverage": 1.0,
|
| 6 |
+
"execute_generated": 1.0,
|
| 7 |
+
"fallback_rate": 0.0,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.0,
|
| 11 |
+
"predicted_margin": 0.5047786612880557,
|
| 12 |
+
"proposal_oracle_success": 1.0,
|
| 13 |
+
"proposal_oracle_utility": 2.0,
|
| 14 |
+
"selected_candidate_index": 3.0,
|
| 15 |
+
"selected_success": 0.0,
|
| 16 |
+
"selected_success_gain_over_base": -1.0,
|
| 17 |
+
"selected_utility": 0.6962459683418274,
|
| 18 |
+
"selected_utility_gain_over_base": -1.3037540316581726,
|
| 19 |
+
"selector_regret": 1.3037540316581726,
|
| 20 |
+
"success_selector_gap": 1.0,
|
| 21 |
+
"success_support_gap": 0.0,
|
| 22 |
+
"support_gap": 0.0,
|
| 23 |
+
"tau": 0.34408156791985406
|
| 24 |
+
},
|
| 25 |
+
"1073161778/train1": {
|
| 26 |
+
"base_success": 1.0,
|
| 27 |
+
"base_utility": 2.0,
|
| 28 |
+
"coverage": 1.0,
|
| 29 |
+
"execute_generated": 1.0,
|
| 30 |
+
"fallback_rate": 0.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.5323396378653275,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.7071996331214905,
|
| 37 |
+
"selected_candidate_index": 1.0,
|
| 38 |
+
"selected_success": 0.0,
|
| 39 |
+
"selected_success_gain_over_base": -1.0,
|
| 40 |
+
"selected_utility": 0.5317060947418213,
|
| 41 |
+
"selected_utility_gain_over_base": -1.4682939052581787,
|
| 42 |
+
"selector_regret": 0.1754935383796692,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.2928003668785095,
|
| 46 |
+
"tau": 0.34408156791985406
|
| 47 |
+
},
|
| 48 |
+
"1073161778/train2": {
|
| 49 |
+
"base_success": 1.0,
|
| 50 |
+
"base_utility": 2.0,
|
| 51 |
+
"coverage": 1.0,
|
| 52 |
+
"execute_generated": 1.0,
|
| 53 |
+
"fallback_rate": 0.0,
|
| 54 |
+
"hidden_chart_oracle_success": 1.0,
|
| 55 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 56 |
+
"outcome_ptr": 0.0,
|
| 57 |
+
"predicted_margin": 0.5132737468890538,
|
| 58 |
+
"proposal_oracle_success": 1.0,
|
| 59 |
+
"proposal_oracle_utility": 2.0,
|
| 60 |
+
"selected_candidate_index": 2.0,
|
| 61 |
+
"selected_success": 1.0,
|
| 62 |
+
"selected_success_gain_over_base": 0.0,
|
| 63 |
+
"selected_utility": 2.0,
|
| 64 |
+
"selected_utility_gain_over_base": 0.0,
|
| 65 |
+
"selector_regret": 0.0,
|
| 66 |
+
"success_selector_gap": 0.0,
|
| 67 |
+
"success_support_gap": 0.0,
|
| 68 |
+
"support_gap": 0.0,
|
| 69 |
+
"tau": 0.34408156791985406
|
| 70 |
+
},
|
| 71 |
+
"1113371261/train0": {
|
| 72 |
+
"base_success": 0.0,
|
| 73 |
+
"base_utility": 0.15842342376708984,
|
| 74 |
+
"coverage": 0.0,
|
| 75 |
+
"execute_generated": 0.0,
|
| 76 |
+
"fallback_rate": 1.0,
|
| 77 |
+
"hidden_chart_oracle_success": 1.0,
|
| 78 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 79 |
+
"outcome_ptr": 0.0,
|
| 80 |
+
"predicted_margin": 0.20380714554880489,
|
| 81 |
+
"proposal_oracle_success": 0.0,
|
| 82 |
+
"proposal_oracle_utility": 0.10274861752986908,
|
| 83 |
+
"selected_candidate_index": 7.0,
|
| 84 |
+
"selected_success": 0.0,
|
| 85 |
+
"selected_success_gain_over_base": 0.0,
|
| 86 |
+
"selected_utility": 0.15842342376708984,
|
| 87 |
+
"selected_utility_gain_over_base": 0.0,
|
| 88 |
+
"selector_regret": 0.0,
|
| 89 |
+
"success_selector_gap": 0.0,
|
| 90 |
+
"success_support_gap": 1.0,
|
| 91 |
+
"support_gap": 1.897251382470131,
|
| 92 |
+
"tau": 0.34408156791985406
|
| 93 |
+
},
|
| 94 |
+
"1113371261/train1": {
|
| 95 |
+
"base_success": 0.0,
|
| 96 |
+
"base_utility": 0.15842342376708984,
|
| 97 |
+
"coverage": 0.0,
|
| 98 |
+
"execute_generated": 0.0,
|
| 99 |
+
"fallback_rate": 1.0,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 1.0,
|
| 103 |
+
"predicted_margin": 0.216136141459529,
|
| 104 |
+
"proposal_oracle_success": 0.0,
|
| 105 |
+
"proposal_oracle_utility": 0.18093222379684448,
|
| 106 |
+
"selected_candidate_index": 3.0,
|
| 107 |
+
"selected_success": 0.0,
|
| 108 |
+
"selected_success_gain_over_base": 0.0,
|
| 109 |
+
"selected_utility": 0.15842342376708984,
|
| 110 |
+
"selected_utility_gain_over_base": 0.0,
|
| 111 |
+
"selector_regret": 0.02250880002975464,
|
| 112 |
+
"success_selector_gap": 0.0,
|
| 113 |
+
"success_support_gap": 1.0,
|
| 114 |
+
"support_gap": 1.8190677762031555,
|
| 115 |
+
"tau": 0.34408156791985406
|
| 116 |
+
},
|
| 117 |
+
"1113371261/train2": {
|
| 118 |
+
"base_success": 0.0,
|
| 119 |
+
"base_utility": 0.15842342376708984,
|
| 120 |
+
"coverage": 0.0,
|
| 121 |
+
"execute_generated": 0.0,
|
| 122 |
+
"fallback_rate": 1.0,
|
| 123 |
+
"hidden_chart_oracle_success": 1.0,
|
| 124 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 125 |
+
"outcome_ptr": 1.0,
|
| 126 |
+
"predicted_margin": 0.1818611172967026,
|
| 127 |
+
"proposal_oracle_success": 0.0,
|
| 128 |
+
"proposal_oracle_utility": 0.19527167081832886,
|
| 129 |
+
"selected_candidate_index": 7.0,
|
| 130 |
+
"selected_success": 0.0,
|
| 131 |
+
"selected_success_gain_over_base": 0.0,
|
| 132 |
+
"selected_utility": 0.15842342376708984,
|
| 133 |
+
"selected_utility_gain_over_base": 0.0,
|
| 134 |
+
"selector_regret": 0.036848247051239014,
|
| 135 |
+
"success_selector_gap": 0.0,
|
| 136 |
+
"success_support_gap": 1.0,
|
| 137 |
+
"support_gap": 1.8047283291816711,
|
| 138 |
+
"tau": 0.34408156791985406
|
| 139 |
+
},
|
| 140 |
+
"1151410346/train0": {
|
| 141 |
+
"base_success": 0.0,
|
| 142 |
+
"base_utility": 0.2260012924671173,
|
| 143 |
+
"coverage": 0.0,
|
| 144 |
+
"execute_generated": 0.0,
|
| 145 |
+
"fallback_rate": 1.0,
|
| 146 |
+
"hidden_chart_oracle_success": 1.0,
|
| 147 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 148 |
+
"outcome_ptr": 1.0,
|
| 149 |
+
"predicted_margin": 0.16380705661970563,
|
| 150 |
+
"proposal_oracle_success": 0.0,
|
| 151 |
+
"proposal_oracle_utility": 0.8663521409034729,
|
| 152 |
+
"selected_candidate_index": 6.0,
|
| 153 |
+
"selected_success": 0.0,
|
| 154 |
+
"selected_success_gain_over_base": 0.0,
|
| 155 |
+
"selected_utility": 0.2260012924671173,
|
| 156 |
+
"selected_utility_gain_over_base": 0.0,
|
| 157 |
+
"selector_regret": 0.6403508484363556,
|
| 158 |
+
"success_selector_gap": 0.0,
|
| 159 |
+
"success_support_gap": 1.0,
|
| 160 |
+
"support_gap": 1.133647859096527,
|
| 161 |
+
"tau": 0.34408156791985406
|
| 162 |
+
},
|
| 163 |
+
"1151410346/train1": {
|
| 164 |
+
"base_success": 0.0,
|
| 165 |
+
"base_utility": 0.2260012924671173,
|
| 166 |
+
"coverage": 1.0,
|
| 167 |
+
"execute_generated": 1.0,
|
| 168 |
+
"fallback_rate": 0.0,
|
| 169 |
+
"hidden_chart_oracle_success": 1.0,
|
| 170 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 171 |
+
"outcome_ptr": 1.0,
|
| 172 |
+
"predicted_margin": 0.3807159751095167,
|
| 173 |
+
"proposal_oracle_success": 0.0,
|
| 174 |
+
"proposal_oracle_utility": 0.8138919472694397,
|
| 175 |
+
"selected_candidate_index": 0.0,
|
| 176 |
+
"selected_success": 0.0,
|
| 177 |
+
"selected_success_gain_over_base": 0.0,
|
| 178 |
+
"selected_utility": 0.8134199976921082,
|
| 179 |
+
"selected_utility_gain_over_base": 0.5874187052249908,
|
| 180 |
+
"selector_regret": 0.00047194957733154297,
|
| 181 |
+
"success_selector_gap": 0.0,
|
| 182 |
+
"success_support_gap": 1.0,
|
| 183 |
+
"support_gap": 1.1861080527305603,
|
| 184 |
+
"tau": 0.34408156791985406
|
| 185 |
+
},
|
| 186 |
+
"1151410346/train2": {
|
| 187 |
+
"base_success": 0.0,
|
| 188 |
+
"base_utility": 0.2260012924671173,
|
| 189 |
+
"coverage": 0.0,
|
| 190 |
+
"execute_generated": 0.0,
|
| 191 |
+
"fallback_rate": 1.0,
|
| 192 |
+
"hidden_chart_oracle_success": 1.0,
|
| 193 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 194 |
+
"outcome_ptr": 0.0,
|
| 195 |
+
"predicted_margin": 0.22275232189021582,
|
| 196 |
+
"proposal_oracle_success": 0.0,
|
| 197 |
+
"proposal_oracle_utility": 0.21912741661071777,
|
| 198 |
+
"selected_candidate_index": 0.0,
|
| 199 |
+
"selected_success": 0.0,
|
| 200 |
+
"selected_success_gain_over_base": 0.0,
|
| 201 |
+
"selected_utility": 0.2260012924671173,
|
| 202 |
+
"selected_utility_gain_over_base": 0.0,
|
| 203 |
+
"selector_regret": 0.0,
|
| 204 |
+
"success_selector_gap": 0.0,
|
| 205 |
+
"success_support_gap": 1.0,
|
| 206 |
+
"support_gap": 1.7808725833892822,
|
| 207 |
+
"tau": 0.34408156791985406
|
| 208 |
+
},
|
| 209 |
+
"1261930456/train0": {
|
| 210 |
+
"base_success": 1.0,
|
| 211 |
+
"base_utility": 2.0,
|
| 212 |
+
"coverage": 1.0,
|
| 213 |
+
"execute_generated": 1.0,
|
| 214 |
+
"fallback_rate": 0.0,
|
| 215 |
+
"hidden_chart_oracle_success": 1.0,
|
| 216 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 217 |
+
"outcome_ptr": 0.0,
|
| 218 |
+
"predicted_margin": 0.8068754349598813,
|
| 219 |
+
"proposal_oracle_success": 1.0,
|
| 220 |
+
"proposal_oracle_utility": 2.0,
|
| 221 |
+
"selected_candidate_index": 3.0,
|
| 222 |
+
"selected_success": 0.0,
|
| 223 |
+
"selected_success_gain_over_base": -1.0,
|
| 224 |
+
"selected_utility": 0.06716175377368927,
|
| 225 |
+
"selected_utility_gain_over_base": -1.9328382462263107,
|
| 226 |
+
"selector_regret": 1.9328382462263107,
|
| 227 |
+
"success_selector_gap": 1.0,
|
| 228 |
+
"success_support_gap": 0.0,
|
| 229 |
+
"support_gap": 0.0,
|
| 230 |
+
"tau": 0.34408156791985406
|
| 231 |
+
},
|
| 232 |
+
"1261930456/train1": {
|
| 233 |
+
"base_success": 1.0,
|
| 234 |
+
"base_utility": 2.0,
|
| 235 |
+
"coverage": 1.0,
|
| 236 |
+
"execute_generated": 1.0,
|
| 237 |
+
"fallback_rate": 0.0,
|
| 238 |
+
"hidden_chart_oracle_success": 1.0,
|
| 239 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 240 |
+
"outcome_ptr": 0.0,
|
| 241 |
+
"predicted_margin": 0.8314472386685839,
|
| 242 |
+
"proposal_oracle_success": 1.0,
|
| 243 |
+
"proposal_oracle_utility": 2.0,
|
| 244 |
+
"selected_candidate_index": 0.0,
|
| 245 |
+
"selected_success": 0.0,
|
| 246 |
+
"selected_success_gain_over_base": -1.0,
|
| 247 |
+
"selected_utility": 0.07528233528137207,
|
| 248 |
+
"selected_utility_gain_over_base": -1.924717664718628,
|
| 249 |
+
"selector_regret": 1.924717664718628,
|
| 250 |
+
"success_selector_gap": 1.0,
|
| 251 |
+
"success_support_gap": 0.0,
|
| 252 |
+
"support_gap": 0.0,
|
| 253 |
+
"tau": 0.34408156791985406
|
| 254 |
+
},
|
| 255 |
+
"1261930456/train2": {
|
| 256 |
+
"base_success": 1.0,
|
| 257 |
+
"base_utility": 2.0,
|
| 258 |
+
"coverage": 1.0,
|
| 259 |
+
"execute_generated": 1.0,
|
| 260 |
+
"fallback_rate": 0.0,
|
| 261 |
+
"hidden_chart_oracle_success": 1.0,
|
| 262 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 263 |
+
"outcome_ptr": 0.0,
|
| 264 |
+
"predicted_margin": 0.5203682065298446,
|
| 265 |
+
"proposal_oracle_success": 1.0,
|
| 266 |
+
"proposal_oracle_utility": 2.0,
|
| 267 |
+
"selected_candidate_index": 3.0,
|
| 268 |
+
"selected_success": 1.0,
|
| 269 |
+
"selected_success_gain_over_base": 0.0,
|
| 270 |
+
"selected_utility": 2.0,
|
| 271 |
+
"selected_utility_gain_over_base": 0.0,
|
| 272 |
+
"selector_regret": 0.0,
|
| 273 |
+
"success_selector_gap": 0.0,
|
| 274 |
+
"success_support_gap": 0.0,
|
| 275 |
+
"support_gap": 0.0,
|
| 276 |
+
"tau": 0.34408156791985406
|
| 277 |
+
},
|
| 278 |
+
"1324133122/train0": {
|
| 279 |
+
"base_success": 0.0,
|
| 280 |
+
"base_utility": 0.09220491349697113,
|
| 281 |
+
"coverage": 0.0,
|
| 282 |
+
"execute_generated": 0.0,
|
| 283 |
+
"fallback_rate": 1.0,
|
| 284 |
+
"hidden_chart_oracle_success": 1.0,
|
| 285 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 286 |
+
"outcome_ptr": 0.0,
|
| 287 |
+
"predicted_margin": 0.0267850715243588,
|
| 288 |
+
"proposal_oracle_success": 0.0,
|
| 289 |
+
"proposal_oracle_utility": 0.054989203810691833,
|
| 290 |
+
"selected_candidate_index": 7.0,
|
| 291 |
+
"selected_success": 0.0,
|
| 292 |
+
"selected_success_gain_over_base": 0.0,
|
| 293 |
+
"selected_utility": 0.09220491349697113,
|
| 294 |
+
"selected_utility_gain_over_base": 0.0,
|
| 295 |
+
"selector_regret": 0.0,
|
| 296 |
+
"success_selector_gap": 0.0,
|
| 297 |
+
"success_support_gap": 1.0,
|
| 298 |
+
"support_gap": 1.9450107961893082,
|
| 299 |
+
"tau": 0.34408156791985406
|
| 300 |
+
},
|
| 301 |
+
"1324133122/train1": {
|
| 302 |
+
"base_success": 0.0,
|
| 303 |
+
"base_utility": 0.09220491349697113,
|
| 304 |
+
"coverage": 0.0,
|
| 305 |
+
"execute_generated": 0.0,
|
| 306 |
+
"fallback_rate": 1.0,
|
| 307 |
+
"hidden_chart_oracle_success": 1.0,
|
| 308 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 309 |
+
"outcome_ptr": 1.0,
|
| 310 |
+
"predicted_margin": 0.166222195833595,
|
| 311 |
+
"proposal_oracle_success": 0.0,
|
| 312 |
+
"proposal_oracle_utility": 0.1324586570262909,
|
| 313 |
+
"selected_candidate_index": 1.0,
|
| 314 |
+
"selected_success": 0.0,
|
| 315 |
+
"selected_success_gain_over_base": 0.0,
|
| 316 |
+
"selected_utility": 0.09220491349697113,
|
| 317 |
+
"selected_utility_gain_over_base": 0.0,
|
| 318 |
+
"selector_regret": 0.04025374352931976,
|
| 319 |
+
"success_selector_gap": 0.0,
|
| 320 |
+
"success_support_gap": 1.0,
|
| 321 |
+
"support_gap": 1.867541342973709,
|
| 322 |
+
"tau": 0.34408156791985406
|
| 323 |
+
},
|
| 324 |
+
"1324133122/train2": {
|
| 325 |
+
"base_success": 0.0,
|
| 326 |
+
"base_utility": 0.09220491349697113,
|
| 327 |
+
"coverage": 0.0,
|
| 328 |
+
"execute_generated": 0.0,
|
| 329 |
+
"fallback_rate": 1.0,
|
| 330 |
+
"hidden_chart_oracle_success": 1.0,
|
| 331 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 332 |
+
"outcome_ptr": 1.0,
|
| 333 |
+
"predicted_margin": 0.1895440816104003,
|
| 334 |
+
"proposal_oracle_success": 0.0,
|
| 335 |
+
"proposal_oracle_utility": 0.19291165471076965,
|
| 336 |
+
"selected_candidate_index": 0.0,
|
| 337 |
+
"selected_success": 0.0,
|
| 338 |
+
"selected_success_gain_over_base": 0.0,
|
| 339 |
+
"selected_utility": 0.09220491349697113,
|
| 340 |
+
"selected_utility_gain_over_base": 0.0,
|
| 341 |
+
"selector_regret": 0.10070674121379852,
|
| 342 |
+
"success_selector_gap": 0.0,
|
| 343 |
+
"success_support_gap": 1.0,
|
| 344 |
+
"support_gap": 1.8070883452892303,
|
| 345 |
+
"tau": 0.34408156791985406
|
| 346 |
+
},
|
| 347 |
+
"1324642411/train0": {
|
| 348 |
+
"base_success": 0.0,
|
| 349 |
+
"base_utility": 0.10647052526473999,
|
| 350 |
+
"coverage": 1.0,
|
| 351 |
+
"execute_generated": 1.0,
|
| 352 |
+
"fallback_rate": 0.0,
|
| 353 |
+
"hidden_chart_oracle_success": 1.0,
|
| 354 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 355 |
+
"outcome_ptr": 1.0,
|
| 356 |
+
"predicted_margin": 0.6157618702014627,
|
| 357 |
+
"proposal_oracle_success": 0.0,
|
| 358 |
+
"proposal_oracle_utility": 0.17193320393562317,
|
| 359 |
+
"selected_candidate_index": 5.0,
|
| 360 |
+
"selected_success": 0.0,
|
| 361 |
+
"selected_success_gain_over_base": 0.0,
|
| 362 |
+
"selected_utility": 0.17193320393562317,
|
| 363 |
+
"selected_utility_gain_over_base": 0.06546267867088318,
|
| 364 |
+
"selector_regret": 0.0,
|
| 365 |
+
"success_selector_gap": 0.0,
|
| 366 |
+
"success_support_gap": 1.0,
|
| 367 |
+
"support_gap": 1.8280667960643768,
|
| 368 |
+
"tau": 0.34408156791985406
|
| 369 |
+
},
|
| 370 |
+
"1324642411/train1": {
|
| 371 |
+
"base_success": 0.0,
|
| 372 |
+
"base_utility": 0.10647052526473999,
|
| 373 |
+
"coverage": 1.0,
|
| 374 |
+
"execute_generated": 1.0,
|
| 375 |
+
"fallback_rate": 0.0,
|
| 376 |
+
"hidden_chart_oracle_success": 1.0,
|
| 377 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 378 |
+
"outcome_ptr": 1.0,
|
| 379 |
+
"predicted_margin": 0.7200821909843477,
|
| 380 |
+
"proposal_oracle_success": 0.0,
|
| 381 |
+
"proposal_oracle_utility": 0.1836909055709839,
|
| 382 |
+
"selected_candidate_index": 7.0,
|
| 383 |
+
"selected_success": 0.0,
|
| 384 |
+
"selected_success_gain_over_base": 0.0,
|
| 385 |
+
"selected_utility": 0.06962272524833679,
|
| 386 |
+
"selected_utility_gain_over_base": -0.0368478000164032,
|
| 387 |
+
"selector_regret": 0.1140681803226471,
|
| 388 |
+
"success_selector_gap": 0.0,
|
| 389 |
+
