Instructions to use evalengine/decision-0.8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use evalengine/decision-0.8b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B") model = PeftModel.from_pretrained(base_model, "evalengine/decision-0.8b") - Notebooks
- Google Colab
- Kaggle
Download evaluation/fresh-comparison.json from evalengine/decision-0.8b: direct link, hf CLI and curl.
- Browser
- Download file 255 kB
-
https://huggingface.co/evalengine/decision-0.8b/resolve/main/evaluation/fresh-comparison.json
- Command line
-
hf download hf://evalengine/decision-0.8b/evaluation/fresh-comparison.json
-
curl -L -o fresh-comparison.json https://huggingface.co/evalengine/decision-0.8b/resolve/main/evaluation/fresh-comparison.json
255 kB
| { | |
| "records": 500, | |
| "dataset_sha256": "9411bdb509a0f18dbb742b4e027613f875b7ac537e4e2ebb688cdc9394ffdd8a", | |
| "models": { | |
| "tev": { | |
| "count": 500, | |
| "attempted": 500, | |
| "scored": 500, | |
| "errors": 0, | |
| "skipped": 0, | |
| "accuracy_all": 0.682, | |
| "accuracy_attempted": 0.682, | |
| "accuracy_scored": 0.682, | |
| "accuracy_family_macro": 0.6819999999999999, | |
| "accuracy_by_family": { | |
| "clinc150": 0.83, | |
| "go_emotions": 0.69, | |
| "helpsteer2": 0.56, | |
| "paws": 0.57, | |
| "vitaminc": 0.76 | |
| }, | |
| "by_source": { | |
| "clinc150": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.83, | |
| "accuracy_attempted": 0.83, | |
| "macro_f1_scored": 0.7186079953983319, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "go_emotions": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.69, | |
| "accuracy_attempted": 0.69, | |
| "macro_f1_scored": 0.6783898744683059, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "helpsteer2": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.56, | |
| "accuracy_attempted": 0.56, | |
| "macro_f1_scored": 0.17182266009852218, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "paws": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.57, | |
| "accuracy_attempted": 0.57, | |
| "macro_f1_scored": 0.5459824728117411, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "vitaminc": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.76, | |
| "accuracy_attempted": 0.76, | |
| "macro_f1_scored": 0.6234891285738743, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| } | |
| }, | |
| "probability_metrics": { | |
| "count": 500, | |
| "brier_multiclass_sum": 0.4771125257344734, | |
| "nll": 0.9122046500219623, | |
| "infinite_nll_cases": 0, | |
| "ece": 0.12910524678230287, | |
| "ece_equal_width_bins": 15, | |
| "aurc": 0.2146130907438458, | |
| "coverage_at_error": { | |
| "0.01": 0.006, | |
| "0.05": 0.006, | |
| "0.1": 0.088 | |
| }, | |
| "risk_coverage_note": "Empirical diagnostic, not a held-out error guarantee; whole ties accepted.", | |
| "risk_coverage": [ | |
| { | |
| "threshold": 0.9999605417251587, | |
| "accepted": 1, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.002, | |
| "coverage_of_all_cases": 0.002 | |
| }, | |
| { | |
| "threshold": 0.9995808005332947, | |
| "accepted": 2, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.004, | |
| "coverage_of_all_cases": 0.004 | |
| }, | |
| { | |
| "threshold": 0.9995239973068237, | |
| "accepted": 3, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.006, | |
| "coverage_of_all_cases": 0.006 | |
| }, | |
| { | |
| "threshold": 0.9994471669197083, | |
| "accepted": 4, | |
| "errors": 1, | |
| "risk": 0.25, | |
| "coverage": 0.008, | |
| "coverage_of_all_cases": 0.008 | |
| }, | |
| { | |
| "threshold": 0.9992903470993042, | |
| "accepted": 5, | |
| "errors": 1, | |
| "risk": 0.2, | |
| "coverage": 0.01, | |
| "coverage_of_all_cases": 0.01 | |
| }, | |
| { | |
| "threshold": 0.9989027976989746, | |
| "accepted": 6, | |
| "errors": 1, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.012, | |
| "coverage_of_all_cases": 0.012 | |
| }, | |
| { | |
| "threshold": 0.9987660646438599, | |
| "accepted": 7, | |
| "errors": 1, | |
| "risk": 0.14285714285714285, | |
| "coverage": 0.014, | |
| "coverage_of_all_cases": 0.014 | |
| }, | |
| { | |
| "threshold": 0.9987118244171143, | |
| "accepted": 8, | |
| "errors": 2, | |
| "risk": 0.25, | |
| "coverage": 0.016, | |
| "coverage_of_all_cases": 0.016 | |
| }, | |
| { | |
| "threshold": 0.9986749291419983, | |
| "accepted": 10, | |
| "errors": 3, | |
| "risk": 0.3, | |
| "coverage": 0.02, | |
| "coverage_of_all_cases": 0.02 | |
| }, | |
| { | |
| "threshold": 0.9984625577926636, | |
| "accepted": 11, | |
| "errors": 3, | |
| "risk": 0.2727272727272727, | |
| "coverage": 0.022, | |
| "coverage_of_all_cases": 0.022 | |
| }, | |
| { | |
| "threshold": 0.9984014630317688, | |
| "accepted": 12, | |
| "errors": 3, | |
| "risk": 0.25, | |
| "coverage": 0.024, | |
| "coverage_of_all_cases": 0.024 | |
| }, | |
| { | |
| "threshold": 0.9980282187461853, | |
| "accepted": 13, | |
| "errors": 3, | |
| "risk": 0.23076923076923078, | |
| "coverage": 0.026, | |
| "coverage_of_all_cases": 0.026 | |
| }, | |
| { | |
| "threshold": 0.9979761242866516, | |
| "accepted": 14, | |
| "errors": 3, | |
| "risk": 0.21428571428571427, | |
| "coverage": 0.028, | |
| "coverage_of_all_cases": 0.028 | |
| }, | |
| { | |
| "threshold": 0.99787437915802, | |
| "accepted": 15, | |
| "errors": 3, | |
| "risk": 0.2, | |
| "coverage": 0.03, | |
| "coverage_of_all_cases": 0.03 | |
| }, | |
| { | |
| "threshold": 0.9973328113555908, | |
| "accepted": 16, | |
| "errors": 3, | |
| "risk": 0.1875, | |
| "coverage": 0.032, | |
| "coverage_of_all_cases": 0.032 | |
| }, | |
| { | |
| "threshold": 0.9971990585327148, | |
| "accepted": 18, | |
| "errors": 3, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.036, | |
| "coverage_of_all_cases": 0.036 | |
| }, | |
| { | |
| "threshold": 0.9967085123062134, | |
| "accepted": 19, | |
| "errors": 3, | |
| "risk": 0.15789473684210525, | |
| "coverage": 0.038, | |
| "coverage_of_all_cases": 0.038 | |
| }, | |
| { | |
| "threshold": 0.9961239695549011, | |
| "accepted": 20, | |
| "errors": 3, | |
| "risk": 0.15, | |
| "coverage": 0.04, | |
| "coverage_of_all_cases": 0.04 | |
| }, | |
| { | |
| "threshold": 0.9961221814155579, | |
| "accepted": 21, | |
| "errors": 3, | |
| "risk": 0.14285714285714285, | |
| "coverage": 0.042, | |
| "coverage_of_all_cases": 0.042 | |
| }, | |
| { | |
| "threshold": 0.9951249957084656, | |
| "accepted": 22, | |
| "errors": 3, | |
| "risk": 0.13636363636363635, | |
| "coverage": 0.044, | |
| "coverage_of_all_cases": 0.044 | |
| }, | |
| { | |
| "threshold": 0.9949851036071777, | |
| "accepted": 23, | |
| "errors": 3, | |
| "risk": 0.13043478260869565, | |
| "coverage": 0.046, | |
| "coverage_of_all_cases": 0.046 | |
| }, | |
| { | |
| "threshold": 0.9949706196784973, | |
| "accepted": 24, | |
| "errors": 3, | |
| "risk": 0.125, | |
| "coverage": 0.048, | |
| "coverage_of_all_cases": 0.048 | |
| }, | |
| { | |
| "threshold": 0.9941239953041077, | |
| "accepted": 25, | |
| "errors": 3, | |
| "risk": 0.12, | |
| "coverage": 0.05, | |
| "coverage_of_all_cases": 0.05 | |
| }, | |
| { | |
| "threshold": 0.9940488338470459, | |
| "accepted": 26, | |
| "errors": 3, | |
| "risk": 0.11538461538461539, | |
| "coverage": 0.052, | |
| "coverage_of_all_cases": 0.052 | |
| }, | |
| { | |
| "threshold": 0.9937092065811157, | |
| "accepted": 27, | |
| "errors": 3, | |
| "risk": 0.1111111111111111, | |
| "coverage": 0.054, | |
| "coverage_of_all_cases": 0.054 | |
| }, | |
| { | |
| "threshold": 0.9932942986488342, | |
| "accepted": 28, | |
| "errors": 3, | |
| "risk": 0.10714285714285714, | |
| "coverage": 0.056, | |
| "coverage_of_all_cases": 0.056 | |
| }, | |
| { | |
| "threshold": 0.9932383298873901, | |
| "accepted": 29, | |
| "errors": 3, | |
| "risk": 0.10344827586206896, | |
| "coverage": 0.058, | |
| "coverage_of_all_cases": 0.058 | |
| }, | |
| { | |
| "threshold": 0.9928731918334961, | |
| "accepted": 30, | |
| "errors": 3, | |
| "risk": 0.1, | |
| "coverage": 0.06, | |
| "coverage_of_all_cases": 0.06 | |
| }, | |
| { | |
| "threshold": 0.9924227595329285, | |
| "accepted": 34, | |
| "errors": 3, | |
| "risk": 0.08823529411764706, | |
| "coverage": 0.068, | |
| "coverage_of_all_cases": 0.068 | |
| }, | |
| { | |
| "threshold": 0.9923338890075684, | |
| "accepted": 35, | |
| "errors": 3, | |
| "risk": 0.08571428571428572, | |
| "coverage": 0.07, | |
| "coverage_of_all_cases": 0.07 | |
| }, | |
| { | |
| "threshold": 0.9914224743843079, | |
| "accepted": 36, | |
| "errors": 4, | |
| "risk": 0.1111111111111111, | |
| "coverage": 0.072, | |
| "coverage_of_all_cases": 0.072 | |
| }, | |
| { | |
| "threshold": 0.9912471175193787, | |
| "accepted": 37, | |
| "errors": 4, | |
| "risk": 0.10810810810810811, | |
| "coverage": 0.074, | |
| "coverage_of_all_cases": 0.074 | |
| }, | |
| { | |
| "threshold": 0.9908271431922913, | |
| "accepted": 38, | |
| "errors": 4, | |
| "risk": 0.10526315789473684, | |
| "coverage": 0.076, | |
| "coverage_of_all_cases": 0.076 | |