"success_support_gap": 1.0,
|
| 390 |
+
"support_gap": 1.8163090944290161,
|
| 391 |
+
"tau": 0.34408156791985406
|
| 392 |
+
},
|
| 393 |
+
"1324642411/train2": {
|
| 394 |
+
"base_success": 0.0,
|
| 395 |
+
"base_utility": 0.10647052526473999,
|
| 396 |
+
"coverage": 1.0,
|
| 397 |
+
"execute_generated": 1.0,
|
| 398 |
+
"fallback_rate": 0.0,
|
| 399 |
+
"hidden_chart_oracle_success": 1.0,
|
| 400 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 401 |
+
"outcome_ptr": 1.0,
|
| 402 |
+
"predicted_margin": 0.8093176408240023,
|
| 403 |
+
"proposal_oracle_success": 1.0,
|
| 404 |
+
"proposal_oracle_utility": 2.0,
|
| 405 |
+
"selected_candidate_index": 3.0,
|
| 406 |
+
"selected_success": 0.0,
|
| 407 |
+
"selected_success_gain_over_base": 0.0,
|
| 408 |
+
"selected_utility": 0.10968391597270966,
|
| 409 |
+
"selected_utility_gain_over_base": 0.0032133907079696655,
|
| 410 |
+
"selector_regret": 1.8903160840272903,
|
| 411 |
+
"success_selector_gap": 1.0,
|
| 412 |
+
"success_support_gap": 0.0,
|
| 413 |
+
"support_gap": 0.0,
|
| 414 |
+
"tau": 0.34408156791985406
|
| 415 |
+
},
|
| 416 |
+
"1375492786/train0": {
|
| 417 |
+
"base_success": 1.0,
|
| 418 |
+
"base_utility": 2.0,
|
| 419 |
+
"coverage": 1.0,
|
| 420 |
+
"execute_generated": 1.0,
|
| 421 |
+
"fallback_rate": 0.0,
|
| 422 |
+
"hidden_chart_oracle_success": 1.0,
|
| 423 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 424 |
+
"outcome_ptr": 0.0,
|
| 425 |
+
"predicted_margin": 0.5723807687992665,
|
| 426 |
+
"proposal_oracle_success": 1.0,
|
| 427 |
+
"proposal_oracle_utility": 2.0,
|
| 428 |
+
"selected_candidate_index": 2.0,
|
| 429 |
+
"selected_success": 0.0,
|
| 430 |
+
"selected_success_gain_over_base": -1.0,
|
| 431 |
+
"selected_utility": 0.008132100105285645,
|
| 432 |
+
"selected_utility_gain_over_base": -1.9918678998947144,
|
| 433 |
+
"selector_regret": 1.9918678998947144,
|
| 434 |
+
"success_selector_gap": 1.0,
|
| 435 |
+
"success_support_gap": 0.0,
|
| 436 |
+
"support_gap": 0.0,
|
| 437 |
+
"tau": 0.34408156791985406
|
| 438 |
+
},
|
| 439 |
+
"1375492786/train1": {
|
| 440 |
+
"base_success": 1.0,
|
| 441 |
+
"base_utility": 2.0,
|
| 442 |
+
"coverage": 0.0,
|
| 443 |
+
"execute_generated": 0.0,
|
| 444 |
+
"fallback_rate": 1.0,
|
| 445 |
+
"hidden_chart_oracle_success": 1.0,
|
| 446 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 447 |
+
"outcome_ptr": 0.0,
|
| 448 |
+
"predicted_margin": 0.09015312457958802,
|
| 449 |
+
"proposal_oracle_success": 0.0,
|
| 450 |
+
"proposal_oracle_utility": 0.08251869678497314,
|
| 451 |
+
"selected_candidate_index": 5.0,
|
| 452 |
+
"selected_success": 1.0,
|
| 453 |
+
"selected_success_gain_over_base": 0.0,
|
| 454 |
+
"selected_utility": 2.0,
|
| 455 |
+
"selected_utility_gain_over_base": 0.0,
|
| 456 |
+
"selector_regret": 0.0,
|
| 457 |
+
"success_selector_gap": 0.0,
|
| 458 |
+
"success_support_gap": 1.0,
|
| 459 |
+
"support_gap": 1.9174813032150269,
|
| 460 |
+
"tau": 0.34408156791985406
|
| 461 |
+
},
|
| 462 |
+
"1375492786/train2": {
|
| 463 |
+
"base_success": 1.0,
|
| 464 |
+
"base_utility": 2.0,
|
| 465 |
+
"coverage": 0.0,
|
| 466 |
+
"execute_generated": 0.0,
|
| 467 |
+
"fallback_rate": 1.0,
|
| 468 |
+
"hidden_chart_oracle_success": 1.0,
|
| 469 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 470 |
+
"outcome_ptr": 0.0,
|
| 471 |
+
"predicted_margin": 0.15985879284842153,
|
| 472 |
+
"proposal_oracle_success": 1.0,
|
| 473 |
+
"proposal_oracle_utility": 2.0,
|
| 474 |
+
"selected_candidate_index": 4.0,
|
| 475 |
+
"selected_success": 1.0,
|
| 476 |
+
"selected_success_gain_over_base": 0.0,
|
| 477 |
+
"selected_utility": 2.0,
|
| 478 |
+
"selected_utility_gain_over_base": 0.0,
|
| 479 |
+
"selector_regret": 0.0,
|
| 480 |
+
"success_selector_gap": 0.0,
|
| 481 |
+
"success_support_gap": 0.0,
|
| 482 |
+
"support_gap": 0.0,
|
| 483 |
+
"tau": 0.34408156791985406
|
| 484 |
+
},
|
| 485 |
+
"141984615/train0": {
|
| 486 |
+
"base_success": 0.0,
|
| 487 |
+
"base_utility": 0.10283424705266953,
|
| 488 |
+
"coverage": 0.0,
|
| 489 |
+
"execute_generated": 0.0,
|
| 490 |
+
"fallback_rate": 1.0,
|
| 491 |
+
"hidden_chart_oracle_success": 0.0,
|
| 492 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 493 |
+
"outcome_ptr": 0.0,
|
| 494 |
+
"predicted_margin": 0.06373241744268668,
|
| 495 |
+
"proposal_oracle_success": 0.0,
|
| 496 |
+
"proposal_oracle_utility": 0.007291515823453665,
|
| 497 |
+
"selected_candidate_index": 1.0,
|
| 498 |
+
"selected_success": 0.0,
|
| 499 |
+
"selected_success_gain_over_base": 0.0,
|
| 500 |
+
"selected_utility": 0.10283424705266953,
|
| 501 |
+
"selected_utility_gain_over_base": 0.0,
|
| 502 |
+
"selector_regret": 0.0,
|
| 503 |
+
"success_selector_gap": 0.0,
|
| 504 |
+
"success_support_gap": 0.0,
|
| 505 |
+
"support_gap": 0.27848575497046113,
|
| 506 |
+
"tau": 0.34408156791985406
|
| 507 |
+
},
|
| 508 |
+
"141984615/train1": {
|
| 509 |
+
"base_success": 0.0,
|
| 510 |
+
"base_utility": 0.10283424705266953,
|
| 511 |
+
"coverage": 0.0,
|
| 512 |
+
"execute_generated": 0.0,
|
| 513 |
+
"fallback_rate": 1.0,
|
| 514 |
+
"hidden_chart_oracle_success": 0.0,
|
| 515 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 516 |
+
"outcome_ptr": 0.0,
|
| 517 |
+
"predicted_margin": 0.20426126222013247,
|
| 518 |
+
"proposal_oracle_success": 0.0,
|
| 519 |
+
"proposal_oracle_utility": 0.037011127918958664,
|
| 520 |
+
"selected_candidate_index": 2.0,
|
| 521 |
+
"selected_success": 0.0,
|
| 522 |
+
"selected_success_gain_over_base": 0.0,
|
| 523 |
+
"selected_utility": 0.10283424705266953,
|
| 524 |
+
"selected_utility_gain_over_base": 0.0,
|
| 525 |
+
"selector_regret": 0.0,
|
| 526 |
+
"success_selector_gap": 0.0,
|
| 527 |
+
"success_support_gap": 0.0,
|
| 528 |
+
"support_gap": 0.24876614287495613,
|
| 529 |
+
"tau": 0.34408156791985406
|
| 530 |
+
},
|
| 531 |
+
"141984615/train2": {
|
| 532 |
+
"base_success": 0.0,
|
| 533 |
+
"base_utility": 0.10283424705266953,
|
| 534 |
+
"coverage": 0.0,
|
| 535 |
+
"execute_generated": 0.0,
|
| 536 |
+
"fallback_rate": 1.0,
|
| 537 |
+
"hidden_chart_oracle_success": 0.0,
|
| 538 |
+
"hidden_chart_oracle_utility": 0.2857772707939148,
|
| 539 |
+
"outcome_ptr": 0.0,
|
| 540 |
+
"predicted_margin": 0.18128468401517966,
|
| 541 |
+
"proposal_oracle_success": 0.0,
|
| 542 |
+
"proposal_oracle_utility": 0.030228236690163612,
|
| 543 |
+
"selected_candidate_index": 0.0,
|
| 544 |
+
"selected_success": 0.0,
|
| 545 |
+
"selected_success_gain_over_base": 0.0,
|
| 546 |
+
"selected_utility": 0.10283424705266953,
|
| 547 |
+
"selected_utility_gain_over_base": 0.0,
|
| 548 |
+
"selector_regret": 0.0,
|
| 549 |
+
"success_selector_gap": 0.0,
|
| 550 |
+
"success_support_gap": 0.0,
|
| 551 |
+
"support_gap": 0.2555490341037512,
|
| 552 |
+
"tau": 0.34408156791985406
|
| 553 |
+
},
|
| 554 |
+
"1461069713/train0": {
|
| 555 |
+
"base_success": 0.0,
|
| 556 |
+
"base_utility": 0.0939030647277832,
|
| 557 |
+
"coverage": 0.0,
|
| 558 |
+
"execute_generated": 0.0,
|
| 559 |
+
"fallback_rate": 1.0,
|
| 560 |
+
"hidden_chart_oracle_success": 0.0,
|
| 561 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 562 |
+
"outcome_ptr": 0.0,
|
| 563 |
+
"predicted_margin": 0.07014763295619539,
|
| 564 |
+
"proposal_oracle_success": 0.0,
|
| 565 |
+
"proposal_oracle_utility": 0.06019836664199829,
|
| 566 |
+
"selected_candidate_index": 2.0,
|
| 567 |
+
"selected_success": 0.0,
|
| 568 |
+
"selected_success_gain_over_base": 0.0,
|
| 569 |
+
"selected_utility": 0.0939030647277832,
|
| 570 |
+
"selected_utility_gain_over_base": 0.0,
|
| 571 |
+
"selector_regret": 0.0,
|
| 572 |
+
"success_selector_gap": 0.0,
|
| 573 |
+
"success_support_gap": 0.0,
|
| 574 |
+
"support_gap": 0.0991440862417221,
|
| 575 |
+
"tau": 0.34408156791985406
|
| 576 |
+
},
|
| 577 |
+
"1461069713/train1": {
|
| 578 |
+
"base_success": 0.0,
|
| 579 |
+
"base_utility": 0.0939030647277832,
|
| 580 |
+
"coverage": 0.0,
|
| 581 |
+
"execute_generated": 0.0,
|
| 582 |
+
"fallback_rate": 1.0,
|
| 583 |
+
"hidden_chart_oracle_success": 0.0,
|
| 584 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 585 |
+
"outcome_ptr": 0.0,
|
| 586 |
+
"predicted_margin": 0.11660139608054601,
|
| 587 |
+
"proposal_oracle_success": 0.0,
|
| 588 |
+
"proposal_oracle_utility": 0.016585012897849083,
|
| 589 |
+
"selected_candidate_index": 6.0,
|
| 590 |
+
"selected_success": 0.0,
|
| 591 |
+
"selected_success_gain_over_base": 0.0,
|
| 592 |
+
"selected_utility": 0.0939030647277832,
|
| 593 |
+
"selected_utility_gain_over_base": 0.0,
|
| 594 |
+
"selector_regret": 0.0,
|
| 595 |
+
"success_selector_gap": 0.0,
|
| 596 |
+
"success_support_gap": 0.0,
|
| 597 |
+
"support_gap": 0.14275743998587132,
|
| 598 |
+
"tau": 0.34408156791985406
|
| 599 |
+
},
|
| 600 |
+
"1461069713/train2": {
|
| 601 |
+
"base_success": 0.0,
|
| 602 |
+
"base_utility": 0.0939030647277832,
|
| 603 |
+
"coverage": 0.0,
|
| 604 |
+
"execute_generated": 0.0,
|
| 605 |
+
"fallback_rate": 1.0,
|
| 606 |
+
"hidden_chart_oracle_success": 0.0,
|
| 607 |
+
"hidden_chart_oracle_utility": 0.1593424528837204,
|
| 608 |
+
"outcome_ptr": 1.0,
|
| 609 |
+
"predicted_margin": 0.14708579808151867,
|
| 610 |
+
"proposal_oracle_success": 0.0,
|
| 611 |
+
"proposal_oracle_utility": 0.09970339387655258,
|
| 612 |
+
"selected_candidate_index": 7.0,
|
| 613 |
+
"selected_success": 0.0,
|
| 614 |
+
"selected_success_gain_over_base": 0.0,
|
| 615 |
+
"selected_utility": 0.0939030647277832,
|
| 616 |
+
"selected_utility_gain_over_base": 0.0,
|
| 617 |
+
"selector_regret": 0.005800329148769379,
|
| 618 |
+
"success_selector_gap": 0.0,
|
| 619 |
+
"success_support_gap": 0.0,
|
| 620 |
+
"support_gap": 0.059639059007167816,
|
| 621 |
+
"tau": 0.34408156791985406
|
| 622 |
+
},
|
| 623 |
+
"1480856810/train0": {
|
| 624 |
+
"base_success": 0.0,
|
| 625 |
+
"base_utility": 0.08703407645225525,
|
| 626 |
+
"coverage": 1.0,
|
| 627 |
+
"execute_generated": 1.0,
|
| 628 |
+
"fallback_rate": 0.0,
|
| 629 |
+
"hidden_chart_oracle_success": 0.0,
|
| 630 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 631 |
+
"outcome_ptr": 1.0,
|
| 632 |
+
"predicted_margin": 0.6460010381991991,
|
| 633 |
+
"proposal_oracle_success": 1.0,
|
| 634 |
+
"proposal_oracle_utility": 2.0,
|
| 635 |
+
"selected_candidate_index": 1.0,
|
| 636 |
+
"selected_success": 1.0,
|
| 637 |
+
"selected_success_gain_over_base": 1.0,
|
| 638 |
+
"selected_utility": 2.0,
|
| 639 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 640 |
+
"selector_regret": 0.0,
|
| 641 |
+
"success_selector_gap": 0.0,
|
| 642 |
+
"success_support_gap": 0.0,
|
| 643 |
+
"support_gap": 0.0,
|
| 644 |
+
"tau": 0.34408156791985406
|
| 645 |
+
},
|
| 646 |
+
"1480856810/train1": {
|
| 647 |
+
"base_success": 0.0,
|
| 648 |
+
"base_utility": 0.08703407645225525,
|
| 649 |
+
"coverage": 1.0,
|
| 650 |
+
"execute_generated": 1.0,
|
| 651 |
+
"fallback_rate": 0.0,
|
| 652 |
+
"hidden_chart_oracle_success": 0.0,
|
| 653 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 654 |
+
"outcome_ptr": 1.0,
|
| 655 |
+
"predicted_margin": 0.6031466837579302,
|
| 656 |
+
"proposal_oracle_success": 1.0,
|
| 657 |
+
"proposal_oracle_utility": 2.0,
|
| 658 |
+
"selected_candidate_index": 4.0,
|
| 659 |
+
"selected_success": 1.0,
|
| 660 |
+
"selected_success_gain_over_base": 1.0,
|
| 661 |
+
"selected_utility": 2.0,
|
| 662 |
+
"selected_utility_gain_over_base": 1.9129659235477448,
|
| 663 |
+
"selector_regret": 0.0,
|
| 664 |
+
"success_selector_gap": 0.0,
|
| 665 |
+
"success_support_gap": 0.0,
|
| 666 |
+
"support_gap": 0.0,
|
| 667 |
+
"tau": 0.34408156791985406
|
| 668 |
+
},
|
| 669 |
+
"1480856810/train2": {
|
| 670 |
+
"base_success": 0.0,
|
| 671 |
+
"base_utility": 0.08703407645225525,
|
| 672 |
+
"coverage": 1.0,
|
| 673 |
+
"execute_generated": 1.0,
|
| 674 |
+
"fallback_rate": 0.0,
|
| 675 |
+
"hidden_chart_oracle_success": 0.0,
|
| 676 |
+
"hidden_chart_oracle_utility": 0.20948036015033722,
|
| 677 |
+
"outcome_ptr": 1.0,
|
| 678 |
+
"predicted_margin": 0.5623456840603507,
|
| 679 |
+
"proposal_oracle_success": 1.0,
|
| 680 |
+
"proposal_oracle_utility": 2.0,
|
| 681 |
+
"selected_candidate_index": 3.0,
|
| 682 |
+
"selected_success": 0.0,
|
| 683 |
+
"selected_success_gain_over_base": 0.0,
|
| 684 |
+
"selected_utility": 0.024744659662246704,
|
| 685 |
+
"selected_utility_gain_over_base": -0.062289416790008545,
|
| 686 |
+
"selector_regret": 1.9752553403377533,
|
| 687 |
+
"success_selector_gap": 1.0,
|
| 688 |
+
"success_support_gap": 0.0,
|
| 689 |
+
"support_gap": 0.0,
|
| 690 |
+
"tau": 0.34408156791985406
|
| 691 |
+
},
|
| 692 |
+
"1509980664/train0": {
|
| 693 |
+
"base_success": 0.0,
|
| 694 |
+
"base_utility": 0.8334100246429443,
|
| 695 |
+
"coverage": 0.0,
|
| 696 |
+
"execute_generated": 0.0,
|
| 697 |
+
"fallback_rate": 1.0,
|
| 698 |
+
"hidden_chart_oracle_success": 1.0,
|
| 699 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 700 |
+
"outcome_ptr": 1.0,
|
| 701 |
+
"predicted_margin": 0.2711783741938117,
|
| 702 |
+
"proposal_oracle_success": 1.0,
|
| 703 |
+
"proposal_oracle_utility": 2.0,
|
| 704 |
+
"selected_candidate_index": 7.0,
|
| 705 |
+
"selected_success": 0.0,
|
| 706 |
+
"selected_success_gain_over_base": 0.0,
|
| 707 |
+
"selected_utility": 0.8334100246429443,
|
| 708 |
+
"selected_utility_gain_over_base": 0.0,
|
| 709 |
+
"selector_regret": 1.1665899753570557,
|
| 710 |
+
"success_selector_gap": 1.0,
|
| 711 |
+
"success_support_gap": 0.0,
|
| 712 |
+
"support_gap": 0.0,
|
| 713 |
+
"tau": 0.34408156791985406
|
| 714 |
+
},
|
| 715 |
+
"1509980664/train1": {
|
| 716 |
+
"base_success": 0.0,
|
| 717 |
+
"base_utility": 0.8334100246429443,
|
| 718 |
+
"coverage": 1.0,
|
| 719 |
+
"execute_generated": 1.0,
|
| 720 |
+
"fallback_rate": 0.0,
|
| 721 |
+
"hidden_chart_oracle_success": 1.0,
|
| 722 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 723 |
+
"outcome_ptr": 1.0,
|
| 724 |
+
"predicted_margin": 0.6271541093649009,
|
| 725 |
+
"proposal_oracle_success": 1.0,
|
| 726 |
+
"proposal_oracle_utility": 2.0,
|
| 727 |
+
"selected_candidate_index": 6.0,
|
| 728 |
+
"selected_success": 1.0,
|
| 729 |
+
"selected_success_gain_over_base": 1.0,
|
| 730 |
+
"selected_utility": 2.0,
|
| 731 |
+
"selected_utility_gain_over_base": 1.1665899753570557,
|
| 732 |
+
"selector_regret": 0.0,
|
| 733 |
+
"success_selector_gap": 0.0,
|
| 734 |
+
"success_support_gap": 0.0,
|
| 735 |
+
"support_gap": 0.0,
|
| 736 |
+
"tau": 0.34408156791985406
|
| 737 |
+
},
|
| 738 |
+
"1509980664/train2": {
|
| 739 |
+
"base_success": 0.0,
|
| 740 |
+
"base_utility": 0.8334100246429443,
|
| 741 |
+
"coverage": 0.0,
|
| 742 |
+
"execute_generated": 0.0,
|
| 743 |
+
"fallback_rate": 1.0,
|
| 744 |
+
"hidden_chart_oracle_success": 1.0,
|
| 745 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 746 |
+
"outcome_ptr": 0.0,
|
| 747 |
+
"predicted_margin": 0.3204171162126431,
|
| 748 |
+
"proposal_oracle_success": 0.0,
|
| 749 |
+
"proposal_oracle_utility": 0.8162217140197754,
|
| 750 |
+
"selected_candidate_index": 7.0,
|
| 751 |
+
"selected_success": 0.0,
|
| 752 |
+
"selected_success_gain_over_base": 0.0,
|
| 753 |
+
"selected_utility": 0.8334100246429443,
|
| 754 |
+
"selected_utility_gain_over_base": 0.0,
|
| 755 |
+
"selector_regret": 0.0,
|
| 756 |
+
"success_selector_gap": 0.0,
|
| 757 |
+
"success_support_gap": 1.0,
|
| 758 |
+
"support_gap": 1.1837782859802246,
|
| 759 |
+
"tau": 0.34408156791985406
|
| 760 |
+
},
|
| 761 |
+
"1522272686/train0": {
|
| 762 |
+
"base_success": 0.0,
|
| 763 |
+
"base_utility": 0.5839591026306152,
|
| 764 |
+
"coverage": 0.0,
|
| 765 |
+
"execute_generated": 0.0,
|
| 766 |
+
"fallback_rate": 1.0,
|
| 767 |
+
"hidden_chart_oracle_success": 1.0,
|
| 768 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 769 |
+