| }, | |
| { | |
| "threshold": 0.9905836582183838, | |
| "accepted": 39, | |
| "errors": 4, | |
| "risk": 0.10256410256410256, | |
| "coverage": 0.078, | |
| "coverage_of_all_cases": 0.078 | |
| }, | |
| { | |
| "threshold": 0.9905250668525696, | |
| "accepted": 40, | |
| "errors": 4, | |
| "risk": 0.1, | |
| "coverage": 0.08, | |
| "coverage_of_all_cases": 0.08 | |
| }, | |
| { | |
| "threshold": 0.9902915358543396, | |
| "accepted": 41, | |
| "errors": 4, | |
| "risk": 0.0975609756097561, | |
| "coverage": 0.082, | |
| "coverage_of_all_cases": 0.082 | |
| }, | |
| { | |
| "threshold": 0.9897508025169373, | |
| "accepted": 42, | |
| "errors": 4, | |
| "risk": 0.09523809523809523, | |
| "coverage": 0.084, | |
| "coverage_of_all_cases": 0.084 | |
| }, | |
| { | |
| "threshold": 0.9896525740623474, | |
| "accepted": 43, | |
| "errors": 4, | |
| "risk": 0.09302325581395349, | |
| "coverage": 0.086, | |
| "coverage_of_all_cases": 0.086 | |
| }, | |
| { | |
| "threshold": 0.9896133542060852, | |
| "accepted": 44, | |
| "errors": 4, | |
| "risk": 0.09090909090909091, | |
| "coverage": 0.088, | |
| "coverage_of_all_cases": 0.088 | |
| }, | |
| { | |
| "threshold": 0.9890130758285522, | |
| "accepted": 45, | |
| "errors": 5, | |
| "risk": 0.1111111111111111, | |
| "coverage": 0.09, | |
| "coverage_of_all_cases": 0.09 | |
| }, | |
| { | |
| "threshold": 0.9882264733314514, | |
| "accepted": 46, | |
| "errors": 5, | |
| "risk": 0.10869565217391304, | |
| "coverage": 0.092, | |
| "coverage_of_all_cases": 0.092 | |
| }, | |
| { | |
| "threshold": 0.9877169728279114, | |
| "accepted": 47, | |
| "errors": 5, | |
| "risk": 0.10638297872340426, | |
| "coverage": 0.094, | |
| "coverage_of_all_cases": 0.094 | |
| }, | |
| { | |
| "threshold": 0.9875683188438416, | |
| "accepted": 50, | |
| "errors": 7, | |
| "risk": 0.14, | |
| "coverage": 0.1, | |
| "coverage_of_all_cases": 0.1 | |
| }, | |
| { | |
| "threshold": 0.9864277243614197, | |
| "accepted": 51, | |
| "errors": 7, | |
| "risk": 0.13725490196078433, | |
| "coverage": 0.102, | |
| "coverage_of_all_cases": 0.102 | |
| }, | |
| { | |
| "threshold": 0.9859364032745361, | |
| "accepted": 55, | |
| "errors": 8, | |
| "risk": 0.14545454545454545, | |
| "coverage": 0.11, | |
| "coverage_of_all_cases": 0.11 | |
| }, | |
| { | |
| "threshold": 0.9858828186988831, | |
| "accepted": 56, | |
| "errors": 9, | |
| "risk": 0.16071428571428573, | |
| "coverage": 0.112, | |
| "coverage_of_all_cases": 0.112 | |
| }, | |
| { | |
| "threshold": 0.9853907823562622, | |
| "accepted": 57, | |
| "errors": 9, | |
| "risk": 0.15789473684210525, | |
| "coverage": 0.114, | |
| "coverage_of_all_cases": 0.114 | |
| }, | |
| { | |
| "threshold": 0.9847862124443054, | |
| "accepted": 58, | |
| "errors": 9, | |
| "risk": 0.15517241379310345, | |
| "coverage": 0.116, | |
| "coverage_of_all_cases": 0.116 | |
| }, | |
| { | |
| "threshold": 0.9846483469009399, | |
| "accepted": 59, | |
| "errors": 9, | |
| "risk": 0.15254237288135594, | |
| "coverage": 0.118, | |
| "coverage_of_all_cases": 0.118 | |
| }, | |
| { | |
| "threshold": 0.9840936064720154, | |
| "accepted": 61, | |
| "errors": 9, | |
| "risk": 0.14754098360655737, | |
| "coverage": 0.122, | |
| "coverage_of_all_cases": 0.122 | |
| }, | |
| { | |
| "threshold": 0.9837685227394104, | |
| "accepted": 62, | |
| "errors": 9, | |
| "risk": 0.14516129032258066, | |
| "coverage": 0.124, | |
| "coverage_of_all_cases": 0.124 | |
| }, | |
| { | |
| "threshold": 0.9836230874061584, | |
| "accepted": 63, | |
| "errors": 9, | |
| "risk": 0.14285714285714285, | |
| "coverage": 0.126, | |
| "coverage_of_all_cases": 0.126 | |
| }, | |
| { | |
| "threshold": 0.9835531711578369, | |
| "accepted": 64, | |
| "errors": 9, | |
| "risk": 0.140625, | |
| "coverage": 0.128, | |
| "coverage_of_all_cases": 0.128 | |
| }, | |
| { | |
| "threshold": 0.9824768900871277, | |
| "accepted": 65, | |
| "errors": 9, | |
| "risk": 0.13846153846153847, | |
| "coverage": 0.13, | |
| "coverage_of_all_cases": 0.13 | |
| }, | |
| { | |
| "threshold": 0.982313871383667, | |
| "accepted": 66, | |
| "errors": 9, | |
| "risk": 0.13636363636363635, | |
| "coverage": 0.132, | |
| "coverage_of_all_cases": 0.132 | |
| }, | |
| { | |
| "threshold": 0.9820137619972229, | |
| "accepted": 68, | |
| "errors": 10, | |
| "risk": 0.14705882352941177, | |
| "coverage": 0.136, | |
| "coverage_of_all_cases": 0.136 | |
| }, | |
| { | |
| "threshold": 0.9817923903465271, | |
| "accepted": 69, | |