"outcome_ptr": 0.0,
|
| 770 |
+
"predicted_margin": 0.028797013011872402,
|
| 771 |
+
"proposal_oracle_success": 0.0,
|
| 772 |
+
"proposal_oracle_utility": 0.18325337767601013,
|
| 773 |
+
"selected_candidate_index": 1.0,
|
| 774 |
+
"selected_success": 0.0,
|
| 775 |
+
"selected_success_gain_over_base": 0.0,
|
| 776 |
+
"selected_utility": 0.5839591026306152,
|
| 777 |
+
"selected_utility_gain_over_base": 0.0,
|
| 778 |
+
"selector_regret": 0.0,
|
| 779 |
+
"success_selector_gap": 0.0,
|
| 780 |
+
"success_support_gap": 1.0,
|
| 781 |
+
"support_gap": 1.8167466223239899,
|
| 782 |
+
"tau": 0.34408156791985406
|
| 783 |
+
},
|
| 784 |
+
"1522272686/train1": {
|
| 785 |
+
"base_success": 0.0,
|
| 786 |
+
"base_utility": 0.5839591026306152,
|
| 787 |
+
"coverage": 0.0,
|
| 788 |
+
"execute_generated": 0.0,
|
| 789 |
+
"fallback_rate": 1.0,
|
| 790 |
+
"hidden_chart_oracle_success": 1.0,
|
| 791 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 792 |
+
"outcome_ptr": 0.0,
|
| 793 |
+
"predicted_margin": 0.04289956654184263,
|
| 794 |
+
"proposal_oracle_success": 0.0,
|
| 795 |
+
"proposal_oracle_utility": 0.07014383375644684,
|
| 796 |
+
"selected_candidate_index": 7.0,
|
| 797 |
+
"selected_success": 0.0,
|
| 798 |
+
"selected_success_gain_over_base": 0.0,
|
| 799 |
+
"selected_utility": 0.5839591026306152,
|
| 800 |
+
"selected_utility_gain_over_base": 0.0,
|
| 801 |
+
"selector_regret": 0.0,
|
| 802 |
+
"success_selector_gap": 0.0,
|
| 803 |
+
"success_support_gap": 1.0,
|
| 804 |
+
"support_gap": 1.9298561662435532,
|
| 805 |
+
"tau": 0.34408156791985406
|
| 806 |
+
},
|
| 807 |
+
"1522272686/train2": {
|
| 808 |
+
"base_success": 0.0,
|
| 809 |
+
"base_utility": 0.5839591026306152,
|
| 810 |
+
"coverage": 0.0,
|
| 811 |
+
"execute_generated": 0.0,
|
| 812 |
+
"fallback_rate": 1.0,
|
| 813 |
+
"hidden_chart_oracle_success": 1.0,
|
| 814 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 815 |
+
"outcome_ptr": 0.0,
|
| 816 |
+
"predicted_margin": 0.036313152627768894,
|
| 817 |
+
"proposal_oracle_success": 0.0,
|
| 818 |
+
"proposal_oracle_utility": 0.14937306940555573,
|
| 819 |
+
"selected_candidate_index": 1.0,
|
| 820 |
+
"selected_success": 0.0,
|
| 821 |
+
"selected_success_gain_over_base": 0.0,
|
| 822 |
+
"selected_utility": 0.5839591026306152,
|
| 823 |
+
"selected_utility_gain_over_base": 0.0,
|
| 824 |
+
"selector_regret": 0.0,
|
| 825 |
+
"success_selector_gap": 0.0,
|
| 826 |
+
"success_support_gap": 1.0,
|
| 827 |
+
"support_gap": 1.8506269305944443,
|
| 828 |
+
"tau": 0.34408156791985406
|
| 829 |
+
},
|
| 830 |
+
"1549324805/train0": {
|
| 831 |
+
"base_success": 0.0,
|
| 832 |
+
"base_utility": 0.10451483726501465,
|
| 833 |
+
"coverage": 0.0,
|
| 834 |
+
"execute_generated": 0.0,
|
| 835 |
+
"fallback_rate": 1.0,
|
| 836 |
+
"hidden_chart_oracle_success": 0.0,
|
| 837 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 838 |
+
"outcome_ptr": 0.0,
|
| 839 |
+
"predicted_margin": 0.11816772500779864,
|
| 840 |
+
"proposal_oracle_success": 0.0,
|
| 841 |
+
"proposal_oracle_utility": 0.0415392704308033,
|
| 842 |
+
"selected_candidate_index": 5.0,
|
| 843 |
+
"selected_success": 0.0,
|
| 844 |
+
"selected_success_gain_over_base": 0.0,
|
| 845 |
+
"selected_utility": 0.10451483726501465,
|
| 846 |
+
"selected_utility_gain_over_base": 0.0,
|
| 847 |
+
"selector_regret": 0.0,
|
| 848 |
+
"success_selector_gap": 0.0,
|
| 849 |
+
"success_support_gap": 0.0,
|
| 850 |
+
"support_gap": 0.255916815251112,
|
| 851 |
+
"tau": 0.34408156791985406
|
| 852 |
+
},
|
| 853 |
+
"1549324805/train1": {
|
| 854 |
+
"base_success": 0.0,
|
| 855 |
+
"base_utility": 0.10451483726501465,
|
| 856 |
+
"coverage": 0.0,
|
| 857 |
+
"execute_generated": 0.0,
|
| 858 |
+
"fallback_rate": 1.0,
|
| 859 |
+
"hidden_chart_oracle_success": 0.0,
|
| 860 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 861 |
+
"outcome_ptr": 1.0,
|
| 862 |
+
"predicted_margin": 0.12623384749452976,
|
| 863 |
+
"proposal_oracle_success": 0.0,
|
| 864 |
+
"proposal_oracle_utility": 0.19892151653766632,
|
| 865 |
+
"selected_candidate_index": 7.0,
|
| 866 |
+
"selected_success": 0.0,
|
| 867 |
+
"selected_success_gain_over_base": 0.0,
|
| 868 |
+
"selected_utility": 0.10451483726501465,
|
| 869 |
+
"selected_utility_gain_over_base": 0.0,
|
| 870 |
+
"selector_regret": 0.09440667927265167,
|
| 871 |
+
"success_selector_gap": 0.0,
|
| 872 |
+
"success_support_gap": 0.0,
|
| 873 |
+
"support_gap": 0.09853456914424896,
|
| 874 |
+
"tau": 0.34408156791985406
|
| 875 |
+
},
|
| 876 |
+
"1549324805/train2": {
|
| 877 |
+
"base_success": 0.0,
|
| 878 |
+
"base_utility": 0.10451483726501465,
|
| 879 |
+
"coverage": 0.0,
|
| 880 |
+
"execute_generated": 0.0,
|
| 881 |
+
"fallback_rate": 1.0,
|
| 882 |
+
"hidden_chart_oracle_success": 0.0,
|
| 883 |
+
"hidden_chart_oracle_utility": 0.2974560856819153,
|
| 884 |
+
"outcome_ptr": 0.0,
|
| 885 |
+
"predicted_margin": 0.08943732805519664,
|
| 886 |
+
"proposal_oracle_success": 0.0,
|
| 887 |
+
"proposal_oracle_utility": 0.09092829376459122,
|
| 888 |
+
"selected_candidate_index": 6.0,
|
| 889 |
+
"selected_success": 0.0,
|
| 890 |
+
"selected_success_gain_over_base": 0.0,
|
| 891 |
+
"selected_utility": 0.10451483726501465,
|
| 892 |
+
"selected_utility_gain_over_base": 0.0,
|
| 893 |
+
"selector_regret": 0.0,
|
| 894 |
+
"success_selector_gap": 0.0,
|
| 895 |
+
"success_support_gap": 0.0,
|
| 896 |
+
"support_gap": 0.20652779191732407,
|
| 897 |
+
"tau": 0.34408156791985406
|
| 898 |
+
},
|
| 899 |
+
"1578990937/train0": {
|
| 900 |
+
"base_success": 0.0,
|
| 901 |
+
"base_utility": 0.82413649559021,
|
| 902 |
+
"coverage": 0.0,
|
| 903 |
+
"execute_generated": 0.0,
|
| 904 |
+
"fallback_rate": 1.0,
|
| 905 |
+
"hidden_chart_oracle_success": 1.0,
|
| 906 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 907 |
+
"outcome_ptr": 1.0,
|
| 908 |
+
"predicted_margin": 0.1638611043693725,
|
| 909 |
+
"proposal_oracle_success": 1.0,
|
| 910 |
+
"proposal_oracle_utility": 2.0,
|
| 911 |
+
"selected_candidate_index": 4.0,
|
| 912 |
+
"selected_success": 0.0,
|
| 913 |
+
"selected_success_gain_over_base": 0.0,
|
| 914 |
+
"selected_utility": 0.82413649559021,
|
| 915 |
+
"selected_utility_gain_over_base": 0.0,
|
| 916 |
+
"selector_regret": 1.17586350440979,
|
| 917 |
+
"success_selector_gap": 1.0,
|
| 918 |
+
"success_support_gap": 0.0,
|
| 919 |
+
"support_gap": 0.0,
|
| 920 |
+
"tau": 0.34408156791985406
|
| 921 |
+
},
|
| 922 |
+
"1578990937/train1": {
|
| 923 |
+
"base_success": 0.0,
|
| 924 |
+
"base_utility": 0.82413649559021,
|
| 925 |
+
"coverage": 0.0,
|
| 926 |
+
"execute_generated": 0.0,
|
| 927 |
+
"fallback_rate": 1.0,
|
| 928 |
+
"hidden_chart_oracle_success": 1.0,
|
| 929 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 930 |
+
"outcome_ptr": 1.0,
|
| 931 |
+
"predicted_margin": 0.15477671498906614,
|
| 932 |
+
"proposal_oracle_success": 1.0,
|
| 933 |
+
"proposal_oracle_utility": 2.0,
|
| 934 |
+
"selected_candidate_index": 5.0,
|
| 935 |
+
"selected_success": 0.0,
|
| 936 |
+
"selected_success_gain_over_base": 0.0,
|
| 937 |
+
"selected_utility": 0.82413649559021,
|
| 938 |
+
"selected_utility_gain_over_base": 0.0,
|
| 939 |
+
"selector_regret": 1.17586350440979,
|
| 940 |
+
"success_selector_gap": 1.0,
|
| 941 |
+
"success_support_gap": 0.0,
|
| 942 |
+
"support_gap": 0.0,
|
| 943 |
+
"tau": 0.34408156791985406
|
| 944 |
+
},
|
| 945 |
+
"1578990937/train2": {
|
| 946 |
+
"base_success": 0.0,
|
| 947 |
+
"base_utility": 0.82413649559021,
|
| 948 |
+
"coverage": 0.0,
|
| 949 |
+
"execute_generated": 0.0,
|
| 950 |
+
"fallback_rate": 1.0,
|
| 951 |
+
"hidden_chart_oracle_success": 1.0,
|
| 952 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 953 |
+
"outcome_ptr": 1.0,
|
| 954 |
+
"predicted_margin": 0.09931026220178542,
|
| 955 |
+
"proposal_oracle_success": 1.0,
|
| 956 |
+
"proposal_oracle_utility": 2.0,
|
| 957 |
+
"selected_candidate_index": 0.0,
|
| 958 |
+
"selected_success": 0.0,
|
| 959 |
+
"selected_success_gain_over_base": 0.0,
|
| 960 |
+
"selected_utility": 0.82413649559021,
|
| 961 |
+
"selected_utility_gain_over_base": 0.0,
|
| 962 |
+
"selector_regret": 1.17586350440979,
|
| 963 |
+
"success_selector_gap": 1.0,
|
| 964 |
+
"success_support_gap": 0.0,
|
| 965 |
+
"support_gap": 0.0,
|
| 966 |
+
"tau": 0.34408156791985406
|
| 967 |
+
},
|
| 968 |
+
"1747178030/train0": {
|
| 969 |
+
"base_success": 1.0,
|
| 970 |
+
"base_utility": 2.0,
|
| 971 |
+
"coverage": 1.0,
|
| 972 |
+
"execute_generated": 1.0,
|
| 973 |
+
"fallback_rate": 0.0,
|
| 974 |
+
"hidden_chart_oracle_success": 1.0,
|
| 975 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 976 |
+
"outcome_ptr": 0.0,
|
| 977 |
+
"predicted_margin": 0.7924670056628417,
|
| 978 |
+
"proposal_oracle_success": 1.0,
|
| 979 |
+
"proposal_oracle_utility": 2.0,
|
| 980 |
+
"selected_candidate_index": 4.0,
|
| 981 |
+
"selected_success": 1.0,
|
| 982 |
+
"selected_success_gain_over_base": 0.0,
|
| 983 |
+
"selected_utility": 2.0,
|
| 984 |
+
"selected_utility_gain_over_base": 0.0,
|
| 985 |
+
"selector_regret": 0.0,
|
| 986 |
+
"success_selector_gap": 0.0,
|
| 987 |
+
"success_support_gap": 0.0,
|
| 988 |
+
"support_gap": 0.0,
|
| 989 |
+
"tau": 0.34408156791985406
|
| 990 |
+
},
|
| 991 |
+
"1747178030/train1": {
|
| 992 |
+
"base_success": 1.0,
|
| 993 |
+
"base_utility": 2.0,
|
| 994 |
+
"coverage": 1.0,
|
| 995 |
+
"execute_generated": 1.0,
|
| 996 |
+
"fallback_rate": 0.0,
|
| 997 |
+
"hidden_chart_oracle_success": 1.0,
|
| 998 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 999 |
+
"outcome_ptr": 0.0,
|
| 1000 |
+
"predicted_margin": 0.8683209874745884,
|
| 1001 |
+
"proposal_oracle_success": 1.0,
|
| 1002 |
+
"proposal_oracle_utility": 2.0,
|
| 1003 |
+
"selected_candidate_index": 1.0,
|
| 1004 |
+
"selected_success": 1.0,
|
| 1005 |
+
"selected_success_gain_over_base": 0.0,
|
| 1006 |
+
"selected_utility": 2.0,
|
| 1007 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1008 |
+
"selector_regret": 0.0,
|
| 1009 |
+
"success_selector_gap": 0.0,
|
| 1010 |
+
"success_support_gap": 0.0,
|
| 1011 |
+
"support_gap": 0.0,
|
| 1012 |
+
"tau": 0.34408156791985406
|
| 1013 |
+
},
|
| 1014 |
+
"1747178030/train2": {
|
| 1015 |
+
"base_success": 1.0,
|
| 1016 |
+
"base_utility": 2.0,
|
| 1017 |
+
"coverage": 1.0,
|
| 1018 |
+
"execute_generated": 1.0,
|
| 1019 |
+
"fallback_rate": 0.0,
|
| 1020 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1021 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1022 |
+
"outcome_ptr": 0.0,
|
| 1023 |
+
"predicted_margin": 0.6084844687781336,
|
| 1024 |
+
"proposal_oracle_success": 1.0,
|
| 1025 |
+
"proposal_oracle_utility": 2.0,
|
| 1026 |
+
"selected_candidate_index": 2.0,
|
| 1027 |
+
"selected_success": 1.0,
|
| 1028 |
+
"selected_success_gain_over_base": 0.0,
|
| 1029 |
+
"selected_utility": 2.0,
|
| 1030 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1031 |
+
"selector_regret": 0.0,
|
| 1032 |
+
"success_selector_gap": 0.0,
|
| 1033 |
+
"success_support_gap": 0.0,
|
| 1034 |
+
"support_gap": 0.0,
|
| 1035 |
+
"tau": 0.34408156791985406
|
| 1036 |
+
},
|
| 1037 |
+
"1790188787/train0": {
|
| 1038 |
+
"base_success": 0.0,
|
| 1039 |
+
"base_utility": 0.12476746737957001,
|
| 1040 |
+
"coverage": 1.0,
|
| 1041 |
+
"execute_generated": 1.0,
|
| 1042 |
+
"fallback_rate": 0.0,
|
| 1043 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1044 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1045 |
+
"outcome_ptr": 0.0,
|
| 1046 |
+
"predicted_margin": 0.8362820060696806,
|
| 1047 |
+
"proposal_oracle_success": 0.0,
|
| 1048 |
+
"proposal_oracle_utility": 0.09791924059391022,
|
| 1049 |
+
"selected_candidate_index": 1.0,
|
| 1050 |
+
"selected_success": 0.0,
|
| 1051 |
+
"selected_success_gain_over_base": 0.0,
|
| 1052 |
+
"selected_utility": 0.06047999858856201,
|
| 1053 |
+
"selected_utility_gain_over_base": -0.064287468791008,
|
| 1054 |
+
"selector_regret": 0.037439242005348206,
|
| 1055 |
+
"success_selector_gap": 0.0,
|
| 1056 |
+
"success_support_gap": 1.0,
|
| 1057 |
+
"support_gap": 1.9020807594060898,
|
| 1058 |
+
"tau": 0.34408156791985406
|
| 1059 |
+
},
|
| 1060 |
+
"1790188787/train1": {
|
| 1061 |
+
"base_success": 0.0,
|
| 1062 |
+
"base_utility": 0.12476746737957001,
|
| 1063 |
+
"coverage": 1.0,
|
| 1064 |
+
"execute_generated": 1.0,
|
| 1065 |
+
"fallback_rate": 0.0,
|
| 1066 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1067 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1068 |
+
"outcome_ptr": 1.0,
|
| 1069 |
+
"predicted_margin": 0.7982925168010331,
|
| 1070 |
+
"proposal_oracle_success": 0.0,
|
| 1071 |
+
"proposal_oracle_utility": 0.13031470775604248,
|
| 1072 |
+
"selected_candidate_index": 0.0,
|
| 1073 |
+
"selected_success": 0.0,
|
| 1074 |
+
"selected_success_gain_over_base": 0.0,
|
| 1075 |
+
"selected_utility": 0.1146477460861206,
|
| 1076 |
+
"selected_utility_gain_over_base": -0.010119721293449402,
|
| 1077 |
+
"selector_regret": 0.015666961669921875,
|
| 1078 |
+
"success_selector_gap": 0.0,
|
| 1079 |
+
"success_support_gap": 1.0,
|
| 1080 |
+
"support_gap": 1.8696852922439575,
|
| 1081 |
+
"tau": 0.34408156791985406
|
| 1082 |
+
},
|
| 1083 |
+
"1790188787/train2": {
|
| 1084 |
+
"base_success": 0.0,
|
| 1085 |
+
"base_utility": 0.12476746737957001,
|
| 1086 |
+
"coverage": 1.0,
|
| 1087 |
+
"execute_generated": 1.0,
|
| 1088 |
+
"fallback_rate": 0.0,
|
| 1089 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1090 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1091 |
+
"outcome_ptr": 1.0,
|
| 1092 |
+
"predicted_margin": 0.840936591096665,
|
| 1093 |
+
"proposal_oracle_success": 1.0,
|
| 1094 |
+
"proposal_oracle_utility": 2.0,
|
| 1095 |
+
"selected_candidate_index": 3.0,
|
| 1096 |
+
"selected_success": 1.0,
|
| 1097 |
+
"selected_success_gain_over_base": 1.0,
|
| 1098 |
+
"selected_utility": 2.0,
|
| 1099 |
+
"selected_utility_gain_over_base": 1.87523253262043,
|
| 1100 |
+
"selector_regret": 0.0,
|
| 1101 |
+
"success_selector_gap": 0.0,
|
| 1102 |
+
"success_support_gap": 0.0,
|
| 1103 |
+
"support_gap": 0.0,
|
| 1104 |
+
"tau": 0.34408156791985406
|
| 1105 |
+
},
|
| 1106 |
+
"1822210471/train0": {
|
| 1107 |
+
"base_success": 0.0,
|
| 1108 |
+
"base_utility": 0.07191530615091324,
|
| 1109 |
+
"coverage": 1.0,
|
| 1110 |
+
"execute_generated": 1.0,
|
| 1111 |
+
"fallback_rate": 0.0,
|
| 1112 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1113 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1114 |
+
"outcome_ptr": 1.0,
|
| 1115 |
+
"predicted_margin": 0.6455405096871031,
|
| 1116 |
+
"proposal_oracle_success": 1.0,
|
| 1117 |
+
"proposal_oracle_utility": 2.0,
|
| 1118 |
+
"selected_candidate_index": 0.0,
|
| 1119 |
+
"selected_success": 0.0,
|
| 1120 |
+
"selected_success_gain_over_base": 0.0,
|
| 1121 |
+
"selected_utility": 0.06306678056716919,
|
| 1122 |
+
"selected_utility_gain_over_base": -0.008848525583744049,
|
| 1123 |
+
"selector_regret": 1.9369332194328308,
|
| 1124 |
+
"success_selector_gap": 1.0,
|
| 1125 |
+
"success_support_gap": 0.0,
|
| 1126 |
+
"support_gap": 0.0,
|
| 1127 |
+
"tau": 0.34408156791985406
|
| 1128 |
+
},
|
| 1129 |
+
"1822210471/train1": {
|
| 1130 |
+
"base_success": 0.0,
|
| 1131 |
+
"base_utility": 0.07191530615091324,
|
| 1132 |
+
"coverage": 0.0,
|
| 1133 |
+
"execute_generated": 0.0,
|
| 1134 |
+
"fallback_rate": 1.0,
|
| 1135 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1136 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1137 |
+
"outcome_ptr": 1.0,
|
| 1138 |
+
"predicted_margin": 0.3054049598551906,
|
| 1139 |
+
"proposal_oracle_success": 1.0,
|
| 1140 |
+
"proposal_oracle_utility": 2.0,
|
| 1141 |
+
"selected_candidate_index": 3.0,
|
| 1142 |
+
"selected_success": 0.0,
|
| 1143 |
+
"selected_success_gain_over_base": 0.0,
|
| 1144 |
+
"selected_utility": 0.07191530615091324,
|
| 1145 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1146 |
+
"selector_regret": 1.9280846938490868,
|
| 1147 |
+
"success_selector_gap": 1.0,
|
| 1148 |
+
"success_support_gap": 0.0,
|
| 1149 |
+
"support_gap": 0.0,
|
| 1150 |
+
"tau": 0.34408156791985406
|
| 1151 |
+
},
|
| 1152 |
+
"1822210471/train2": {
|
| 1153 |
+
"base_success": 0.0,
|
| 1154 |
+
"base_utility": 0.07191530615091324,
|
| 1155 |
+
"coverage": 1.0,
|
| 1156 |
+
"execute_generated": 1.0,
|
| 1157 |
+
"fallback_rate": 0.0,
|
| 1158 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1159 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1160 |
+
"outcome_ptr": 1.0,
|
| 1161 |
+
"predicted_margin": 0.521098644476326,
|
| 1162 |
+
"proposal_oracle_success": 1.0,
|
| 1163 |
+
"proposal_oracle_utility": 2.0,
|
| 1164 |
+
"selected_candidate_index": 2.0,
|
| 1165 |
+
"selected_success": 0.0,
|
| 1166 |
+
"selected_success_gain_over_base": 0.0,
|
| 1167 |
+
"selected_utility": 0.08819514513015747,
|
| 1168 |
+
"selected_utility_gain_over_base": 0.016279838979244232,
|
| 1169 |
+
"selector_regret": 1.9118048548698425,
|
| 1170 |
+
"success_selector_gap": 1.0,
|
| 1171 |
+
"success_support_gap": 0.0,
|
| 1172 |
+
"support_gap": 0.0,
|
| 1173 |
+
"tau": 0.34408156791985406
|
| 1174 |
+
},
|
| 1175 |
+
"1845489013/train0": {
|
| 1176 |
+
"base_success": 1.0,
|
| 1177 |
+
"base_utility": 2.0,
|
| 1178 |
+
"coverage": 1.0,
|
| 1179 |
+
"execute_generated": 1.0,
|
| 1180 |
+
"fallback_rate": 0.0,
|
| 1181 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1182 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1183 |
+
"outcome_ptr": 0.0,
|
| 1184 |
+
"predicted_margin": 0.8344191292729335,
|
| 1185 |
+
"proposal_oracle_success": 1.0,
|
| 1186 |
+
"proposal_oracle_utility": 2.0,
|
| 1187 |
+
"selected_candidate_index": 4.0,
|
| 1188 |
+
"selected_success": 1.0,
|
| 1189 |
+
"selected_success_gain_over_base": 0.0,
|
| 1190 |
+
"selected_utility": 2.0,
|
| 1191 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1192 |
+
"selector_regret": 0.0,
|
| 1193 |
+
"success_selector_gap": 0.0,
|
| 1194 |
+
"success_support_gap": 0.0,
|
| 1195 |
+
"support_gap": 0.0,
|
| 1196 |
+
"tau": 0.34408156791985406
|
| 1197 |
+
},
|
| 1198 |
+
"1845489013/train1": {
|
| 1199 |
+
"base_success": 1.0,
|
| 1200 |
+
"base_utility": 2.0,
|
| 1201 |
+
"coverage": 1.0,
|
| 1202 |
+
"execute_generated": 1.0,
|
| 1203 |
+
"fallback_rate": 0.0,
|
| 1204 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1205 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1206 |
+
"outcome_ptr": 0.0,
|
| 1207 |
+
"predicted_margin": 0.8748628344239395,
|
| 1208 |
+
"proposal_oracle_success": 1.0,
|
| 1209 |
+
"proposal_oracle_utility": 2.0,
|
| 1210 |
+
"selected_candidate_index": 3.0,
|
| 1211 |
+
"selected_success": 1.0,
|
| 1212 |
+
"selected_success_gain_over_base": 0.0,
|
| 1213 |
+
"selected_utility": 2.0,
|
| 1214 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1215 |
+
"selector_regret": 0.0,
|
| 1216 |
+
"success_selector_gap": 0.0,
|
| 1217 |
+
"success_support_gap": 0.0,
|
| 1218 |
+
"support_gap": 0.0,
|
| 1219 |
+
"tau": 0.34408156791985406
|
| 1220 |
+
},
|
| 1221 |
+
"1845489013/train2": {
|
| 1222 |
+
"base_success": 1.0,
|
| 1223 |
+
"base_utility": 2.0,
|
| 1224 |
+
"coverage": 1.0,
|
| 1225 |
+
"execute_generated": 1.0,
|
| 1226 |
+
"fallback_rate": 0.0,
|
| 1227 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1228 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1229 |
+
"outcome_ptr": 0.0,
|
| 1230 |
+
"predicted_margin": 0.7678061787371938,
|
| 1231 |
+
"proposal_oracle_success": 1.0,
|
| 1232 |
+
"proposal_oracle_utility": 2.0,
|
| 1233 |
+
"selected_candidate_index": 7.0,
|
| 1234 |
+
"selected_success": 1.0,
|
| 1235 |
+
"selected_success_gain_over_base": 0.0,
|
| 1236 |
+
"selected_utility": 2.0,
|
| 1237 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1238 |
+
"selector_regret": 0.0,
|
| 1239 |
+
"success_selector_gap": 0.0,
|
| 1240 |
+
"success_support_gap": 0.0,
|
| 1241 |
+
"support_gap": 0.0,
|
| 1242 |
+
"tau": 0.34408156791985406
|
| 1243 |
+
},
|
| 1244 |
+
"1999022574/train0": {
|
| 1245 |
+
"base_success": 1.0,
|
| 1246 |
+
"base_utility": 2.0,
|
| 1247 |
+
"coverage": 1.0,
|
| 1248 |
+
"execute_generated": 1.0,
|
| 1249 |
+
"fallback_rate": 0.0,
|
| 1250 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1251 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1252 |
+
"outcome_ptr": 0.0,
|
| 1253 |
+
"predicted_margin": 0.5365982119223281,
|
| 1254 |
+
"proposal_oracle_success": 1.0,
|
| 1255 |
+
"proposal_oracle_utility": 2.0,
|
| 1256 |
+
"selected_candidate_index": 6.0,
|
| 1257 |
+
"selected_success": 1.0,
|
| 1258 |
+
"selected_success_gain_over_base": 0.0,
|
| 1259 |
+
"selected_utility": 2.0,
|
| 1260 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1261 |
+
"selector_regret": 0.0,
|
| 1262 |
+
"success_selector_gap": 0.0,
|
| 1263 |
+
"success_support_gap": 0.0,
|
| 1264 |
+
"support_gap": 0.0,
|
| 1265 |
+
"tau": 0.34408156791985406
|
| 1266 |
+
},
|
| 1267 |
+
"1999022574/train1": {
|
| 1268 |
+
"base_success": 1.0,
|
| 1269 |
+
"base_utility": 2.0,
|
| 1270 |
+
"coverage": 1.0,
|
| 1271 |
+
"execute_generated": 1.0,
|
| 1272 |
+
"fallback_rate": 0.0,
|
| 1273 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1274 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1275 |
+
"outcome_ptr": 0.0,
|
| 1276 |
+
"predicted_margin": 0.6265576940062217,
|
| 1277 |
+
"proposal_oracle_success": 1.0,
|
| 1278 |
+
"proposal_oracle_utility": 2.0,
|
| 1279 |
+
"selected_candidate_index": 2.0,
|
| 1280 |
+
"selected_success": 1.0,
|
| 1281 |
+
"selected_success_gain_over_base": 0.0,
|
| 1282 |
+
"selected_utility": 2.0,
|
| 1283 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1284 |
+
"selector_regret": 0.0,
|
| 1285 |
+
"success_selector_gap": 0.0,
|
| 1286 |
+
"success_support_gap": 0.0,
|
| 1287 |
+
"support_gap": 0.0,
|
| 1288 |
+
"tau": 0.34408156791985406
|
| 1289 |
+
},
|
| 1290 |
+
"1999022574/train2": {
|
| 1291 |
+
"base_success": 1.0,
|
| 1292 |
+
"base_utility": 2.0,
|
| 1293 |
+
"coverage": 0.0,
|
| 1294 |
+
"execute_generated": 0.0,
|
| 1295 |
+
"fallback_rate": 1.0,
|
| 1296 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1297 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1298 |
+
"outcome_ptr": 0.0,
|
| 1299 |
+
"predicted_margin": 0.29912216229597205,
|
| 1300 |
+
"proposal_oracle_success": 1.0,
|
| 1301 |
+
"proposal_oracle_utility": 2.0,
|
| 1302 |
+
"selected_candidate_index": 4.0,
|
| 1303 |
+
"selected_success": 1.0,
|
| 1304 |
+
"selected_success_gain_over_base": 0.0,
|
| 1305 |
+
"selected_utility": 2.0,
|
| 1306 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1307 |
+
"selector_regret": 0.0,
|
| 1308 |
+
"success_selector_gap": 0.0,
|
| 1309 |
+
"success_support_gap": 0.0,
|
| 1310 |
+
"support_gap": 0.0,
|
| 1311 |
+
"tau": 0.34408156791985406
|
| 1312 |
+
},
|
| 1313 |
+
"2012211287/train0": {
|
| 1314 |
+
"base_success": 0.0,
|
| 1315 |
+
"base_utility": 0.7236053347587585,
|
| 1316 |
+
"coverage": 0.0,
|
| 1317 |
+
"execute_generated": 0.0,
|
| 1318 |
+
"fallback_rate": 1.0,
|
| 1319 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1320 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1321 |
+
"outcome_ptr": 1.0,
|
| 1322 |
+
"predicted_margin": 0.28601672596330097,
|
| 1323 |
+
"proposal_oracle_success": 1.0,
|
| 1324 |
+
"proposal_oracle_utility": 2.0,
|
| 1325 |
+
"selected_candidate_index": 2.0,
|
| 1326 |
+
"selected_success": 0.0,
|
| 1327 |
+
"selected_success_gain_over_base": 0.0,
|
| 1328 |
+
"selected_utility": 0.7236053347587585,
|
| 1329 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1330 |
+
"selector_regret": 1.2763946652412415,
|
| 1331 |
+
"success_selector_gap": 1.0,
|
| 1332 |
+
"success_support_gap": 0.0,
|
| 1333 |
+
"support_gap": 0.0,
|
| 1334 |
+
"tau": 0.34408156791985406
|
| 1335 |
+
},
|
| 1336 |
+
"2012211287/train1": {
|
| 1337 |
+
"base_success": 0.0,
|
| 1338 |
+
"base_utility": 0.7236053347587585,
|
| 1339 |
+
"coverage": 1.0,
|
| 1340 |
+
"execute_generated": 1.0,
|
| 1341 |
+
"fallback_rate": 0.0,
|
| 1342 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1343 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1344 |
+
"outcome_ptr": 1.0,
|
| 1345 |
+
"predicted_margin": 0.5007199064566366,
|
| 1346 |
+
"proposal_oracle_success": 1.0,
|
| 1347 |
+
"proposal_oracle_utility": 2.0,
|
| 1348 |
+
"selected_candidate_index": 2.0,
|
| 1349 |
+
"selected_success": 0.0,
|
| 1350 |
+
"selected_success_gain_over_base": 0.0,
|
| 1351 |
+
"selected_utility": 0.7183246612548828,
|
| 1352 |
+
"selected_utility_gain_over_base": -0.005280673503875732,
|
| 1353 |
+
"selector_regret": 1.2816753387451172,
|
| 1354 |
+
"success_selector_gap": 1.0,
|
| 1355 |
+
"success_support_gap": 0.0,
|
| 1356 |
+
"support_gap": 0.0,
|
| 1357 |
+
"tau": 0.34408156791985406
|
| 1358 |
+
},
|
| 1359 |
+
"2012211287/train2": {
|
| 1360 |
+
"base_success": 0.0,
|
| 1361 |
+
"base_utility": 0.7236053347587585,
|
| 1362 |
+
"coverage": 1.0,
|
| 1363 |
+
"execute_generated": 1.0,
|
| 1364 |
+
"fallback_rate": 0.0,
|
| 1365 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1366 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1367 |
+
"outcome_ptr": 1.0,
|
| 1368 |
+
"predicted_margin": 0.448502256643165,
|
| 1369 |
+
"proposal_oracle_success": 1.0,
|
| 1370 |
+
"proposal_oracle_utility": 2.0,
|
| 1371 |
+
"selected_candidate_index": 2.0,
|
| 1372 |
+
"selected_success": 1.0,
|
| 1373 |
+
"selected_success_gain_over_base": 1.0,
|
| 1374 |
+
"selected_utility": 2.0,
|
| 1375 |
+
"selected_utility_gain_over_base": 1.2763946652412415,
|
| 1376 |
+
"selector_regret": 0.0,
|
| 1377 |
+
"success_selector_gap": 0.0,
|
| 1378 |
+
"success_support_gap": 0.0,
|
| 1379 |
+
"support_gap": 0.0,
|
| 1380 |
+
"tau": 0.34408156791985406
|
| 1381 |
+
},
|
| 1382 |
+
"2038594191/train0": {
|
| 1383 |
+
"base_success": 1.0,
|
| 1384 |
+
"base_utility": 2.0,
|
| 1385 |
+
"coverage": 0.0,
|
| 1386 |
+
"execute_generated": 0.0,
|
| 1387 |
+
"fallback_rate": 1.0,
|
| 1388 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1389 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1390 |
+
"outcome_ptr": 0.0,
|
| 1391 |
+
"predicted_margin": 0.30175972912544086,
|
| 1392 |
+
"proposal_oracle_success": 1.0,
|
| 1393 |
+
"proposal_oracle_utility": 2.0,
|
| 1394 |
+
"selected_candidate_index": 7.0,
|
| 1395 |
+
"selected_success": 1.0,
|
| 1396 |
+
"selected_success_gain_over_base": 0.0,
|
| 1397 |
+
"selected_utility": 2.0,
|
| 1398 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1399 |
+
"selector_regret": 0.0,
|
| 1400 |
+
"success_selector_gap": 0.0,
|
| 1401 |
+
"success_support_gap": 0.0,
|
| 1402 |
+
"support_gap": 0.0,
|
| 1403 |
+
"tau": 0.34408156791985406
|
| 1404 |
+
},
|
| 1405 |
+
"2038594191/train1": {
|
| 1406 |
+
"base_success": 1.0,
|
| 1407 |
+
"base_utility": 2.0,
|
| 1408 |
+
"coverage": 1.0,
|
| 1409 |
+
"execute_generated": 1.0,
|
| 1410 |
+
"fallback_rate": 0.0,
|
| 1411 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1412 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1413 |
+
"outcome_ptr": 0.0,
|
| 1414 |
+
"predicted_margin": 0.3478707570137989,
|
| 1415 |
+
"proposal_oracle_success": 1.0,
|
| 1416 |
+
"proposal_oracle_utility": 2.0,
|
| 1417 |
+
"selected_candidate_index": 5.0,
|
| 1418 |
+
"selected_success": 0.0,
|
| 1419 |
+
"selected_success_gain_over_base": -1.0,
|
| 1420 |
+
"selected_utility": 0.07674666494131088,
|
| 1421 |
+
"selected_utility_gain_over_base": -1.9232533350586891,
|
| 1422 |
+
"selector_regret": 1.9232533350586891,
|
| 1423 |
+
"success_selector_gap": 1.0,
|
| 1424 |
+
"success_support_gap": 0.0,
|
| 1425 |
+
"support_gap": 0.0,
|
| 1426 |
+
"tau": 0.34408156791985406
|
| 1427 |
+
},
|
| 1428 |
+
"2038594191/train2": {
|
| 1429 |
+
"base_success": 1.0,
|
| 1430 |
+
"base_utility": 2.0,
|
| 1431 |
+
"coverage": 1.0,
|
| 1432 |
+
"execute_generated": 1.0,
|
| 1433 |
+
"fallback_rate": 0.0,
|
| 1434 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1435 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1436 |
+
"outcome_ptr": 0.0,
|
| 1437 |
+
"predicted_margin": 0.6956523320904741,
|
| 1438 |
+
"proposal_oracle_success": 1.0,
|
| 1439 |
+
"proposal_oracle_utility": 2.0,
|
| 1440 |
+
"selected_candidate_index": 3.0,
|
| 1441 |
+
"selected_success": 0.0,
|
| 1442 |
+
"selected_success_gain_over_base": -1.0,
|
| 1443 |
+
"selected_utility": 0.12977690994739532,
|
| 1444 |
+
"selected_utility_gain_over_base": -1.8702230900526047,
|
| 1445 |
+
"selector_regret": 1.8702230900526047,
|
| 1446 |
+
"success_selector_gap": 1.0,
|
| 1447 |
+
"success_support_gap": 0.0,
|
| 1448 |
+
"support_gap": 0.0,
|
| 1449 |
+
"tau": 0.34408156791985406
|
| 1450 |
+
},
|
| 1451 |
+
"2054899126/train0": {
|
| 1452 |
+
"base_success": 1.0,
|
| 1453 |
+
"base_utility": 2.0,
|
| 1454 |
+
"coverage": 0.5,
|
| 1455 |
+
"execute_generated": 0.5,
|
| 1456 |
+
"fallback_rate": 0.5,
|
| 1457 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1458 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1459 |
+
"outcome_ptr": 0.0,
|
| 1460 |
+
"predicted_margin": 0.40038765069149596,
|
| 1461 |
+
"proposal_oracle_success": 0.5,
|
| 1462 |
+
"proposal_oracle_utility": 1.077283151447773,
|
| 1463 |
+
"selected_candidate_index": 0.5,
|
| 1464 |
+
"selected_success": 0.5,
|
| 1465 |
+
"selected_success_gain_over_base": -0.5,
|
| 1466 |
+
"selected_utility": 1.0714938417077065,
|
| 1467 |
+
"selected_utility_gain_over_base": -0.9285061582922935,
|
| 1468 |
+
"selector_regret": 0.005789309740066528,
|
| 1469 |
+
"success_selector_gap": 0.0,
|
| 1470 |
+
"success_support_gap": 0.5,
|
| 1471 |
+
"support_gap": 0.922716848552227,
|
| 1472 |
+
"tau": 0.34408156791985406
|
| 1473 |
+
},
|
| 1474 |
+
"2054899126/train1": {
|
| 1475 |
+
"base_success": 1.0,
|
| 1476 |
+
"base_utility": 2.0,
|
| 1477 |
+
"coverage": 0.5,
|
| 1478 |
+
"execute_generated": 0.5,
|
| 1479 |
+
"fallback_rate": 0.5,
|
| 1480 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1481 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1482 |
+
"outcome_ptr": 0.0,
|
| 1483 |
+
"predicted_margin": 0.5251440689575144,
|
| 1484 |
+
"proposal_oracle_success": 0.5,
|
| 1485 |
+
"proposal_oracle_utility": 1.0696808770298958,
|
| 1486 |
+
"selected_candidate_index": 4.0,
|
| 1487 |
+
"selected_success": 0.5,
|
| 1488 |
+
"selected_success_gain_over_base": -0.5,
|
| 1489 |
+
"selected_utility": 1.0660420358181,
|
| 1490 |
+
"selected_utility_gain_over_base": -0.9339579641819,
|
| 1491 |
+
"selector_regret": 0.003638841211795807,
|
| 1492 |
+
"success_selector_gap": 0.0,
|
| 1493 |
+
"success_support_gap": 0.5,
|
| 1494 |
+
"support_gap": 0.9303191229701042,
|
| 1495 |
+
"tau": 0.34408156791985406
|
| 1496 |
+
},
|
| 1497 |
+
"2054899126/train2": {
|
| 1498 |
+
"base_success": 1.0,
|
| 1499 |
+
"base_utility": 2.0,
|
| 1500 |
+
"coverage": 0.5,
|
| 1501 |
+
"execute_generated": 0.5,
|
| 1502 |
+
"fallback_rate": 0.5,
|
| 1503 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1504 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1505 |
+
"outcome_ptr": 0.0,
|
| 1506 |
+
"predicted_margin": 0.334834464710266,
|
| 1507 |
+
"proposal_oracle_success": 0.5,
|
| 1508 |
+
"proposal_oracle_utility": 1.0455262660980225,
|
| 1509 |
+
"selected_candidate_index": 3.5,
|
| 1510 |
+
"selected_success": 0.5,
|
| 1511 |
+
"selected_success_gain_over_base": -0.5,
|
| 1512 |
+
"selected_utility": 1.0276100430637598,
|
| 1513 |
+
"selected_utility_gain_over_base": -0.9723899569362402,
|
| 1514 |
+
"selector_regret": 0.017916223034262657,
|
| 1515 |
+
"success_selector_gap": 0.0,