| "errors": 11, | |
| "risk": 0.15942028985507245, | |
| "coverage": 0.138, | |
| "coverage_of_all_cases": 0.138 | |
| }, | |
| { | |
| "threshold": 0.9799087643623352, | |
| "accepted": 70, | |
| "errors": 11, | |
| "risk": 0.15714285714285714, | |
| "coverage": 0.14, | |
| "coverage_of_all_cases": 0.14 | |
| }, | |
| { | |
| "threshold": 0.979312539100647, | |
| "accepted": 71, | |
| "errors": 11, | |
| "risk": 0.15492957746478872, | |
| "coverage": 0.142, | |
| "coverage_of_all_cases": 0.142 | |
| }, | |
| { | |
| "threshold": 0.978954017162323, | |
| "accepted": 72, | |
| "errors": 11, | |
| "risk": 0.1527777777777778, | |
| "coverage": 0.144, | |
| "coverage_of_all_cases": 0.144 | |
| }, | |
| { | |
| "threshold": 0.9787108302116394, | |
| "accepted": 73, | |
| "errors": 11, | |
| "risk": 0.1506849315068493, | |
| "coverage": 0.146, | |
| "coverage_of_all_cases": 0.146 | |
| }, | |
| { | |
| "threshold": 0.9785712361335754, | |
| "accepted": 74, | |
| "errors": 11, | |
| "risk": 0.14864864864864866, | |
| "coverage": 0.148, | |
| "coverage_of_all_cases": 0.148 | |
| }, | |
| { | |
| "threshold": 0.9784640073776245, | |
| "accepted": 75, | |
| "errors": 11, | |
| "risk": 0.14666666666666667, | |
| "coverage": 0.15, | |
| "coverage_of_all_cases": 0.15 | |
| }, | |
| { | |
| "threshold": 0.9783686399459839, | |
| "accepted": 76, | |
| "errors": 11, | |
| "risk": 0.14473684210526316, | |
| "coverage": 0.152, | |
| "coverage_of_all_cases": 0.152 | |
| }, | |
| { | |
| "threshold": 0.9782274961471558, | |
| "accepted": 77, | |
| "errors": 11, | |
| "risk": 0.14285714285714285, | |
| "coverage": 0.154, | |
| "coverage_of_all_cases": 0.154 | |
| }, | |
| { | |
| "threshold": 0.9780428409576416, | |
| "accepted": 78, | |
| "errors": 11, | |
| "risk": 0.14102564102564102, | |
| "coverage": 0.156, | |
| "coverage_of_all_cases": 0.156 | |
| }, | |
| { | |
| "threshold": 0.9777677655220032, | |
| "accepted": 79, | |
| "errors": 12, | |
| "risk": 0.1518987341772152, | |
| "coverage": 0.158, | |
| "coverage_of_all_cases": 0.158 | |
| }, | |
| { | |
| "threshold": 0.9774346351623535, | |
| "accepted": 80, | |
| "errors": 12, | |
| "risk": 0.15, | |
| "coverage": 0.16, | |
| "coverage_of_all_cases": 0.16 | |
| }, | |
| { | |
| "threshold": 0.977022647857666, | |
| "accepted": 82, | |
| "errors": 12, | |
| "risk": 0.14634146341463414, | |
| "coverage": 0.164, | |
| "coverage_of_all_cases": 0.164 | |
| }, | |
| { | |
| "threshold": 0.9745867252349854, | |
| "accepted": 83, | |
| "errors": 12, | |
| "risk": 0.14457831325301204, | |
| "coverage": 0.166, | |
| "coverage_of_all_cases": 0.166 | |
| }, | |
| { | |
| "threshold": 0.9740425944328308, | |
| "accepted": 86, | |
| "errors": 13, | |
| "risk": 0.1511627906976744, | |
| "coverage": 0.172, | |
| "coverage_of_all_cases": 0.172 | |
| }, | |
| { | |
| "threshold": 0.973919689655304, | |
| "accepted": 87, | |
| "errors": 13, | |
| "risk": 0.14942528735632185, | |
| "coverage": 0.174, | |
| "coverage_of_all_cases": 0.174 | |
| }, | |
| { | |
| "threshold": 0.9732432961463928, | |
| "accepted": 88, | |
| "errors": 13, | |
| "risk": 0.14772727272727273, | |
| "coverage": 0.176, | |
| "coverage_of_all_cases": 0.176 | |
| }, | |
| { | |
| "threshold": 0.9724129438400269, | |
| "accepted": 89, | |
| "errors": 14, | |
| "risk": 0.15730337078651685, | |
| "coverage": 0.178, | |
| "coverage_of_all_cases": 0.178 | |
| }, | |
| { | |
| "threshold": 0.9709238409996033, | |
| "accepted": 90, | |
| "errors": 15, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.18, | |
| "coverage_of_all_cases": 0.18 | |
| }, | |
| { | |
| "threshold": 0.970687747001648, | |
| "accepted": 94, | |
| "errors": 16, | |
| "risk": 0.1702127659574468, | |
| "coverage": 0.188, | |
| "coverage_of_all_cases": 0.188 | |
| }, | |
| { | |
| "threshold": 0.9705185294151306, | |
| "accepted": 95, | |
| "errors": 16, | |
| "risk": 0.16842105263157894, | |
| "coverage": 0.19, | |
| "coverage_of_all_cases": 0.19 | |
| }, | |
| { | |
| "threshold": 0.9694164991378784, | |
| "accepted": 96, | |
| "errors": 16, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.192, | |
| "coverage_of_all_cases": 0.192 | |
| }, | |
| { | |
| "threshold": 0.9669140577316284, | |
| "accepted": 100, | |
| "errors": 17, | |
| "risk": 0.17, | |
| "coverage": 0.2, | |
| "coverage_of_all_cases": 0.2 | |
| }, | |
| { | |
| "threshold": 0.966042160987854, | |
| "accepted": 101, | |
| "errors": 17, | |
| "risk": 0.16831683168316833, | |
| "coverage": 0.202, | |
| "coverage_of_all_cases": 0.202 | |
| }, | |
| { | |
| "threshold": 0.9656751751899719, | |
| "accepted": 102, | |
| "errors": 17, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.204, | |
| "coverage_of_all_cases": 0.204 | |
| }, | |
| { | |
| "threshold": 0.9652398228645325, | |
| "accepted": 103, | |
| "errors": 17, | |
| "risk": 0.1650485436893204, | |
| "coverage": 0.206, | |
| "coverage_of_all_cases": 0.206 | |
| }, | |
| { | |
| "threshold": 0.9626730680465698, | |
| "accepted": 106, | |
| "errors": 17, | |
| "risk": 0.16037735849056603, | |
| "coverage": 0.212, | |
| "coverage_of_all_cases": 0.212 | |
| }, | |
| { | |
| "threshold": 0.962068498134613, | |
| "accepted": 107, | |
| "errors": 17, | |
| "risk": 0.1588785046728972, | |
| "coverage": 0.214, | |
| "coverage_of_all_cases": 0.214 | |
| }, | |
| { | |
| "threshold": 0.9601105451583862, | |
| "accepted": 108, | |
| "errors": 18, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.216, | |
| "coverage_of_all_cases": 0.216 | |
| }, | |
| { | |
| "threshold": 0.9593423008918762, | |
| "accepted": 109, | |
| "errors": 18, | |
| "risk": 0.1651376146788991, | |
| "coverage": 0.218, | |
| "coverage_of_all_cases": 0.218 | |
| }, | |
| { | |
| "threshold": 0.9589940905570984, | |
| "accepted": 110, | |
| "errors": 18, | |
| "risk": 0.16363636363636364, | |
| "coverage": 0.22, | |
| "coverage_of_all_cases": 0.22 | |
| }, | |
| { | |
| "threshold": 0.9583985805511475, | |
| "accepted": 111, | |
| "errors": 18, | |
| "risk": 0.16216216216216217, | |
| "coverage": 0.222, | |
| "coverage_of_all_cases": 0.222 | |
| }, | |
| { | |
| "threshold": 0.957912266254425, | |
| "accepted": 116, | |
| "errors": 19, | |
| "risk": 0.16379310344827586, | |
| "coverage": 0.232, | |
| "coverage_of_all_cases": 0.232 | |
| }, | |
| { | |
| "threshold": 0.9565674662590027, | |
| "accepted": 117, | |
| "errors": 20, | |
| "risk": 0.17094017094017094, | |
| "coverage": 0.234, | |
| "coverage_of_all_cases": 0.234 | |
| }, | |
| { | |
| "threshold": 0.9556431770324707, | |
| "accepted": 118, | |
| "errors": 20, | |
| "risk": 0.1694915254237288, | |
| "coverage": 0.236, | |
| "coverage_of_all_cases": 0.236 | |
| }, | |
| { | |
| "threshold": 0.954976499080658, | |
| "accepted": 119, | |
| "errors": 20, | |
| "risk": 0.16806722689075632, | |
| "coverage": 0.238, | |
| "coverage_of_all_cases": 0.238 | |
| }, | |
| { | |
| "threshold": 0.9534148573875427, | |
| "accepted": 120, | |
| "errors": 20, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.24, | |
| "coverage_of_all_cases": 0.24 | |
| }, | |
| { | |
| "threshold": 0.9525741338729858, | |
| "accepted": 127, | |
| "errors": 20, | |
| "risk": 0.15748031496062992, | |
| "coverage": 0.254, | |
| "coverage_of_all_cases": 0.254 | |
| }, | |
| { | |
| "threshold": 0.950524091720581, | |
| "accepted": 128, | |
| "errors": 20, | |
| "risk": 0.15625, | |
| "coverage": 0.256, | |
| "coverage_of_all_cases": 0.256 | |
| }, | |
| { | |
| "threshold": 0.9493662714958191, | |
| "accepted": 129, | |
| "errors": 20, | |
| "risk": 0.15503875968992248, | |
| "coverage": 0.258, | |
| "coverage_of_all_cases": 0.258 | |
| }, | |
| { | |
| "threshold": 0.9490231275558472, | |
| "accepted": 130, | |
| "errors": 20, | |
| "risk": 0.15384615384615385, | |
| "coverage": 0.26, | |
| "coverage_of_all_cases": 0.26 | |
| }, | |
| { | |
| "threshold": 0.9478260278701782, | |
| "accepted": 131, | |
| "errors": 20, | |
| "risk": 0.15267175572519084, | |
| "coverage": 0.262, | |
| "coverage_of_all_cases": 0.262 | |
| }, | |
| { | |
| "threshold": 0.9472090005874634, | |
| "accepted": 132, | |
| "errors": 21, | |
| "risk": 0.1590909090909091, | |
| "coverage": 0.264, | |
| "coverage_of_all_cases": 0.264 | |
| }, | |
| { | |
| "threshold": 0.9465966820716858, | |
| "accepted": 135, | |
| "errors": 22, | |
| "risk": 0.16296296296296298, | |
| "coverage": 0.27, | |
| "coverage_of_all_cases": 0.27 | |
| }, | |
| { | |
| "threshold": 0.9459109902381897, | |
| "accepted": 136, | |
| "errors": 22, | |
| "risk": 0.16176470588235295, | |
| "coverage": 0.272, | |
| "coverage_of_all_cases": 0.272 | |
| }, | |
| { | |
| "threshold": 0.9457945823669434, | |
| "accepted": 137, | |
| "errors": 22, | |
| "risk": 0.16058394160583941, | |
| "coverage": 0.274, | |
| "coverage_of_all_cases": 0.274 | |
| }, | |
| { | |
| "threshold": 0.9455951452255249, | |
| "accepted": 138, | |
| "errors": 22, | |
| "risk": 0.15942028985507245, | |