|
| 1516 |
+
"success_support_gap": 0.5,
|
| 1517 |
+
"support_gap": 0.9544737339019775,
|
| 1518 |
+
"tau": 0.34408156791985406
|
| 1519 |
+
},
|
| 1520 |
+
"2061635888/train0": {
|
| 1521 |
+
"base_success": 0.0,
|
| 1522 |
+
"base_utility": 0.05225050449371338,
|
| 1523 |
+
"coverage": 0.0,
|
| 1524 |
+
"execute_generated": 0.0,
|
| 1525 |
+
"fallback_rate": 1.0,
|
| 1526 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1527 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1528 |
+
"outcome_ptr": 1.0,
|
| 1529 |
+
"predicted_margin": 0.25347796342569456,
|
| 1530 |
+
"proposal_oracle_success": 0.0,
|
| 1531 |
+
"proposal_oracle_utility": 0.09799930453300476,
|
| 1532 |
+
"selected_candidate_index": 7.0,
|
| 1533 |
+
"selected_success": 0.0,
|
| 1534 |
+
"selected_success_gain_over_base": 0.0,
|
| 1535 |
+
"selected_utility": 0.05225050449371338,
|
| 1536 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1537 |
+
"selector_regret": 0.04574880003929138,
|
| 1538 |
+
"success_selector_gap": 0.0,
|
| 1539 |
+
"success_support_gap": 1.0,
|
| 1540 |
+
"support_gap": 1.9020006954669952,
|
| 1541 |
+
"tau": 0.34408156791985406
|
| 1542 |
+
},
|
| 1543 |
+
"2061635888/train1": {
|
| 1544 |
+
"base_success": 0.0,
|
| 1545 |
+
"base_utility": 0.05225050449371338,
|
| 1546 |
+
"coverage": 0.0,
|
| 1547 |
+
"execute_generated": 0.0,
|
| 1548 |
+
"fallback_rate": 1.0,
|
| 1549 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1550 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1551 |
+
"outcome_ptr": 1.0,
|
| 1552 |
+
"predicted_margin": 0.2576974397440808,
|
| 1553 |
+
"proposal_oracle_success": 0.0,
|
| 1554 |
+
"proposal_oracle_utility": 0.07580336928367615,
|
| 1555 |
+
"selected_candidate_index": 1.0,
|
| 1556 |
+
"selected_success": 0.0,
|
| 1557 |
+
"selected_success_gain_over_base": 0.0,
|
| 1558 |
+
"selected_utility": 0.05225050449371338,
|
| 1559 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1560 |
+
"selector_regret": 0.02355286478996277,
|
| 1561 |
+
"success_selector_gap": 0.0,
|
| 1562 |
+
"success_support_gap": 1.0,
|
| 1563 |
+
"support_gap": 1.9241966307163239,
|
| 1564 |
+
"tau": 0.34408156791985406
|
| 1565 |
+
},
|
| 1566 |
+
"2061635888/train2": {
|
| 1567 |
+
"base_success": 0.0,
|
| 1568 |
+
"base_utility": 0.05225050449371338,
|
| 1569 |
+
"coverage": 0.0,
|
| 1570 |
+
"execute_generated": 0.0,
|
| 1571 |
+
"fallback_rate": 1.0,
|
| 1572 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1573 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1574 |
+
"outcome_ptr": 1.0,
|
| 1575 |
+
"predicted_margin": 0.14461486871684395,
|
| 1576 |
+
"proposal_oracle_success": 0.0,
|
| 1577 |
+
"proposal_oracle_utility": 0.11105132102966309,
|
| 1578 |
+
"selected_candidate_index": 2.0,
|
| 1579 |
+
"selected_success": 0.0,
|
| 1580 |
+
"selected_success_gain_over_base": 0.0,
|
| 1581 |
+
"selected_utility": 0.05225050449371338,
|
| 1582 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1583 |
+
"selector_regret": 0.05880081653594971,
|
| 1584 |
+
"success_selector_gap": 0.0,
|
| 1585 |
+
"success_support_gap": 1.0,
|
| 1586 |
+
"support_gap": 1.888948678970337,
|
| 1587 |
+
"tau": 0.34408156791985406
|
| 1588 |
+
},
|
| 1589 |
+
"211245842/train0": {
|
| 1590 |
+
"base_success": 0.0,
|
| 1591 |
+
"base_utility": 0.19090841710567474,
|
| 1592 |
+
"coverage": 1.0,
|
| 1593 |
+
"execute_generated": 1.0,
|
| 1594 |
+
"fallback_rate": 0.0,
|
| 1595 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1596 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1597 |
+
"outcome_ptr": 1.0,
|
| 1598 |
+
"predicted_margin": 0.3785855718496198,
|
| 1599 |
+
"proposal_oracle_success": 1.0,
|
| 1600 |
+
"proposal_oracle_utility": 2.0,
|
| 1601 |
+
"selected_candidate_index": 1.0,
|
| 1602 |
+
"selected_success": 0.0,
|
| 1603 |
+
"selected_success_gain_over_base": 0.0,
|
| 1604 |
+
"selected_utility": 0.12738418579101562,
|
| 1605 |
+
"selected_utility_gain_over_base": -0.06352423131465912,
|
| 1606 |
+
"selector_regret": 1.8726158142089844,
|
| 1607 |
+
"success_selector_gap": 1.0,
|
| 1608 |
+
"success_support_gap": 0.0,
|
| 1609 |
+
"support_gap": 0.0,
|
| 1610 |
+
"tau": 0.34408156791985406
|
| 1611 |
+
},
|
| 1612 |
+
"211245842/train1": {
|
| 1613 |
+
"base_success": 0.0,
|
| 1614 |
+
"base_utility": 0.19090841710567474,
|
| 1615 |
+
"coverage": 0.0,
|
| 1616 |
+
"execute_generated": 0.0,
|
| 1617 |
+
"fallback_rate": 1.0,
|
| 1618 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1619 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1620 |
+
"outcome_ptr": 1.0,
|
| 1621 |
+
"predicted_margin": 0.15046609148838602,
|
| 1622 |
+
"proposal_oracle_success": 0.0,
|
| 1623 |
+
"proposal_oracle_utility": 0.21295717358589172,
|
| 1624 |
+
"selected_candidate_index": 2.0,
|
| 1625 |
+
"selected_success": 0.0,
|
| 1626 |
+
"selected_success_gain_over_base": 0.0,
|
| 1627 |
+
"selected_utility": 0.19090841710567474,
|
| 1628 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1629 |
+
"selector_regret": 0.02204875648021698,
|
| 1630 |
+
"success_selector_gap": 0.0,
|
| 1631 |
+
"success_support_gap": 1.0,
|
| 1632 |
+
"support_gap": 1.7870428264141083,
|
| 1633 |
+
"tau": 0.34408156791985406
|
| 1634 |
+
},
|
| 1635 |
+
"211245842/train2": {
|
| 1636 |
+
"base_success": 0.0,
|
| 1637 |
+
"base_utility": 0.19090841710567474,
|
| 1638 |
+
"coverage": 0.0,
|
| 1639 |
+
"execute_generated": 0.0,
|
| 1640 |
+
"fallback_rate": 1.0,
|
| 1641 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1642 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1643 |
+
"outcome_ptr": 1.0,
|
| 1644 |
+
"predicted_margin": 0.16061195744478388,
|
| 1645 |
+
"proposal_oracle_success": 0.0,
|
| 1646 |
+
"proposal_oracle_utility": 0.21523693203926086,
|
| 1647 |
+
"selected_candidate_index": 4.0,
|
| 1648 |
+
"selected_success": 0.0,
|
| 1649 |
+
"selected_success_gain_over_base": 0.0,
|
| 1650 |
+
"selected_utility": 0.19090841710567474,
|
| 1651 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1652 |
+
"selector_regret": 0.02432851493358612,
|
| 1653 |
+
"success_selector_gap": 0.0,
|
| 1654 |
+
"success_support_gap": 1.0,
|
| 1655 |
+
"support_gap": 1.7847630679607391,
|
| 1656 |
+
"tau": 0.34408156791985406
|
| 1657 |
+
},
|
| 1658 |
+
"278008524/train0": {
|
| 1659 |
+
"base_success": 0.0,
|
| 1660 |
+
"base_utility": 0.042734989896416664,
|
| 1661 |
+
"coverage": 0.0,
|
| 1662 |
+
"execute_generated": 0.0,
|
| 1663 |
+
"fallback_rate": 1.0,
|
| 1664 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1665 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1666 |
+
"outcome_ptr": 1.0,
|
| 1667 |
+
"predicted_margin": 0.14581513472810403,
|
| 1668 |
+
"proposal_oracle_success": 0.5,
|
| 1669 |
+
"proposal_oracle_utility": 1.0287093725055456,
|
| 1670 |
+
"selected_candidate_index": 6.0,
|
| 1671 |
+
"selected_success": 0.0,
|
| 1672 |
+
"selected_success_gain_over_base": 0.0,
|
| 1673 |
+
"selected_utility": 0.042734989896416664,
|
| 1674 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1675 |
+
"selector_regret": 0.985974382609129,
|
| 1676 |
+
"success_selector_gap": 0.5,
|
| 1677 |
+
"success_support_gap": 0.0,
|
| 1678 |
+
"support_gap": 0.08519926853477955,
|
| 1679 |
+
"tau": 0.34408156791985406
|
| 1680 |
+
},
|
| 1681 |
+
"278008524/train1": {
|
| 1682 |
+
"base_success": 0.0,
|
| 1683 |
+
"base_utility": 0.042734989896416664,
|
| 1684 |
+
"coverage": 0.0,
|
| 1685 |
+
"execute_generated": 0.0,
|
| 1686 |
+
"fallback_rate": 1.0,
|
| 1687 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1688 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1689 |
+
"outcome_ptr": 1.0,
|
| 1690 |
+
"predicted_margin": 0.12964633215572155,
|
| 1691 |
+
"proposal_oracle_success": 0.5,
|
| 1692 |
+
"proposal_oracle_utility": 1.0376745946705341,
|
| 1693 |
+
"selected_candidate_index": 4.0,
|
| 1694 |
+
"selected_success": 0.0,
|
| 1695 |
+
"selected_success_gain_over_base": 0.0,
|
| 1696 |
+
"selected_utility": 0.042734989896416664,
|
| 1697 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1698 |
+
"selector_regret": 0.9949396047741175,
|
| 1699 |
+
"success_selector_gap": 0.5,
|
| 1700 |
+
"success_support_gap": 0.0,
|
| 1701 |
+
"support_gap": 0.07623404636979103,
|
| 1702 |
+
"tau": 0.34408156791985406
|
| 1703 |
+
},
|
| 1704 |
+
"278008524/train2": {
|
| 1705 |
+
"base_success": 0.0,
|
| 1706 |
+
"base_utility": 0.042734989896416664,
|
| 1707 |
+
"coverage": 0.0,
|
| 1708 |
+
"execute_generated": 0.0,
|
| 1709 |
+
"fallback_rate": 1.0,
|
| 1710 |
+
"hidden_chart_oracle_success": 0.5,
|
| 1711 |
+
"hidden_chart_oracle_utility": 1.1139086410403252,
|
| 1712 |
+
"outcome_ptr": 1.0,
|
| 1713 |
+
"predicted_margin": 0.11421197996697016,
|
| 1714 |
+
"proposal_oracle_success": 0.5,
|
| 1715 |
+
"proposal_oracle_utility": 1.1359489113092422,
|
| 1716 |
+
"selected_candidate_index": 1.0,
|
| 1717 |
+
"selected_success": 0.0,
|
| 1718 |
+
"selected_success_gain_over_base": 0.0,
|
| 1719 |
+
"selected_utility": 0.042734989896416664,
|
| 1720 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1721 |
+
"selector_regret": 1.0932139214128256,
|
| 1722 |
+
"success_selector_gap": 0.5,
|
| 1723 |
+
"success_support_gap": 0.0,
|
| 1724 |
+
"support_gap": 0.0,
|
| 1725 |
+
"tau": 0.34408156791985406
|
| 1726 |
+
},
|
| 1727 |
+
"307068879/train0": {
|
| 1728 |
+
"base_success": 0.0,
|
| 1729 |
+
"base_utility": 0.6000905632972717,
|
| 1730 |
+
"coverage": 0.0,
|
| 1731 |
+
"execute_generated": 0.0,
|
| 1732 |
+
"fallback_rate": 1.0,
|
| 1733 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1734 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1735 |
+
"outcome_ptr": 0.0,
|
| 1736 |
+
"predicted_margin": 0.1887491123406104,
|
| 1737 |
+
"proposal_oracle_success": 0.0,
|
| 1738 |
+
"proposal_oracle_utility": 0.2115575522184372,
|
| 1739 |
+
"selected_candidate_index": 0.0,
|
| 1740 |
+
"selected_success": 0.0,
|
| 1741 |
+
"selected_success_gain_over_base": 0.0,
|
| 1742 |
+
"selected_utility": 0.6000905632972717,
|
| 1743 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1744 |
+
"selector_regret": 0.0,
|
| 1745 |
+
"success_selector_gap": 0.0,
|
| 1746 |
+
"success_support_gap": 1.0,
|
| 1747 |
+
"support_gap": 1.7884424477815628,
|
| 1748 |
+
"tau": 0.34408156791985406
|
| 1749 |
+
},
|
| 1750 |
+
"307068879/train1": {
|
| 1751 |
+
"base_success": 0.0,
|
| 1752 |
+
"base_utility": 0.6000905632972717,
|
| 1753 |
+
"coverage": 0.0,
|
| 1754 |
+
"execute_generated": 0.0,
|
| 1755 |
+
"fallback_rate": 1.0,
|
| 1756 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1757 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1758 |
+
"outcome_ptr": 0.0,
|
| 1759 |
+
"predicted_margin": 0.1074108711810591,
|
| 1760 |
+
"proposal_oracle_success": 0.0,
|
| 1761 |
+
"proposal_oracle_utility": 0.5876073241233826,
|
| 1762 |
+
"selected_candidate_index": 1.0,
|
| 1763 |
+
"selected_success": 0.0,
|
| 1764 |
+
"selected_success_gain_over_base": 0.0,
|
| 1765 |
+
"selected_utility": 0.6000905632972717,
|
| 1766 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1767 |
+
"selector_regret": 0.0,
|
| 1768 |
+
"success_selector_gap": 0.0,
|
| 1769 |
+
"success_support_gap": 1.0,
|
| 1770 |
+
"support_gap": 1.4123926758766174,
|
| 1771 |
+
"tau": 0.34408156791985406
|
| 1772 |
+
},
|
| 1773 |
+
"307068879/train2": {
|
| 1774 |
+
"base_success": 0.0,
|
| 1775 |
+
"base_utility": 0.6000905632972717,
|
| 1776 |
+
"coverage": 0.0,
|
| 1777 |
+
"execute_generated": 0.0,
|
| 1778 |
+
"fallback_rate": 1.0,
|
| 1779 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1780 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1781 |
+
"outcome_ptr": 0.0,
|
| 1782 |
+
"predicted_margin": 0.16243232875050095,
|
| 1783 |
+
"proposal_oracle_success": 0.0,
|
| 1784 |
+
"proposal_oracle_utility": 0.22727864980697632,
|
| 1785 |
+
"selected_candidate_index": 1.0,
|
| 1786 |
+
"selected_success": 0.0,
|
| 1787 |
+
"selected_success_gain_over_base": 0.0,
|
| 1788 |
+
"selected_utility": 0.6000905632972717,
|
| 1789 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1790 |
+
"selector_regret": 0.0,
|
| 1791 |
+
"success_selector_gap": 0.0,
|
| 1792 |
+
"success_support_gap": 1.0,
|
| 1793 |
+
"support_gap": 1.7727213501930237,
|
| 1794 |
+
"tau": 0.34408156791985406
|
| 1795 |
+
},
|
| 1796 |
+
"412102563/train0": {
|
| 1797 |
+
"base_success": 1.0,
|
| 1798 |
+
"base_utility": 2.0,
|
| 1799 |
+
"coverage": 1.0,
|
| 1800 |
+
"execute_generated": 1.0,
|
| 1801 |
+
"fallback_rate": 0.0,
|
| 1802 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1803 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1804 |
+
"outcome_ptr": 0.0,
|
| 1805 |
+
"predicted_margin": 0.7010170953685468,
|
| 1806 |
+
"proposal_oracle_success": 1.0,
|
| 1807 |
+
"proposal_oracle_utility": 2.0,
|
| 1808 |
+
"selected_candidate_index": 4.0,
|
| 1809 |
+
"selected_success": 1.0,
|
| 1810 |
+
"selected_success_gain_over_base": 0.0,
|
| 1811 |
+
"selected_utility": 2.0,
|
| 1812 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1813 |
+
"selector_regret": 0.0,
|
| 1814 |
+
"success_selector_gap": 0.0,
|
| 1815 |
+
"success_support_gap": 0.0,
|
| 1816 |
+
"support_gap": 0.0,
|
| 1817 |
+
"tau": 0.34408156791985406
|
| 1818 |
+
},
|
| 1819 |
+
"412102563/train1": {
|
| 1820 |
+
"base_success": 1.0,
|
| 1821 |
+
"base_utility": 2.0,
|
| 1822 |
+
"coverage": 1.0,
|
| 1823 |
+
"execute_generated": 1.0,
|
| 1824 |
+
"fallback_rate": 0.0,
|
| 1825 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1826 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1827 |
+
"outcome_ptr": 0.0,
|
| 1828 |
+
"predicted_margin": 0.5698137543063153,
|
| 1829 |
+
"proposal_oracle_success": 1.0,
|
| 1830 |
+
"proposal_oracle_utility": 2.0,
|
| 1831 |
+
"selected_candidate_index": 4.0,
|
| 1832 |
+
"selected_success": 1.0,
|
| 1833 |
+
"selected_success_gain_over_base": 0.0,
|
| 1834 |
+
"selected_utility": 2.0,
|
| 1835 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1836 |
+
"selector_regret": 0.0,
|
| 1837 |
+
"success_selector_gap": 0.0,
|
| 1838 |
+
"success_support_gap": 0.0,
|
| 1839 |
+
"support_gap": 0.0,
|
| 1840 |
+
"tau": 0.34408156791985406
|
| 1841 |
+
},
|
| 1842 |
+
"412102563/train2": {
|
| 1843 |
+
"base_success": 1.0,
|
| 1844 |
+
"base_utility": 2.0,
|
| 1845 |
+
"coverage": 1.0,
|
| 1846 |
+
"execute_generated": 1.0,
|
| 1847 |
+
"fallback_rate": 0.0,
|
| 1848 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1849 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1850 |
+
"outcome_ptr": 0.0,
|
| 1851 |
+
"predicted_margin": 0.38545147035771476,
|
| 1852 |
+
"proposal_oracle_success": 1.0,
|
| 1853 |
+
"proposal_oracle_utility": 2.0,
|
| 1854 |
+
"selected_candidate_index": 7.0,
|
| 1855 |
+
"selected_success": 0.0,
|
| 1856 |
+
"selected_success_gain_over_base": -1.0,
|
| 1857 |
+
"selected_utility": 0.8126504421234131,
|
| 1858 |
+
"selected_utility_gain_over_base": -1.187349557876587,
|
| 1859 |
+
"selector_regret": 1.187349557876587,
|
| 1860 |
+
"success_selector_gap": 1.0,
|
| 1861 |
+
"success_support_gap": 0.0,
|
| 1862 |
+
"support_gap": 0.0,
|
| 1863 |
+
"tau": 0.34408156791985406
|
| 1864 |
+
},
|
| 1865 |
+
"440577711/train0": {
|
| 1866 |
+
"base_success": 0.0,
|
| 1867 |
+
"base_utility": 0.036152780055999756,
|
| 1868 |
+
"coverage": 1.0,
|
| 1869 |
+
"execute_generated": 1.0,
|
| 1870 |
+
"fallback_rate": 0.0,
|
| 1871 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1872 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1873 |
+
"outcome_ptr": 1.0,
|
| 1874 |
+
"predicted_margin": 0.7826205556130074,
|
| 1875 |
+
"proposal_oracle_success": 1.0,
|
| 1876 |
+
"proposal_oracle_utility": 2.0,
|
| 1877 |
+
"selected_candidate_index": 1.0,
|
| 1878 |
+
"selected_success": 1.0,
|
| 1879 |
+
"selected_success_gain_over_base": 1.0,
|
| 1880 |
+
"selected_utility": 2.0,
|
| 1881 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1882 |
+
"selector_regret": 0.0,
|
| 1883 |
+
"success_selector_gap": 0.0,
|
| 1884 |
+
"success_support_gap": 0.0,
|
| 1885 |
+
"support_gap": 0.0,
|
| 1886 |
+
"tau": 0.34408156791985406
|
| 1887 |
+
},
|
| 1888 |
+
"440577711/train1": {
|
| 1889 |
+
"base_success": 0.0,
|
| 1890 |
+
"base_utility": 0.036152780055999756,
|
| 1891 |
+
"coverage": 1.0,
|
| 1892 |
+
"execute_generated": 1.0,
|
| 1893 |
+
"fallback_rate": 0.0,
|
| 1894 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1895 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1896 |
+
"outcome_ptr": 1.0,
|
| 1897 |
+
"predicted_margin": 0.7916612246735112,
|
| 1898 |
+
"proposal_oracle_success": 1.0,
|
| 1899 |
+
"proposal_oracle_utility": 2.0,
|
| 1900 |
+
"selected_candidate_index": 3.0,
|
| 1901 |
+
"selected_success": 1.0,
|
| 1902 |
+
"selected_success_gain_over_base": 1.0,
|
| 1903 |
+
"selected_utility": 2.0,
|
| 1904 |
+
"selected_utility_gain_over_base": 1.9638472199440002,
|
| 1905 |
+
"selector_regret": 0.0,
|
| 1906 |
+
"success_selector_gap": 0.0,
|
| 1907 |
+
"success_support_gap": 0.0,
|
| 1908 |
+
"support_gap": 0.0,
|
| 1909 |
+
"tau": 0.34408156791985406
|
| 1910 |
+
},
|
| 1911 |
+
"440577711/train2": {
|
| 1912 |
+
"base_success": 0.0,
|
| 1913 |
+
"base_utility": 0.036152780055999756,
|
| 1914 |
+
"coverage": 1.0,
|
| 1915 |
+
"execute_generated": 1.0,
|
| 1916 |
+
"fallback_rate": 0.0,
|
| 1917 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1918 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1919 |
+
"outcome_ptr": 1.0,
|
| 1920 |
+
"predicted_margin": 0.8330203790971261,
|
| 1921 |
+
"proposal_oracle_success": 1.0,
|
| 1922 |
+
"proposal_oracle_utility": 2.0,
|
| 1923 |
+
"selected_candidate_index": 4.0,
|
| 1924 |
+
"selected_success": 0.0,
|
| 1925 |
+
"selected_success_gain_over_base": 0.0,
|
| 1926 |
+
"selected_utility": 0.12224134802818298,
|
| 1927 |
+
"selected_utility_gain_over_base": 0.08608856797218323,
|
| 1928 |
+
"selector_regret": 1.877758651971817,
|
| 1929 |
+
"success_selector_gap": 1.0,
|
| 1930 |
+
"success_support_gap": 0.0,
|
| 1931 |
+
"support_gap": 0.0,
|
| 1932 |
+
"tau": 0.34408156791985406
|
| 1933 |
+
},
|
| 1934 |
+
"441046872/train0": {
|
| 1935 |
+
"base_success": 0.0,
|
| 1936 |
+
"base_utility": 0.6999551653862,
|
| 1937 |
+
"coverage": 0.0,
|
| 1938 |
+
"execute_generated": 0.0,
|
| 1939 |
+
"fallback_rate": 1.0,
|
| 1940 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1941 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1942 |
+
"outcome_ptr": 0.0,
|
| 1943 |
+
"predicted_margin": 0.1369652832639738,
|
| 1944 |
+
"proposal_oracle_success": 0.0,
|
| 1945 |
+
"proposal_oracle_utility": 0.5148025155067444,
|
| 1946 |
+
"selected_candidate_index": 1.0,
|
| 1947 |
+
"selected_success": 0.0,
|
| 1948 |
+
"selected_success_gain_over_base": 0.0,
|
| 1949 |
+
"selected_utility": 0.6999551653862,
|
| 1950 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1951 |
+
"selector_regret": 0.0,
|
| 1952 |
+
"success_selector_gap": 0.0,
|
| 1953 |
+
"success_support_gap": 1.0,
|
| 1954 |
+
"support_gap": 1.4851974844932556,
|
| 1955 |
+
"tau": 0.34408156791985406
|
| 1956 |
+
},
|
| 1957 |
+
"441046872/train1": {
|
| 1958 |
+
"base_success": 0.0,
|
| 1959 |
+
"base_utility": 0.6999551653862,
|
| 1960 |
+
"coverage": 0.0,
|
| 1961 |
+
"execute_generated": 0.0,
|
| 1962 |
+
"fallback_rate": 1.0,
|
| 1963 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1964 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1965 |
+
"outcome_ptr": 1.0,
|
| 1966 |
+
"predicted_margin": 0.1381008153886979,
|
| 1967 |
+
"proposal_oracle_success": 0.0,
|
| 1968 |
+
"proposal_oracle_utility": 0.7233588695526123,
|
| 1969 |
+
"selected_candidate_index": 0.0,
|
| 1970 |
+
"selected_success": 0.0,
|
| 1971 |
+
"selected_success_gain_over_base": 0.0,
|
| 1972 |
+
"selected_utility": 0.6999551653862,
|
| 1973 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1974 |
+
"selector_regret": 0.023403704166412354,
|
| 1975 |
+
"success_selector_gap": 0.0,
|
| 1976 |
+
"success_support_gap": 1.0,
|
| 1977 |
+
"support_gap": 1.2766411304473877,
|
| 1978 |
+
"tau": 0.34408156791985406
|
| 1979 |
+
},
|
| 1980 |
+
"441046872/train2": {
|
| 1981 |
+
"base_success": 0.0,
|
| 1982 |
+
"base_utility": 0.6999551653862,
|
| 1983 |
+
"coverage": 0.0,
|
| 1984 |
+
"execute_generated": 0.0,
|
| 1985 |
+
"fallback_rate": 1.0,
|
| 1986 |
+
"hidden_chart_oracle_success": 1.0,
|
| 1987 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 1988 |
+
"outcome_ptr": 1.0,
|
| 1989 |
+
"predicted_margin": 0.16102481521823614,
|
| 1990 |
+
"proposal_oracle_success": 0.0,
|
| 1991 |
+
"proposal_oracle_utility": 0.7130289077758789,
|
| 1992 |
+
"selected_candidate_index": 2.0,
|
| 1993 |
+
"selected_success": 0.0,
|
| 1994 |
+
"selected_success_gain_over_base": 0.0,
|
| 1995 |
+
"selected_utility": 0.6999551653862,
|
| 1996 |
+
"selected_utility_gain_over_base": 0.0,
|
| 1997 |
+
"selector_regret": 0.013073742389678955,
|
| 1998 |
+
"success_selector_gap": 0.0,
|
| 1999 |
+
"success_support_gap": 1.0,
|
| 2000 |
+
"support_gap": 1.286971092224121,
|
| 2001 |
+
"tau": 0.34408156791985406
|
| 2002 |
+
},
|
| 2003 |
+
"509430392/train0": {
|
| 2004 |
+
"base_success": 0.0,
|
| 2005 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2006 |
+
"coverage": 1.0,
|
| 2007 |
+
"execute_generated": 1.0,
|
| 2008 |
+
"fallback_rate": 0.0,
|
| 2009 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2010 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2011 |
+
"outcome_ptr": 1.0,
|
| 2012 |
+
"predicted_margin": 0.8694829408465863,
|
| 2013 |
+
"proposal_oracle_success": 1.0,
|
| 2014 |
+
"proposal_oracle_utility": 2.0,
|
| 2015 |
+
"selected_candidate_index": 4.0,
|
| 2016 |
+
"selected_success": 0.0,
|
| 2017 |
+
"selected_success_gain_over_base": 0.0,
|
| 2018 |
+
"selected_utility": 6.109476089477539e-07,
|
| 2019 |
+
"selected_utility_gain_over_base": 3.8743019104003906e-07,
|
| 2020 |
+
"selector_regret": 1.999999389052391,
|
| 2021 |
+
"success_selector_gap": 1.0,
|
| 2022 |
+
"success_support_gap": 0.0,
|
| 2023 |
+
"support_gap": 0.0,
|
| 2024 |
+
"tau": 0.34408156791985406
|
| 2025 |
+
},
|
| 2026 |
+
"509430392/train1": {
|
| 2027 |
+
"base_success": 0.0,
|
| 2028 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2029 |
+
"coverage": 1.0,
|
| 2030 |
+
"execute_generated": 1.0,
|
| 2031 |
+
"fallback_rate": 0.0,
|
| 2032 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2033 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2034 |
+
"outcome_ptr": 1.0,
|
| 2035 |
+
"predicted_margin": 0.8876110106518329,
|
| 2036 |
+
"proposal_oracle_success": 0.0,
|
| 2037 |
+
"proposal_oracle_utility": 6.164610385894775e-05,
|
| 2038 |
+
"selected_candidate_index": 2.0,
|
| 2039 |
+
"selected_success": 0.0,
|
| 2040 |
+
"selected_success_gain_over_base": 0.0,
|
| 2041 |
+
"selected_utility": 1.519918441772461e-06,
|
| 2042 |
+
"selected_utility_gain_over_base": 1.296401023864746e-06,
|
| 2043 |
+
"selector_regret": 6.012618541717529e-05,
|
| 2044 |
+
"success_selector_gap": 0.0,
|
| 2045 |
+
"success_support_gap": 1.0,
|
| 2046 |
+
"support_gap": 1.999938353896141,
|
| 2047 |
+
"tau": 0.34408156791985406
|
| 2048 |
+
},
|
| 2049 |
+
"509430392/train2": {
|
| 2050 |
+
"base_success": 0.0,
|
| 2051 |
+
"base_utility": 2.2351741790771484e-07,
|
| 2052 |
+
"coverage": 1.0,
|
| 2053 |
+
"execute_generated": 1.0,
|
| 2054 |
+
"fallback_rate": 0.0,
|
| 2055 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2056 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2057 |
+
"outcome_ptr": 1.0,
|
| 2058 |
+
"predicted_margin": 0.877751694992998,
|
| 2059 |
+
"proposal_oracle_success": 0.0,
|
| 2060 |
+
"proposal_oracle_utility": 5.424022674560547e-06,
|
| 2061 |
+
"selected_candidate_index": 0.0,
|
| 2062 |
+
"selected_success": 0.0,
|
| 2063 |
+
"selected_success_gain_over_base": 0.0,
|
| 2064 |
+
"selected_utility": 2.682209014892578e-07,
|
| 2065 |
+
"selected_utility_gain_over_base": 4.470348358154297e-08,
|
| 2066 |
+
"selector_regret": 5.155801773071289e-06,
|
| 2067 |
+
"success_selector_gap": 0.0,
|
| 2068 |
+
"success_support_gap": 1.0,
|
| 2069 |
+
"support_gap": 1.9999945759773254,
|
| 2070 |
+
"tau": 0.34408156791985406
|
| 2071 |
+
},
|
| 2072 |
+
"585904130/train0": {
|
| 2073 |
+
"base_success": 0.0,
|
| 2074 |
+
"base_utility": 0.18171554803848267,
|
| 2075 |
+
"coverage": 1.0,
|
| 2076 |
+
"execute_generated": 1.0,
|
| 2077 |
+
"fallback_rate": 0.0,
|
| 2078 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2079 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2080 |
+
"outcome_ptr": 1.0,
|
| 2081 |
+
"predicted_margin": 0.5615544380344981,
|
| 2082 |
+
"proposal_oracle_success": 1.0,
|
| 2083 |
+
"proposal_oracle_utility": 2.0,
|
| 2084 |
+
"selected_candidate_index": 2.0,
|
| 2085 |
+
"selected_success": 1.0,
|
| 2086 |
+
"selected_success_gain_over_base": 1.0,
|
| 2087 |
+
"selected_utility": 2.0,
|
| 2088 |
+
"selected_utility_gain_over_base": 1.8182844519615173,
|
| 2089 |
+
"selector_regret": 0.0,
|
| 2090 |
+
"success_selector_gap": 0.0,
|
| 2091 |
+
"success_support_gap": 0.0,
|
| 2092 |
+
"support_gap": 0.0,
|
| 2093 |
+
"tau": 0.34408156791985406
|
| 2094 |
+
},
|
| 2095 |
+
"585904130/train1": {
|
| 2096 |
+
"base_success": 0.0,
|
| 2097 |
+
"base_utility": 0.18171554803848267,
|
| 2098 |
+
"coverage": 1.0,
|
| 2099 |
+
"execute_generated": 1.0,
|
| 2100 |
+
"fallback_rate": 0.0,
|
| 2101 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2102 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2103 |
+
"outcome_ptr": 1.0,
|
| 2104 |
+
"predicted_margin": 0.6514445232612912,
|
| 2105 |
+
"proposal_oracle_success": 1.0,
|
| 2106 |
+
"proposal_oracle_utility": 2.0,
|
| 2107 |
+
"selected_candidate_index": 4.0,
|
| 2108 |
+
"selected_success": 1.0,
|
| 2109 |
+
"selected_success_gain_over_base": 1.0,
|
| 2110 |
+
"selected_utility": 2.0,
|
| 2111 |
+
"selected_utility_gain_over_base": 1.8182844519615173,
|
| 2112 |
+
"selector_regret": 0.0,
|
| 2113 |
+
"success_selector_gap": 0.0,
|
| 2114 |
+
"success_support_gap": 0.0,
|
| 2115 |
+
"support_gap": 0.0,
|
| 2116 |
+
"tau": 0.34408156791985406
|
| 2117 |
+
},
|
| 2118 |
+
"585904130/train2": {
|
| 2119 |
+
"base_success": 0.0,
|
| 2120 |
+
"base_utility": 0.18171554803848267,
|
| 2121 |
+
"coverage": 1.0,
|
| 2122 |
+
"execute_generated": 1.0,
|
| 2123 |
+
"fallback_rate": 0.0,
|
| 2124 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2125 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2126 |
+
"outcome_ptr": 1.0,
|
| 2127 |
+
"predicted_margin": 0.6191661897193406,
|
| 2128 |
+
"proposal_oracle_success": 1.0,
|
| 2129 |
+
"proposal_oracle_utility": 2.0,
|
| 2130 |
+
"selected_candidate_index": 3.0,
|
| 2131 |
+
"selected_success": 1.0,
|
| 2132 |
+
"selected_success_gain_over_base": 1.0,
|
| 2133 |
+
"selected_utility": 2.0,
|
| 2134 |
+
"selected_utility_gain_over_base": 1.8182844519615173,
|
| 2135 |
+
"selector_regret": 0.0,
|
| 2136 |
+
"success_selector_gap": 0.0,
|
| 2137 |
+
"success_support_gap": 0.0,
|
| 2138 |
+
"support_gap": 0.0,
|
| 2139 |
+
"tau": 0.34408156791985406
|
| 2140 |
+
},
|
| 2141 |
+
"608016290/train0": {
|
| 2142 |
+
"base_success": 0.0,
|
| 2143 |
+
"base_utility": 0.725701630115509,
|
| 2144 |
+
"coverage": 1.0,
|
| 2145 |
+
"execute_generated": 1.0,
|
| 2146 |
+
"fallback_rate": 0.0,
|
| 2147 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2148 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2149 |
+
"outcome_ptr": 1.0,
|
| 2150 |
+
"predicted_margin": 0.6553002828082154,
|
| 2151 |
+
"proposal_oracle_success": 1.0,
|
| 2152 |
+
"proposal_oracle_utility": 2.0,
|
| 2153 |
+
"selected_candidate_index": 5.0,
|
| 2154 |
+
"selected_success": 1.0,
|
| 2155 |
+
"selected_success_gain_over_base": 1.0,
|
| 2156 |
+
"selected_utility": 2.0,
|
| 2157 |
+
"selected_utility_gain_over_base": 1.274298369884491,
|
| 2158 |
+
"selector_regret": 0.0,
|
| 2159 |
+
"success_selector_gap": 0.0,
|
| 2160 |
+
"success_support_gap": 0.0,
|
| 2161 |
+
"support_gap": 0.0,
|
| 2162 |
+
"tau": 0.34408156791985406
|
| 2163 |
+
},
|
| 2164 |
+
"608016290/train1": {
|
| 2165 |
+
"base_success": 0.0,
|
| 2166 |
+
"base_utility": 0.725701630115509,
|
| 2167 |
+
"coverage": 1.0,
|
| 2168 |
+
"execute_generated": 1.0,
|
| 2169 |
+
"fallback_rate": 0.0,
|
| 2170 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2171 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2172 |
+
"outcome_ptr": 1.0,
|
| 2173 |
+
"predicted_margin": 0.5900770630713733,
|
| 2174 |
+
"proposal_oracle_success": 1.0,
|
| 2175 |
+
"proposal_oracle_utility": 2.0,
|
| 2176 |
+
"selected_candidate_index": 1.0,
|
| 2177 |
+
"selected_success": 1.0,
|
| 2178 |
+
"selected_success_gain_over_base": 1.0,
|
| 2179 |
+
"selected_utility": 2.0,
|
| 2180 |
+
"selected_utility_gain_over_base": 1.274298369884491,
|
| 2181 |
+
"selector_regret": 0.0,
|
| 2182 |
+
"success_selector_gap": 0.0,
|
| 2183 |
+
"success_support_gap": 0.0,
|
| 2184 |
+
"support_gap": 0.0,
|
| 2185 |
+
"tau": 0.34408156791985406
|
| 2186 |
+
},
|
| 2187 |
+
"608016290/train2": {
|
| 2188 |
+
"base_success": 0.0,
|
| 2189 |
+
"base_utility": 0.725701630115509,
|
| 2190 |
+
"coverage": 0.0,
|
| 2191 |
+
"execute_generated": 0.0,
|
| 2192 |
+
"fallback_rate": 1.0,
|
| 2193 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2194 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2195 |
+
"outcome_ptr": 0.0,
|
| 2196 |
+
"predicted_margin": 0.3062491108599271,
|
| 2197 |
+
"proposal_oracle_success": 0.0,
|
| 2198 |
+
"proposal_oracle_utility": 0.6825780272483826,
|
| 2199 |
+
"selected_candidate_index": 3.0,
|
| 2200 |
+
"selected_success": 0.0,
|
| 2201 |
+
"selected_success_gain_over_base": 0.0,
|
| 2202 |
+
"selected_utility": 0.725701630115509,
|
| 2203 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2204 |
+
"selector_regret": 0.0,
|
| 2205 |
+
"success_selector_gap": 0.0,
|
| 2206 |
+
"success_support_gap": 1.0,
|
| 2207 |
+
"support_gap": 1.3174219727516174,
|
| 2208 |
+
"tau": 0.34408156791985406
|
| 2209 |
+
},
|
| 2210 |
+
"626486813/train0": {
|
| 2211 |
+
"base_success": 0.0,
|
| 2212 |
+
"base_utility": 0.00509834272088483,
|
| 2213 |
+
"coverage": 0.0,
|
| 2214 |
+
"execute_generated": 0.0,
|
| 2215 |
+
"fallback_rate": 1.0,
|
| 2216 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2217 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2218 |
+
"outcome_ptr": 1.0,
|
| 2219 |
+
"predicted_margin": 0.12362553612050224,
|
| 2220 |
+
"proposal_oracle_success": 0.0,
|
| 2221 |
+
"proposal_oracle_utility": 0.043898362666368484,
|
| 2222 |
+
"selected_candidate_index": 1.0,
|
| 2223 |
+
"selected_success": 0.0,
|
| 2224 |
+
"selected_success_gain_over_base": 0.0,
|
| 2225 |
+
"selected_utility": 0.00509834272088483,
|
| 2226 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2227 |
+
"selector_regret": 0.038800019945483655,
|
| 2228 |
+
"success_selector_gap": 0.0,
|
| 2229 |
+
"success_support_gap": 0.0,
|
| 2230 |
+
"support_gap": 0.12241578102111816,
|
| 2231 |
+
"tau": 0.34408156791985406
|
| 2232 |
+
},
|
| 2233 |
+
"626486813/train1": {
|
| 2234 |
+
"base_success": 0.0,
|
| 2235 |
+
"base_utility": 0.00509834272088483,
|
| 2236 |
+
"coverage": 1.0,
|
| 2237 |
+
"execute_generated": 1.0,
|
| 2238 |
+
"fallback_rate": 0.0,
|
| 2239 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2240 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2241 |
+
"outcome_ptr": 1.0,
|
| 2242 |
+
"predicted_margin": 0.4708417796239817,
|
| 2243 |
+
"proposal_oracle_success": 0.0,
|
| 2244 |
+