| "coverage": 0.276, | |
| "coverage_of_all_cases": 0.276 | |
| }, | |
| { | |
| "threshold": 0.9449998736381531, | |
| "accepted": 139, | |
| "errors": 22, | |
| "risk": 0.15827338129496402, | |
| "coverage": 0.278, | |
| "coverage_of_all_cases": 0.278 | |
| }, | |
| { | |
| "threshold": 0.9440900087356567, | |
| "accepted": 140, | |
| "errors": 22, | |
| "risk": 0.15714285714285714, | |
| "coverage": 0.28, | |
| "coverage_of_all_cases": 0.28 | |
| }, | |
| { | |
| "threshold": 0.9440637826919556, | |
| "accepted": 141, | |
| "errors": 22, | |
| "risk": 0.15602836879432624, | |
| "coverage": 0.282, | |
| "coverage_of_all_cases": 0.282 | |
| }, | |
| { | |
| "threshold": 0.9429488778114319, | |
| "accepted": 142, | |
| "errors": 22, | |
| "risk": 0.15492957746478872, | |
| "coverage": 0.284, | |
| "coverage_of_all_cases": 0.284 | |
| }, | |
| { | |
| "threshold": 0.9409707188606262, | |
| "accepted": 143, | |
| "errors": 22, | |
| "risk": 0.15384615384615385, | |
| "coverage": 0.286, | |
| "coverage_of_all_cases": 0.286 | |
| }, | |
| { | |
| "threshold": 0.9401869177818298, | |
| "accepted": 144, | |
| "errors": 22, | |
| "risk": 0.1527777777777778, | |
| "coverage": 0.288, | |
| "coverage_of_all_cases": 0.288 | |
| }, | |
| { | |
| "threshold": 0.9399133324623108, | |
| "accepted": 147, | |
| "errors": 23, | |
| "risk": 0.1564625850340136, | |
| "coverage": 0.294, | |
| "coverage_of_all_cases": 0.294 | |
| }, | |
| { | |
| "threshold": 0.9388473629951477, | |
| "accepted": 148, | |
| "errors": 23, | |
| "risk": 0.1554054054054054, | |
| "coverage": 0.296, | |
| "coverage_of_all_cases": 0.296 | |
| }, | |
| { | |
| "threshold": 0.938465416431427, | |
| "accepted": 149, | |
| "errors": 23, | |
| "risk": 0.15436241610738255, | |
| "coverage": 0.298, | |
| "coverage_of_all_cases": 0.298 | |
| }, | |
| { | |
| "threshold": 0.938017725944519, | |
| "accepted": 150, | |
| "errors": 24, | |
| "risk": 0.16, | |
| "coverage": 0.3, | |
| "coverage_of_all_cases": 0.3 | |
| }, | |
| { | |
| "threshold": 0.9368079304695129, | |
| "accepted": 151, | |
| "errors": 25, | |
| "risk": 0.16556291390728478, | |
| "coverage": 0.302, | |
| "coverage_of_all_cases": 0.302 | |
| }, | |
| { | |
| "threshold": 0.9365880489349365, | |
| "accepted": 152, | |
| "errors": 25, | |
| "risk": 0.16447368421052633, | |
| "coverage": 0.304, | |
| "coverage_of_all_cases": 0.304 | |
| }, | |
| { | |
| "threshold": 0.9341068267822266, | |
| "accepted": 154, | |
| "errors": 25, | |
| "risk": 0.16233766233766234, | |
| "coverage": 0.308, | |
| "coverage_of_all_cases": 0.308 | |
| }, | |
| { | |
| "threshold": 0.9332162141799927, | |
| "accepted": 155, | |
| "errors": 25, | |
| "risk": 0.16129032258064516, | |
| "coverage": 0.31, | |
| "coverage_of_all_cases": 0.31 | |
| }, | |
| { | |
| "threshold": 0.932506263256073, | |
| "accepted": 156, | |
| "errors": 26, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.312, | |
| "coverage_of_all_cases": 0.312 | |
| }, | |
| { | |
| "threshold": 0.9324532747268677, | |
| "accepted": 161, | |
| "errors": 27, | |
| "risk": 0.16770186335403728, | |
| "coverage": 0.322, | |
| "coverage_of_all_cases": 0.322 | |
| }, | |
| { | |
| "threshold": 0.928991436958313, | |
| "accepted": 162, | |
| "errors": 27, | |
| "risk": 0.16666666666666666, | |
| "coverage": 0.324, | |
| "coverage_of_all_cases": 0.324 | |
| }, | |
| { | |
| "threshold": 0.926585853099823, | |
| "accepted": 163, | |
| "errors": 28, | |
| "risk": 0.17177914110429449, | |
| "coverage": 0.326, | |
| "coverage_of_all_cases": 0.326 | |
| }, | |
| { | |
| "threshold": 0.9241418242454529, | |
| "accepted": 167, | |
| "errors": 29, | |
| "risk": 0.17365269461077845, | |
| "coverage": 0.334, | |
| "coverage_of_all_cases": 0.334 | |
| }, | |
| { | |
| "threshold": 0.9233053922653198, | |
| "accepted": 168, | |
| "errors": 29, | |
| "risk": 0.17261904761904762, | |
| "coverage": 0.336, | |
| "coverage_of_all_cases": 0.336 | |
| }, | |
| { | |
| "threshold": 0.9226970672607422, | |
| "accepted": 169, | |
| "errors": 29, | |
| "risk": 0.17159763313609466, | |
| "coverage": 0.338, | |
| "coverage_of_all_cases": 0.338 | |
| }, | |
| { | |
| "threshold": 0.9225048422813416, | |
| "accepted": 170, | |
| "errors": 29, | |
| "risk": 0.17058823529411765, | |
| "coverage": 0.34, | |
| "coverage_of_all_cases": 0.34 | |
| }, | |
| { | |
| "threshold": 0.9194818735122681, | |
| "accepted": 171, | |
| "errors": 29, | |
| "risk": 0.1695906432748538, | |
| "coverage": 0.342, | |