"proposal_oracle_utility": 0.030555277597159147,
|
| 2245 |
+
"selected_candidate_index": 5.5,
|
| 2246 |
+
"selected_success": 0.0,
|
| 2247 |
+
"selected_success_gain_over_base": 0.0,
|
| 2248 |
+
"selected_utility": 0.006621529464609921,
|
| 2249 |
+
"selected_utility_gain_over_base": 0.0015231867437250912,
|
| 2250 |
+
"selector_regret": 0.023933748132549226,
|
| 2251 |
+
"success_selector_gap": 0.0,
|
| 2252 |
+
"success_support_gap": 0.0,
|
| 2253 |
+
"support_gap": 0.13502710359171033,
|
| 2254 |
+
"tau": 0.34408156791985406
|
| 2255 |
+
},
|
| 2256 |
+
"626486813/train2": {
|
| 2257 |
+
"base_success": 0.0,
|
| 2258 |
+
"base_utility": 0.00509834272088483,
|
| 2259 |
+
"coverage": 0.0,
|
| 2260 |
+
"execute_generated": 0.0,
|
| 2261 |
+
"fallback_rate": 1.0,
|
| 2262 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2263 |
+
"hidden_chart_oracle_utility": 0.16558238118886948,
|
| 2264 |
+
"outcome_ptr": 1.0,
|
| 2265 |
+
"predicted_margin": 0.039552385944957046,
|
| 2266 |
+
"proposal_oracle_success": 0.0,
|
| 2267 |
+
"proposal_oracle_utility": 0.03856666944921017,
|
| 2268 |
+
"selected_candidate_index": 0.5,
|
| 2269 |
+
"selected_success": 0.0,
|
| 2270 |
+
"selected_success_gain_over_base": 0.0,
|
| 2271 |
+
"selected_utility": 0.00509834272088483,
|
| 2272 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2273 |
+
"selector_regret": 0.03346832672832534,
|
| 2274 |
+
"success_selector_gap": 0.0,
|
| 2275 |
+
"success_support_gap": 0.0,
|
| 2276 |
+
"support_gap": 0.1270157117396593,
|
| 2277 |
+
"tau": 0.34408156791985406
|
| 2278 |
+
},
|
| 2279 |
+
"636680137/train0": {
|
| 2280 |
+
"base_success": 0.0,
|
| 2281 |
+
"base_utility": 0.08313504606485367,
|
| 2282 |
+
"coverage": 0.0,
|
| 2283 |
+
"execute_generated": 0.0,
|
| 2284 |
+
"fallback_rate": 1.0,
|
| 2285 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2286 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2287 |
+
"outcome_ptr": 1.0,
|
| 2288 |
+
"predicted_margin": 0.12068125693439798,
|
| 2289 |
+
"proposal_oracle_success": 0.0,
|
| 2290 |
+
"proposal_oracle_utility": 0.08826130628585815,
|
| 2291 |
+
"selected_candidate_index": 5.0,
|
| 2292 |
+
"selected_success": 0.0,
|
| 2293 |
+
"selected_success_gain_over_base": 0.0,
|
| 2294 |
+
"selected_utility": 0.08313504606485367,
|
| 2295 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2296 |
+
"selector_regret": 0.005126260221004486,
|
| 2297 |
+
"success_selector_gap": 0.0,
|
| 2298 |
+
"success_support_gap": 0.0,
|
| 2299 |
+
"support_gap": 0.0823030173778534,
|
| 2300 |
+
"tau": 0.34408156791985406
|
| 2301 |
+
},
|
| 2302 |
+
"636680137/train1": {
|
| 2303 |
+
"base_success": 0.0,
|
| 2304 |
+
"base_utility": 0.08313504606485367,
|
| 2305 |
+
"coverage": 0.0,
|
| 2306 |
+
"execute_generated": 0.0,
|
| 2307 |
+
"fallback_rate": 1.0,
|
| 2308 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2309 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2310 |
+
"outcome_ptr": 0.0,
|
| 2311 |
+
"predicted_margin": 0.21234411275170456,
|
| 2312 |
+
"proposal_oracle_success": 0.0,
|
| 2313 |
+
"proposal_oracle_utility": 0.06741118431091309,
|
| 2314 |
+
"selected_candidate_index": 1.0,
|
| 2315 |
+
"selected_success": 0.0,
|
| 2316 |
+
"selected_success_gain_over_base": 0.0,
|
| 2317 |
+
"selected_utility": 0.08313504606485367,
|
| 2318 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2319 |
+
"selector_regret": 0.0,
|
| 2320 |
+
"success_selector_gap": 0.0,
|
| 2321 |
+
"success_support_gap": 0.0,
|
| 2322 |
+
"support_gap": 0.10315313935279846,
|
| 2323 |
+
"tau": 0.34408156791985406
|
| 2324 |
+
},
|
| 2325 |
+
"636680137/train2": {
|
| 2326 |
+
"base_success": 0.0,
|
| 2327 |
+
"base_utility": 0.08313504606485367,
|
| 2328 |
+
"coverage": 0.0,
|
| 2329 |
+
"execute_generated": 0.0,
|
| 2330 |
+
"fallback_rate": 1.0,
|
| 2331 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2332 |
+
"hidden_chart_oracle_utility": 0.17056432366371155,
|
| 2333 |
+
"outcome_ptr": 0.0,
|
| 2334 |
+
"predicted_margin": 0.13211103402371466,
|
| 2335 |
+
"proposal_oracle_success": 0.0,
|
| 2336 |
+
"proposal_oracle_utility": 0.0756516233086586,
|
| 2337 |
+
"selected_candidate_index": 7.0,
|
| 2338 |
+
"selected_success": 0.0,
|
| 2339 |
+
"selected_success_gain_over_base": 0.0,
|
| 2340 |
+
"selected_utility": 0.08313504606485367,
|
| 2341 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2342 |
+
"selector_regret": 0.0,
|
| 2343 |
+
"success_selector_gap": 0.0,
|
| 2344 |
+
"success_support_gap": 0.0,
|
| 2345 |
+
"support_gap": 0.09491270035505295,
|
| 2346 |
+
"tau": 0.34408156791985406
|
| 2347 |
+
},
|
| 2348 |
+
"655884605/train0": {
|
| 2349 |
+
"base_success": 0.0,
|
| 2350 |
+
"base_utility": 0.16300667822360992,
|
| 2351 |
+
"coverage": 0.0,
|
| 2352 |
+
"execute_generated": 0.0,
|
| 2353 |
+
"fallback_rate": 1.0,
|
| 2354 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2355 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2356 |
+
"outcome_ptr": 0.0,
|
| 2357 |
+
"predicted_margin": 0.21643525031550226,
|
| 2358 |
+
"proposal_oracle_success": 0.0,
|
| 2359 |
+
"proposal_oracle_utility": 0.13732868432998657,
|
| 2360 |
+
"selected_candidate_index": 7.0,
|
| 2361 |
+
"selected_success": 0.0,
|
| 2362 |
+
"selected_success_gain_over_base": 0.0,
|
| 2363 |
+
"selected_utility": 0.16300667822360992,
|
| 2364 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2365 |
+
"selector_regret": 0.0,
|
| 2366 |
+
"success_selector_gap": 0.0,
|
| 2367 |
+
"success_support_gap": 1.0,
|
| 2368 |
+
"support_gap": 1.8626713156700134,
|
| 2369 |
+
"tau": 0.34408156791985406
|
| 2370 |
+
},
|
| 2371 |
+
"655884605/train1": {
|
| 2372 |
+
"base_success": 0.0,
|
| 2373 |
+
"base_utility": 0.16300667822360992,
|
| 2374 |
+
"coverage": 0.0,
|
| 2375 |
+
"execute_generated": 0.0,
|
| 2376 |
+
"fallback_rate": 1.0,
|
| 2377 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2378 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2379 |
+
"outcome_ptr": 1.0,
|
| 2380 |
+
"predicted_margin": 0.2994868754670774,
|
| 2381 |
+
"proposal_oracle_success": 0.0,
|
| 2382 |
+
"proposal_oracle_utility": 0.1651531159877777,
|
| 2383 |
+
"selected_candidate_index": 3.0,
|
| 2384 |
+
"selected_success": 0.0,
|
| 2385 |
+
"selected_success_gain_over_base": 0.0,
|
| 2386 |
+
"selected_utility": 0.16300667822360992,
|
| 2387 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2388 |
+
"selector_regret": 0.0021464377641677856,
|
| 2389 |
+
"success_selector_gap": 0.0,
|
| 2390 |
+
"success_support_gap": 1.0,
|
| 2391 |
+
"support_gap": 1.8348468840122223,
|
| 2392 |
+
"tau": 0.34408156791985406
|
| 2393 |
+
},
|
| 2394 |
+
"655884605/train2": {
|
| 2395 |
+
"base_success": 0.0,
|
| 2396 |
+
"base_utility": 0.16300667822360992,
|
| 2397 |
+
"coverage": 0.0,
|
| 2398 |
+
"execute_generated": 0.0,
|
| 2399 |
+
"fallback_rate": 1.0,
|
| 2400 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2401 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2402 |
+
"outcome_ptr": 1.0,
|
| 2403 |
+
"predicted_margin": 0.24482913949185411,
|
| 2404 |
+
"proposal_oracle_success": 0.0,
|
| 2405 |
+
"proposal_oracle_utility": 0.21447330713272095,
|
| 2406 |
+
"selected_candidate_index": 3.0,
|
| 2407 |
+
"selected_success": 0.0,
|
| 2408 |
+
"selected_success_gain_over_base": 0.0,
|
| 2409 |
+
"selected_utility": 0.16300667822360992,
|
| 2410 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2411 |
+
"selector_regret": 0.05146662890911102,
|
| 2412 |
+
"success_selector_gap": 0.0,
|
| 2413 |
+
"success_support_gap": 1.0,
|
| 2414 |
+
"support_gap": 1.785526692867279,
|
| 2415 |
+
"tau": 0.34408156791985406
|
| 2416 |
+
},
|
| 2417 |
+
"672328262/train0": {
|
| 2418 |
+
"base_success": 1.0,
|
| 2419 |
+
"base_utility": 2.0,
|
| 2420 |
+
"coverage": 1.0,
|
| 2421 |
+
"execute_generated": 1.0,
|
| 2422 |
+
"fallback_rate": 0.0,
|
| 2423 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2424 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2425 |
+
"outcome_ptr": 0.0,
|
| 2426 |
+
"predicted_margin": 0.4623294557049326,
|
| 2427 |
+
"proposal_oracle_success": 1.0,
|
| 2428 |
+
"proposal_oracle_utility": 2.0,
|
| 2429 |
+
"selected_candidate_index": 0.0,
|
| 2430 |
+
"selected_success": 1.0,
|
| 2431 |
+
"selected_success_gain_over_base": 0.0,
|
| 2432 |
+
"selected_utility": 2.0,
|
| 2433 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2434 |
+
"selector_regret": 0.0,
|
| 2435 |
+
"success_selector_gap": 0.0,
|
| 2436 |
+
"success_support_gap": 0.0,
|
| 2437 |
+
"support_gap": 0.0,
|
| 2438 |
+
"tau": 0.34408156791985406
|
| 2439 |
+
},
|
| 2440 |
+
"672328262/train1": {
|
| 2441 |
+
"base_success": 1.0,
|
| 2442 |
+
"base_utility": 2.0,
|
| 2443 |
+
"coverage": 0.0,
|
| 2444 |
+
"execute_generated": 0.0,
|
| 2445 |
+
"fallback_rate": 1.0,
|
| 2446 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2447 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2448 |
+
"outcome_ptr": 0.0,
|
| 2449 |
+
"predicted_margin": 0.32509114906662,
|
| 2450 |
+
"proposal_oracle_success": 1.0,
|
| 2451 |
+
"proposal_oracle_utility": 2.0,
|
| 2452 |
+
"selected_candidate_index": 6.0,
|
| 2453 |
+
"selected_success": 1.0,
|
| 2454 |
+
"selected_success_gain_over_base": 0.0,
|
| 2455 |
+
"selected_utility": 2.0,
|
| 2456 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2457 |
+
"selector_regret": 0.0,
|
| 2458 |
+
"success_selector_gap": 0.0,
|
| 2459 |
+
"success_support_gap": 0.0,
|
| 2460 |
+
"support_gap": 0.0,
|
| 2461 |
+
"tau": 0.34408156791985406
|
| 2462 |
+
},
|
| 2463 |
+
"672328262/train2": {
|
| 2464 |
+
"base_success": 1.0,
|
| 2465 |
+
"base_utility": 2.0,
|
| 2466 |
+
"coverage": 1.0,
|
| 2467 |
+
"execute_generated": 1.0,
|
| 2468 |
+
"fallback_rate": 0.0,
|
| 2469 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2470 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2471 |
+
"outcome_ptr": 0.0,
|
| 2472 |
+
"predicted_margin": 0.4398883507596493,
|
| 2473 |
+
"proposal_oracle_success": 1.0,
|
| 2474 |
+
"proposal_oracle_utility": 2.0,
|
| 2475 |
+
"selected_candidate_index": 5.0,
|
| 2476 |
+
"selected_success": 1.0,
|
| 2477 |
+
"selected_success_gain_over_base": 0.0,
|
| 2478 |
+
"selected_utility": 2.0,
|
| 2479 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2480 |
+
"selector_regret": 0.0,
|
| 2481 |
+
"success_selector_gap": 0.0,
|
| 2482 |
+
"success_support_gap": 0.0,
|
| 2483 |
+
"support_gap": 0.0,
|
| 2484 |
+
"tau": 0.34408156791985406
|
| 2485 |
+
},
|
| 2486 |
+
"701667486/train0": {
|
| 2487 |
+
"base_success": 1.0,
|
| 2488 |
+
"base_utility": 2.0,
|
| 2489 |
+
"coverage": 1.0,
|
| 2490 |
+
"execute_generated": 1.0,
|
| 2491 |
+
"fallback_rate": 0.0,
|
| 2492 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2493 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2494 |
+
"outcome_ptr": 0.0,
|
| 2495 |
+
"predicted_margin": 0.6093046734206291,
|
| 2496 |
+
"proposal_oracle_success": 1.0,
|
| 2497 |
+
"proposal_oracle_utility": 2.0,
|
| 2498 |
+
"selected_candidate_index": 4.0,
|
| 2499 |
+
"selected_success": 0.0,
|
| 2500 |
+
"selected_success_gain_over_base": -1.0,
|
| 2501 |
+
"selected_utility": 0.18805170059204102,
|
| 2502 |
+
"selected_utility_gain_over_base": -1.811948299407959,
|
| 2503 |
+
"selector_regret": 1.811948299407959,
|
| 2504 |
+
"success_selector_gap": 1.0,
|
| 2505 |
+
"success_support_gap": 0.0,
|
| 2506 |
+
"support_gap": 0.0,
|
| 2507 |
+
"tau": 0.34408156791985406
|
| 2508 |
+
},
|
| 2509 |
+
"701667486/train1": {
|
| 2510 |
+
"base_success": 1.0,
|
| 2511 |
+
"base_utility": 2.0,
|
| 2512 |
+
"coverage": 1.0,
|
| 2513 |
+
"execute_generated": 1.0,
|
| 2514 |
+
"fallback_rate": 0.0,
|
| 2515 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2516 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2517 |
+
"outcome_ptr": 0.0,
|
| 2518 |
+
"predicted_margin": 0.5422427512573754,
|
| 2519 |
+
"proposal_oracle_success": 1.0,
|
| 2520 |
+
"proposal_oracle_utility": 2.0,
|
| 2521 |
+
"selected_candidate_index": 2.0,
|
| 2522 |
+
"selected_success": 1.0,
|
| 2523 |
+
"selected_success_gain_over_base": 0.0,
|
| 2524 |
+
"selected_utility": 2.0,
|
| 2525 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2526 |
+
"selector_regret": 0.0,
|
| 2527 |
+
"success_selector_gap": 0.0,
|
| 2528 |
+
"success_support_gap": 0.0,
|
| 2529 |
+
"support_gap": 0.0,
|
| 2530 |
+
"tau": 0.34408156791985406
|
| 2531 |
+
},
|
| 2532 |
+
"701667486/train2": {
|
| 2533 |
+
"base_success": 1.0,
|
| 2534 |
+
"base_utility": 2.0,
|
| 2535 |
+
"coverage": 1.0,
|
| 2536 |
+
"execute_generated": 1.0,
|
| 2537 |
+
"fallback_rate": 0.0,
|
| 2538 |
+
"hidden_chart_oracle_success": 1.0,
|
| 2539 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 2540 |
+
"outcome_ptr": 0.0,
|
| 2541 |
+
"predicted_margin": 0.6258136711557138,
|
| 2542 |
+
"proposal_oracle_success": 1.0,
|
| 2543 |
+
"proposal_oracle_utility": 2.0,
|
| 2544 |
+
"selected_candidate_index": 4.0,
|
| 2545 |
+
"selected_success": 1.0,
|
| 2546 |
+
"selected_success_gain_over_base": 0.0,
|
| 2547 |
+
"selected_utility": 2.0,
|
| 2548 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2549 |
+
"selector_regret": 0.0,
|
| 2550 |
+
"success_selector_gap": 0.0,
|
| 2551 |
+
"success_support_gap": 0.0,
|
| 2552 |
+
"support_gap": 0.0,
|
| 2553 |
+
"tau": 0.34408156791985406
|
| 2554 |
+
},
|
| 2555 |
+
"747260437/train0": {
|
| 2556 |
+
"base_success": 1.0,
|
| 2557 |
+
"base_utility": 2.0,
|
| 2558 |
+
"coverage": 0.0,
|
| 2559 |
+
"execute_generated": 0.0,
|
| 2560 |
+
"fallback_rate": 1.0,
|
| 2561 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2562 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2563 |
+
"outcome_ptr": 0.0,
|
| 2564 |
+
"predicted_margin": 0.13550930803858485,
|
| 2565 |
+
"proposal_oracle_success": 0.0,
|
| 2566 |
+
"proposal_oracle_utility": 0.10839563608169556,
|
| 2567 |
+
"selected_candidate_index": 6.0,
|
| 2568 |
+
"selected_success": 1.0,
|
| 2569 |
+
"selected_success_gain_over_base": 0.0,
|
| 2570 |
+
"selected_utility": 2.0,
|
| 2571 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2572 |
+
"selector_regret": 0.0,
|
| 2573 |
+
"success_selector_gap": 0.0,
|
| 2574 |
+
"success_support_gap": 0.0,
|
| 2575 |
+
"support_gap": 0.17026761174201965,
|
| 2576 |
+
"tau": 0.34408156791985406
|
| 2577 |
+
},
|
| 2578 |
+
"747260437/train1": {
|
| 2579 |
+
"base_success": 1.0,
|
| 2580 |
+
"base_utility": 2.0,
|
| 2581 |
+
"coverage": 0.0,
|
| 2582 |
+
"execute_generated": 0.0,
|
| 2583 |
+
"fallback_rate": 1.0,
|
| 2584 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2585 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2586 |
+
"outcome_ptr": 0.0,
|
| 2587 |
+
"predicted_margin": 0.0318722933242058,
|
| 2588 |
+
"proposal_oracle_success": 0.0,
|
| 2589 |
+
"proposal_oracle_utility": 0.05267423391342163,
|
| 2590 |
+
"selected_candidate_index": 0.0,
|
| 2591 |
+
"selected_success": 1.0,
|
| 2592 |
+
"selected_success_gain_over_base": 0.0,
|
| 2593 |
+
"selected_utility": 2.0,
|
| 2594 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2595 |
+
"selector_regret": 0.0,
|
| 2596 |
+
"success_selector_gap": 0.0,
|
| 2597 |
+
"success_support_gap": 0.0,
|
| 2598 |
+
"support_gap": 0.22598901391029358,
|
| 2599 |
+
"tau": 0.34408156791985406
|
| 2600 |
+
},
|
| 2601 |
+
"747260437/train2": {
|
| 2602 |
+
"base_success": 1.0,
|
| 2603 |
+
"base_utility": 2.0,
|
| 2604 |
+
"coverage": 0.0,
|
| 2605 |
+
"execute_generated": 0.0,
|
| 2606 |
+
"fallback_rate": 1.0,
|
| 2607 |
+
"hidden_chart_oracle_success": 0.0,
|
| 2608 |
+
"hidden_chart_oracle_utility": 0.2786632478237152,
|
| 2609 |
+
"outcome_ptr": 0.0,
|
| 2610 |
+
"predicted_margin": 0.04297570610377669,
|
| 2611 |
+
"proposal_oracle_success": 0.0,
|
| 2612 |
+
"proposal_oracle_utility": 0.12510187923908234,
|
| 2613 |
+
"selected_candidate_index": 7.0,
|
| 2614 |
+
"selected_success": 1.0,
|
| 2615 |
+
"selected_success_gain_over_base": 0.0,
|
| 2616 |
+
"selected_utility": 2.0,
|
| 2617 |
+
"selected_utility_gain_over_base": 0.0,
|
| 2618 |
+
"selector_regret": 0.0,
|
| 2619 |
+
"success_selector_gap": 0.0,
|
| 2620 |
+
"success_support_gap": 0.0,
|
| 2621 |
+
"support_gap": 0.15356136858463287,
|
| 2622 |
+
"tau": 0.34408156791985406
|
| 2623 |
+
},
|
| 2624 |
+
"750448296/train0": {
|
| 2625 |
+
"base_success": 0.0,
|
| 2626 |
+
"base_utility": 0.11759314934412639,
|
| 2627 |
+
"coverage": 0.3333333333333333,
|
| 2628 |
+
"execute_generated": 0.3333333333333333,
|
| 2629 |
+
"fallback_rate": 0.6666666666666666,
|
| 2630 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2631 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2632 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2633 |
+
"predicted_margin": 0.3191869353543992,
|
| 2634 |
+
"proposal_oracle_success": 0.3333333333333333,
|
| 2635 |
+
"proposal_oracle_utility": 0.7526603279014429,
|
| 2636 |
+
"selected_candidate_index": 3.6666666666666665,
|
| 2637 |
+
"selected_success": 0.3333333333333333,
|
| 2638 |
+
"selected_success_gain_over_base": 0.3333333333333333,
|
| 2639 |
+
"selected_utility": 0.7452354828516642,
|
| 2640 |
+
"selected_utility_gain_over_base": 0.6276423335075378,
|
| 2641 |
+
"selector_regret": 0.024625877539316814,
|
| 2642 |
+
"success_selector_gap": 0.0,
|
| 2643 |
+
"success_support_gap": 0.3333333333333333,
|
| 2644 |
+
"support_gap": 0.6553361676633358,
|
| 2645 |
+
"tau": 0.34408156791985406
|
| 2646 |
+
},
|
| 2647 |
+
"750448296/train1": {
|
| 2648 |
+
"base_success": 0.0,
|
| 2649 |
+
"base_utility": 0.11759314934412639,
|
| 2650 |
+
"coverage": 0.6666666666666666,
|
| 2651 |
+
"execute_generated": 0.6666666666666666,
|
| 2652 |
+
"fallback_rate": 0.3333333333333333,
|
| 2653 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2654 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2655 |
+
"outcome_ptr": 1.0,
|
| 2656 |
+
"predicted_margin": 0.39915235063549687,
|
| 2657 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2658 |
+
"proposal_oracle_utility": 1.3705032741030057,
|
| 2659 |
+
"selected_candidate_index": 5.0,
|
| 2660 |
+
"selected_success": 0.0,
|
| 2661 |
+
"selected_success_gain_over_base": 0.0,
|
| 2662 |
+
"selected_utility": 0.13002302000919977,
|
| 2663 |
+
"selected_utility_gain_over_base": 0.012429870665073395,
|
| 2664 |
+
"selector_regret": 1.240480254093806,
|
| 2665 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2666 |
+
"success_support_gap": 0.0,
|
| 2667 |
+
"support_gap": 0.03749322146177292,
|
| 2668 |
+
"tau": 0.34408156791985406
|
| 2669 |
+
},
|
| 2670 |
+
"750448296/train2": {
|
| 2671 |
+
"base_success": 0.0,
|
| 2672 |
+
"base_utility": 0.11759314934412639,
|
| 2673 |
+
"coverage": 0.3333333333333333,
|
| 2674 |
+
"execute_generated": 0.3333333333333333,
|
| 2675 |
+
"fallback_rate": 0.6666666666666666,
|
| 2676 |
+
"hidden_chart_oracle_success": 0.6666666666666666,
|
| 2677 |
+
"hidden_chart_oracle_utility": 1.4079964955647786,
|
| 2678 |
+
"outcome_ptr": 0.6666666666666666,
|
| 2679 |
+
"predicted_margin": 0.2604958289656638,
|
| 2680 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 2681 |
+
"proposal_oracle_utility": 1.349846323331197,
|
| 2682 |
+
"selected_candidate_index": 4.333333333333333,
|
| 2683 |
+
"selected_success": 0.0,
|
| 2684 |
+
"selected_success_gain_over_base": 0.0,
|
| 2685 |
+
"selected_utility": 0.10690136750539143,
|
| 2686 |
+
"selected_utility_gain_over_base": -0.010691781838734945,
|
| 2687 |
+
"selector_regret": 1.2574311296145122,
|
| 2688 |
+
"success_selector_gap": 0.6666666666666666,
|
| 2689 |
+
"success_support_gap": 0.0,
|
| 2690 |
+
"support_gap": 0.05815017223358154,
|
| 2691 |
+
"tau": 0.34408156791985406
|
| 2692 |
+
},
|
| 2693 |
+
"767747424/train0": {
|
| 2694 |
+
"base_success": 0.25,
|
| 2695 |
+
"base_utility": 0.5731993420049548,
|
| 2696 |
+
"coverage": 0.5,
|
| 2697 |
+
"execute_generated": 0.5,
|
| 2698 |
+
"fallback_rate": 0.5,
|
| 2699 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2700 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2701 |
+
"outcome_ptr": 0.5,
|
| 2702 |
+
"predicted_margin": 0.4445396242683897,
|
| 2703 |
+
"proposal_oracle_success": 0.5,
|
| 2704 |
+
"proposal_oracle_utility": 1.0424291878007352,
|
| 2705 |
+
"selected_candidate_index": 1.75,
|
| 2706 |
+
"selected_success": 0.25,
|
| 2707 |
+
"selected_success_gain_over_base": 0.0,
|
| 2708 |
+
"selected_utility": 0.5375678082928061,
|
| 2709 |
+
"selected_utility_gain_over_base": -0.035631533712148666,
|
| 2710 |
+
"selector_regret": 0.5135916564613581,
|
| 2711 |
+
"success_selector_gap": 0.25,
|
| 2712 |
+
"success_support_gap": 0.0,
|
| 2713 |
+
"support_gap": 0.06562284985557199,
|
| 2714 |
+
"tau": 0.34408156791985406
|
| 2715 |
+
},
|
| 2716 |
+
"767747424/train1": {
|
| 2717 |
+
"base_success": 0.25,
|
| 2718 |
+
"base_utility": 0.5731993420049548,
|
| 2719 |
+
"coverage": 0.5,
|
| 2720 |
+
"execute_generated": 0.5,
|
| 2721 |
+
"fallback_rate": 0.5,
|
| 2722 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2723 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2724 |
+
"outcome_ptr": 0.25,
|
| 2725 |
+
"predicted_margin": 0.3626172469935749,
|
| 2726 |
+
"proposal_oracle_success": 0.25,
|
| 2727 |
+
"proposal_oracle_utility": 0.5951075805351138,
|
| 2728 |
+
"selected_candidate_index": 2.0,
|
| 2729 |
+
"selected_success": 0.25,
|
| 2730 |
+
"selected_success_gain_over_base": 0.0,
|
| 2731 |
+
"selected_utility": 0.5778386716265231,
|
| 2732 |
+
"selected_utility_gain_over_base": 0.004639329621568322,
|
| 2733 |
+
"selector_regret": 0.025535901775583625,
|
| 2734 |
+
"success_selector_gap": 0.0,
|
| 2735 |
+
"success_support_gap": 0.25,
|
| 2736 |
+
"support_gap": 0.5129444571211934,
|
| 2737 |
+
"tau": 0.34408156791985406
|
| 2738 |
+
},
|
| 2739 |
+
"767747424/train2": {
|
| 2740 |
+
"base_success": 0.25,
|
| 2741 |
+
"base_utility": 0.5731993420049548,
|
| 2742 |
+
"coverage": 0.5,
|
| 2743 |
+
"execute_generated": 0.5,
|
| 2744 |
+
"fallback_rate": 0.5,
|
| 2745 |
+
"hidden_chart_oracle_success": 0.25,
|
| 2746 |
+
"hidden_chart_oracle_utility": 0.6737305596470833,
|
| 2747 |
+
"outcome_ptr": 0.5,
|
| 2748 |
+
"predicted_margin": 0.33960353103820384,
|
| 2749 |
+
"proposal_oracle_success": 0.25,
|
| 2750 |
+
"proposal_oracle_utility": 0.6134321661666036,
|
| 2751 |
+
"selected_candidate_index": 4.75,
|
| 2752 |
+
"selected_success": 0.25,
|
| 2753 |
+
"selected_success_gain_over_base": 0.0,
|
| 2754 |
+
"selected_utility": 0.5891513926908374,
|
| 2755 |
+
"selected_utility_gain_over_base": 0.01595205068588257,
|
| 2756 |
+
"selector_regret": 0.024280773475766182,
|
| 2757 |
+
"success_selector_gap": 0.0,
|
| 2758 |
+
"success_support_gap": 0.25,
|
| 2759 |
+
"support_gap": 0.49461987148970366,
|
| 2760 |
+
"tau": 0.34408156791985406
|
| 2761 |
+
}
|
| 2762 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/metrics_by_task.json
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"LiftPegUpright-v1": {
|
| 3 |
+
"base_success": 0.2,
|
| 4 |
+
"base_utility": 0.9498705387115478,
|
| 5 |
+
"coverage": 0.4666666666666667,
|
| 6 |
+
"execute_generated": 0.4666666666666667,
|
| 7 |
+
"fallback_rate": 0.5333333333333333,
|
| 8 |
+
"hidden_chart_oracle_success": 1.0,
|
| 9 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 10 |
+
"outcome_ptr": 0.4666666666666667,
|
| 11 |
+
"predicted_margin": 0.34879604119920893,
|
| 12 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 13 |
+
"proposal_oracle_utility": 1.2244940986235937,
|
| 14 |
+
"selected_candidate_index": 1.7333333333333334,
|
| 15 |
+
"selected_success": 0.26666666666666666,
|
| 16 |
+
"selected_success_gain_over_base": 0.06666666666666667,
|
| 17 |
+
"selected_utility": 1.0197147250175476,
|
| 18 |
+
"selected_utility_gain_over_base": 0.06984418630599976,
|
| 19 |
+
"selector_regret": 0.27158633470535276,
|
| 20 |
+
"success_selector_gap": 0.2,
|
| 21 |
+
"success_support_gap": 0.5333333333333333,
|
| 22 |
+
"support_gap": 0.7755059013764064,
|
| 23 |
+
"tau": 0.34408156791985406
|
| 24 |
+
},
|
| 25 |
+
"PickCube-v1": {
|
| 26 |
+
"base_success": 0.0,
|
| 27 |
+
"base_utility": 0.5839591026306152,
|
| 28 |
+
"coverage": 0.0,
|
| 29 |
+
"execute_generated": 0.0,
|
| 30 |
+
"fallback_rate": 1.0,
|
| 31 |
+
"hidden_chart_oracle_success": 1.0,
|
| 32 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 33 |
+
"outcome_ptr": 0.0,
|
| 34 |
+
"predicted_margin": 0.03600324406049464,
|
| 35 |
+
"proposal_oracle_success": 0.0,
|
| 36 |
+
"proposal_oracle_utility": 0.13425676027933756,
|
| 37 |
+
"selected_candidate_index": 3.0,
|
| 38 |
+
"selected_success": 0.0,
|
| 39 |
+
"selected_success_gain_over_base": 0.0,
|
| 40 |
+
"selected_utility": 0.5839591026306152,
|
| 41 |
+
"selected_utility_gain_over_base": 0.0,
|
| 42 |
+
"selector_regret": 0.0,
|
| 43 |
+
"success_selector_gap": 0.0,
|
| 44 |
+
"success_support_gap": 1.0,
|
| 45 |
+
"support_gap": 1.8657432397206624,
|
| 46 |
+
"tau": 0.34408156791985406
|
| 47 |
+
},
|
| 48 |
+
"PullCube-v1": {
|
| 49 |
+
"base_success": 0.36,
|
| 50 |
+
"base_utility": 0.7751704612234608,
|
| 51 |
+
"coverage": 0.41333333333333333,
|
| 52 |
+
"execute_generated": 0.41333333333333333,
|
| 53 |
+
"fallback_rate": 0.5866666666666667,
|
| 54 |
+
"hidden_chart_oracle_success": 0.52,
|
| 55 |
+
"hidden_chart_oracle_utility": 1.1467878860235214,
|
| 56 |
+
"outcome_ptr": 0.44,
|
| 57 |
+
"predicted_margin": 0.33772887669024154,
|
| 58 |
+
"proposal_oracle_success": 0.4666666666666667,
|
| 59 |
+
"proposal_oracle_utility": 0.9816135169876119,
|
| 60 |
+
"selected_candidate_index": 3.453333333333333,
|
| 61 |
+
"selected_success": 0.3333333333333333,
|
| 62 |
+
"selected_success_gain_over_base": -0.02666666666666667,
|
| 63 |
+
"selected_utility": 0.7196805840544402,
|
| 64 |
+
"selected_utility_gain_over_base": -0.05548987716902047,
|
| 65 |
+
"selector_regret": 0.37178792303428054,
|
| 66 |
+
"success_selector_gap": 0.18666666666666668,
|
| 67 |
+
"success_support_gap": 0.09333333333333334,
|
| 68 |
+
"support_gap": 0.23527305972451965,
|
| 69 |
+
"tau": 0.3440815679198542
|
| 70 |
+
},
|
| 71 |
+
"PushCube-v1": {
|
| 72 |
+
"base_success": 0.16666666666666666,
|
| 73 |
+
"base_utility": 0.3924041787783305,
|
| 74 |
+
"coverage": 1.0,
|
| 75 |
+
"execute_generated": 1.0,
|
| 76 |
+
"fallback_rate": 0.0,
|
| 77 |
+
"hidden_chart_oracle_success": 0.8333333333333334,
|
| 78 |
+
"hidden_chart_oracle_utility": 1.7015800600250561,
|
| 79 |
+
"outcome_ptr": 0.7777777777777778,
|
| 80 |
+
"predicted_margin": 0.7573891615571136,
|
| 81 |
+
"proposal_oracle_success": 0.6666666666666666,
|
| 82 |
+
"proposal_oracle_utility": 1.365773618221283,
|
| 83 |
+
"selected_candidate_index": 2.611111111111111,
|
| 84 |
+
"selected_success": 0.3333333333333333,
|
| 85 |
+
"selected_success_gain_over_base": 0.16666666666666666,
|
| 86 |
+
"selected_utility": 0.7119888936479887,
|
| 87 |
+
"selected_utility_gain_over_base": 0.31958471486965817,
|
| 88 |
+
"selector_regret": 0.6537847245732943,
|
| 89 |
+
"success_selector_gap": 0.3333333333333333,
|
| 90 |
+
"success_support_gap": 0.3333333333333333,
|
| 91 |
+
"support_gap": 0.634226381778717,
|
| 92 |
+
"tau": 0.3440815679198541
|
| 93 |
+
},
|
| 94 |
+
"StackCube-v1": {
|
| 95 |
+
"base_success": 0.2727272727272727,
|
| 96 |
+
"base_utility": 0.7763947045261209,
|
| 97 |
+
"coverage": 0.3333333333333333,
|
| 98 |
+
"execute_generated": 0.3333333333333333,
|
| 99 |
+
"fallback_rate": 0.6666666666666666,
|
| 100 |
+
"hidden_chart_oracle_success": 1.0,
|
| 101 |
+
"hidden_chart_oracle_utility": 2.0,
|
| 102 |
+
"outcome_ptr": 0.5757575757575758,
|
| 103 |
+
"predicted_margin": 0.31486228576542635,
|
| 104 |
+
"proposal_oracle_success": 0.45454545454545453,
|
| 105 |
+
"proposal_oracle_utility": 1.0546941955884297,
|
| 106 |
+
"selected_candidate_index": 3.8484848484848486,
|
| 107 |
+
"selected_success": 0.24242424242424243,
|
| 108 |
+
"selected_success_gain_over_base": -0.030303030303030304,
|
| 109 |
+
"selected_utility": 0.7367336921619646,
|
| 110 |
+
"selected_utility_gain_over_base": -0.03966101236415632,
|
| 111 |
+
"selector_regret": 0.3222826457384861,
|
| 112 |
+
"success_selector_gap": 0.21212121212121213,
|
| 113 |
+
"success_support_gap": 0.5454545454545454,
|
| 114 |
+
"support_gap": 0.9453058044115702,
|
| 115 |
+
"tau": 0.34408156791985417
|
| 116 |
+
}
|
| 117 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/report.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Nonlinear Train-Calibrated CTT Selector
|
| 2 |
+
|
| 3 |
+
Calibration rows: `432`
|
| 4 |
+
Fit rows: `277`
|
| 5 |
+
Selection rows: `155`
|
| 6 |
+
Eval rows: `144`
|
| 7 |
+
Selected model: `hgb_classifier`
|
| 8 |
+
Selected params: `{"l2_regularization": 0.01, "learning_rate": 0.05, "max_iter": 80, "max_leaf_nodes": 15, "random_state": 0}`
|
| 9 |
+
Tau: `0.344082`
|
| 10 |
+
Feature set: `context_tangent`
|
| 11 |
+
Target: `success`
|
| 12 |
+
|
| 13 |
+
The model is fit on calibration-fit rows, and model/tau are selected on held-out calibration-selection rows only. Eval outcomes are used only for reporting.
|
| 14 |
+
|
| 15 |
+
| Split | Coverage | Fallback | Base success | Selected success | Proposal oracle | OutcomePTR | Success support gap | Success selector gap |
|
| 16 |
+
| --- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
|
| 17 |
+
| fit | 0.4729 | 0.5271 | 0.2780 | 0.5126 | 0.4910 | 0.4838 | 0.2058 | 0.0433 |
|
| 18 |
+
| selection | 0.4710 | 0.5290 | 0.2774 | 0.3742 | 0.4387 | 0.5032 | 0.2774 | 0.1226 |
|
| 19 |
+
| eval | 0.4653 | 0.5347 | 0.2917 | 0.2986 | 0.4792 | 0.5069 | 0.2917 | 0.2083 |
|
| 20 |
+
|
| 21 |
+
This is a train-calibrated selector diagnostic over already measured candidates, not a new rollout.
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/split_hash.txt
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"calibration_target_index": {
|
| 3 |
+
"content_hash": "67f7b4a692f7c7e71da24378dc71e3399c5d35afc14c494869eba6087b765c42",
|
| 4 |
+
"retrieval_index_allowed": true,
|
| 5 |
+
"split": "train",
|
| 6 |
+
"split_hash": "867a94a1c67686c082765671a7bf8d74a9d633085e1b2619c83197c60bf58372"
|
| 7 |
+
},
|
| 8 |
+
"eval_target_index": {
|
| 9 |
+
"content_hash": "0c38d73dc9bc4ab756e12006671b5d12f1a23358b281e54b3f6a9ae3cbf6e9af",
|
| 10 |
+
"retrieval_index_allowed": false,
|
| 11 |
+
"split": "test",
|
| 12 |
+
"split_hash": "84151df9e88c219b76751677558cc5bbbc19082bf358cea7330158e9e403e25f"
|
| 13 |
+
}
|
| 14 |
+
}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/table.tex
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
% Auto-generated by scripts/eval_nonlinear_dominance_selector.py
|
| 2 |
+
\begin{tabular}{lrrrrrrrr}
|
| 3 |
+
\toprule
|
| 4 |
+
Rows & Coverage & Fallback & Base succ. & Selected succ. & Oracle succ. & OutcomePTR & Succ. support gap & Succ. selector gap \\
|
| 5 |
+
\midrule
|
| 6 |
+
144 & 0.4653 & 0.5347 & 0.2917 & 0.2986 & 0.4792 & 0.5069 & 0.2917 & 0.2083 \\
|
| 7 |
+
\bottomrule
|
| 8 |
+
\end{tabular}
|
workspace/runs/ctt_base_context_obs_nonlinear_dominance_context_tangent_success_envclip_train_to_test/train.log
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
trained nonlinear dominance selector on calibration-fit rows only
|
| 2 |
+
selected_model_type=hgb_classifier
|
| 3 |
+
selected_model_params={"l2_regularization": 0.01, "learning_rate": 0.05, "max_iter": 80, "max_leaf_nodes": 15, "random_state": 0}
|
| 4 |
+
tau=0.344082
|
| 5 |
+
calibration_input=runs/ctt_base_context_obs_train_cal_envclip_rollout_comparison/combined_measured_candidates.json
|