| "coverage_of_all_cases": 0.342 | |
| }, | |
| { | |
| "threshold": 0.9180960655212402, | |
| "accepted": 172, | |
| "errors": 30, | |
| "risk": 0.1744186046511628, | |
| "coverage": 0.344, | |
| "coverage_of_all_cases": 0.344 | |
| }, | |
| { | |
| "threshold": 0.9158769845962524, | |
| "accepted": 173, | |
| "errors": 30, | |
| "risk": 0.17341040462427745, | |
| "coverage": 0.346, | |
| "coverage_of_all_cases": 0.346 | |
| }, | |
| { | |
| "threshold": 0.9149009585380554, | |
| "accepted": 178, | |
| "errors": 31, | |
| "risk": 0.17415730337078653, | |
| "coverage": 0.356, | |
| "coverage_of_all_cases": 0.356 | |
| }, | |
| { | |
| "threshold": 0.9147506356239319, | |
| "accepted": 179, | |
| "errors": 31, | |
| "risk": 0.17318435754189945, | |
| "coverage": 0.358, | |
| "coverage_of_all_cases": 0.358 | |
| }, | |
| { | |
| "threshold": 0.9137597680091858, | |
| "accepted": 180, | |
| "errors": 31, | |
| "risk": 0.17222222222222222, | |
| "coverage": 0.36, | |
| "coverage_of_all_cases": 0.36 | |
| }, | |
| { | |
| "threshold": 0.9104833602905273, | |
| "accepted": 181, | |
| "errors": 32, | |
| "risk": 0.17679558011049723, | |
| "coverage": 0.362, | |
| "coverage_of_all_cases": 0.362 | |
| }, | |
| { | |
| "threshold": 0.908841609954834, | |
| "accepted": 182, | |
| "errors": 32, | |
| "risk": 0.17582417582417584, | |
| "coverage": 0.364, | |
| "coverage_of_all_cases": 0.364 | |
| }, | |
| { | |
| "threshold": 0.9076785445213318, | |
| "accepted": 183, | |
| "errors": 32, | |
| "risk": 0.17486338797814208, | |
| "coverage": 0.366, | |
| "coverage_of_all_cases": 0.366 | |
| }, | |
| { | |
| "threshold": 0.9068632125854492, | |
| "accepted": 184, | |
| "errors": 32, | |
| "risk": 0.17391304347826086, | |
| "coverage": 0.368, | |
| "coverage_of_all_cases": 0.368 | |
| }, | |
| { | |
| "threshold": 0.9052753448486328, | |
| "accepted": 185, | |
| "errors": 32, | |
| "risk": 0.17297297297297298, | |
| "coverage": 0.37, | |
| "coverage_of_all_cases": 0.37 | |
| }, | |
| { | |
| "threshold": 0.9046505093574524, | |
| "accepted": 189, | |
| "errors": 34, | |
| "risk": 0.17989417989417988, | |
| "coverage": 0.378, | |
| "coverage_of_all_cases": 0.378 | |
| }, | |
| { | |
| "threshold": 0.9044840335845947, | |
| "accepted": 190, | |
| "errors": 34, | |
| "risk": 0.17894736842105263, | |
| "coverage": 0.38, | |
| "coverage_of_all_cases": 0.38 | |
| }, | |
| { | |
| "threshold": 0.9031149744987488, | |
| "accepted": 191, | |
| "errors": 35, | |
| "risk": 0.18324607329842932, | |
| "coverage": 0.382, | |
| "coverage_of_all_cases": 0.382 | |
| }, | |
| { | |
| "threshold": 0.9003353118896484, | |
| "accepted": 192, | |
| "errors": 35, | |
| "risk": 0.18229166666666666, | |
| "coverage": 0.384, | |
| "coverage_of_all_cases": 0.384 | |
| }, | |
| { | |
| "threshold": 0.8998225927352905, | |
| "accepted": 194, | |
| "errors": 36, | |
| "risk": 0.18556701030927836, | |
| "coverage": 0.388, | |
| "coverage_of_all_cases": 0.388 | |
| }, | |
| { | |
| "threshold": 0.8961768746376038, | |
| "accepted": 195, | |
| "errors": 37, | |
| "risk": 0.18974358974358974, | |
| "coverage": 0.39, | |
| "coverage_of_all_cases": 0.39 | |
| }, | |
| { | |
| "threshold": 0.8957550525665283, | |
| "accepted": 196, | |
| "errors": 37, | |
| "risk": 0.18877551020408162, | |
| "coverage": 0.392, | |
| "coverage_of_all_cases": 0.392 | |
| }, | |
| { | |
| "threshold": 0.8937137126922607, | |
| "accepted": 197, | |
| "errors": 37, | |
| "risk": 0.18781725888324874, | |
| "coverage": 0.394, | |
| "coverage_of_all_cases": 0.394 | |
| }, | |
| { | |
| "threshold": 0.8933094143867493, | |
| "accepted": 202, | |
| "errors": 38, | |
| "risk": 0.18811881188118812, | |
| "coverage": 0.404, | |
| "coverage_of_all_cases": 0.404 | |
| }, | |
| { | |
| "threshold": 0.8918785452842712, | |
| "accepted": 203, | |
| "errors": 39, | |
| "risk": 0.1921182266009852, | |
| "coverage": 0.406, | |
| "coverage_of_all_cases": 0.406 | |
| }, | |
| { | |
| "threshold": 0.8910854458808899, | |
| "accepted": 204, | |
| "errors": 39, | |
| "risk": 0.19117647058823528, | |
| "coverage": 0.408, | |
| "coverage_of_all_cases": 0.408 | |
| }, | |
| { | |
| "threshold": 0.8910693526268005, | |
| "accepted": 205, | |
| "errors": 39, | |
| "risk": 0.1902439024390244, | |
| "coverage": 0.41, | |
| "coverage_of_all_cases": 0.41 | |
| }, | |
| { | |
| "threshold": 0.8883513808250427, | |
| "accepted": 206, | |
| "errors": 40, | |
| "risk": 0.1941747572815534, | |
| "coverage": 0.412, | |
| "coverage_of_all_cases": 0.412 | |
| }, | |
| { | |
| "threshold": 0.8880821466445923, | |
| "accepted": 207, | |
| "errors": 40, | |
| "risk": 0.1932367149758454, | |
| "coverage": 0.414, | |
| "coverage_of_all_cases": 0.414 | |
| }, | |
| { | |
| "threshold": 0.8871704936027527, | |
| "accepted": 208, | |
| "errors": 40, | |
| "risk": 0.19230769230769232, | |
| "coverage": 0.416, | |
| "coverage_of_all_cases": 0.416 | |
| }, | |
| { | |
| "threshold": 0.8865199089050293, | |
| "accepted": 209, | |
| "errors": 40, | |
| "risk": 0.19138755980861244, | |
| "coverage": 0.418, | |
| "coverage_of_all_cases": 0.418 | |
| }, | |
| { | |
| "threshold": 0.8864582777023315, | |
| "accepted": 210, | |
| "errors": 41, | |
| "risk": 0.19523809523809524, | |
| "coverage": 0.42, | |
| "coverage_of_all_cases": 0.42 | |
| }, | |
| { | |
| "threshold": 0.8836978673934937, | |
| "accepted": 211, | |
| "errors": 41, | |
| "risk": 0.1943127962085308, | |
| "coverage": 0.422, | |
| "coverage_of_all_cases": 0.422 | |
| }, | |
| { | |
| "threshold": 0.8831304311752319, | |
| "accepted": 212, | |
| "errors": 42, | |
| "risk": 0.19811320754716982, | |
| "coverage": 0.424, | |
| "coverage_of_all_cases": 0.424 | |
| }, | |
| { | |
| "threshold": 0.8810077905654907, | |
| "accepted": 213, | |
| "errors": 42, | |
| "risk": 0.19718309859154928, | |
| "coverage": 0.426, | |
| "coverage_of_all_cases": 0.426 | |
| }, | |
| { | |
| "threshold": 0.8807970285415649, | |
| "accepted": 215, | |
| "errors": 42, | |
| "risk": 0.19534883720930232, | |
| "coverage": 0.43, | |
| "coverage_of_all_cases": 0.43 | |
| }, | |
| { | |
| "threshold": 0.8804859519004822, | |
| "accepted": 216, | |
| "errors": 42, | |
| "risk": 0.19444444444444445, | |
| "coverage": 0.432, | |
| "coverage_of_all_cases": 0.432 | |
| }, | |
| { | |
| "threshold": 0.8782239556312561, | |
| "accepted": 217, | |
| "errors": 42, | |
| "risk": 0.1935483870967742, | |
| "coverage": 0.434, | |
| "coverage_of_all_cases": 0.434 | |
| }, | |
| { | |
| "threshold": 0.869750440120697, | |
| "accepted": 218, | |
| "errors": 43, | |
| "risk": 0.19724770642201836, | |
| "coverage": 0.436, | |
| "coverage_of_all_cases": 0.436 | |
| }, | |
| { | |
| "threshold": 0.8679274320602417, | |
| "accepted": 219, | |
| "errors": 43, | |
| "risk": 0.1963470319634703, | |
| "coverage": 0.438, | |
| "coverage_of_all_cases": 0.438 | |
| }, | |
| { | |
| "threshold": 0.8675511479377747, | |
| "accepted": 220, | |
| "errors": 43, | |
| "risk": 0.19545454545454546, | |
| "coverage": 0.44, | |
| "coverage_of_all_cases": 0.44 | |
| }, | |
| { | |
| "threshold": 0.8670357465744019, | |
| "accepted": 228, | |
| "errors": 47, | |
| "risk": 0.20614035087719298, | |
| "coverage": 0.456, | |
| "coverage_of_all_cases": 0.456 | |
| }, | |
| { | |
| "threshold": 0.8665583729743958, | |
| "accepted": 229, | |
| "errors": 47, | |
| "risk": 0.2052401746724891, | |
| "coverage": 0.458, | |
| "coverage_of_all_cases": 0.458 | |
| }, | |
| { | |
| "threshold": 0.8658868670463562, | |
| "accepted": 230, | |
| "errors": 47, | |
| "risk": 0.20434782608695654, | |
| "coverage": 0.46, | |
| "coverage_of_all_cases": 0.46 | |
| }, | |
| { | |
| "threshold": 0.8643329739570618, | |
| "accepted": 231, | |
| "errors": 47, | |
| "risk": 0.20346320346320346, | |
| "coverage": 0.462, | |
| "coverage_of_all_cases": 0.462 | |
| }, | |
| { | |
| "threshold": 0.8607219457626343, | |
| "accepted": 232, | |
| "errors": 47, | |
| "risk": 0.2025862068965517, | |
| "coverage": 0.464, | |
| "coverage_of_all_cases": 0.464 | |
| }, | |
| { | |
| "threshold": 0.8605802059173584, | |
| "accepted": 233, | |
| "errors": 47, | |
| "risk": 0.2017167381974249, | |
| "coverage": 0.466, | |
| "coverage_of_all_cases": 0.466 | |
| }, | |
| { | |
| "threshold": 0.8604625463485718, | |
| "accepted": 234, | |
| "errors": 47, | |
| "risk": 0.20085470085470086, | |
| "coverage": 0.468, | |
| "coverage_of_all_cases": 0.468 | |
| }, | |
| { | |
| "threshold": 0.8589182496070862, | |
| "accepted": 235, | |
| "errors": 47, | |
| "risk": 0.2, | |
| "coverage": 0.47, | |
| "coverage_of_all_cases": 0.47 | |
| }, | |
| { | |
| "threshold": 0.851952850818634, | |
| "accepted": 243, | |
| "errors": 51, | |
| "risk": 0.20987654320987653, | |
| "coverage": 0.486, | |
| "coverage_of_all_cases": 0.486 | |
| }, | |
| { | |
| "threshold": 0.8510570526123047, | |
| "accepted": 244, | |
| "errors": 51, | |
| "risk": 0.20901639344262296, | |
| "coverage": 0.488, | |
| "coverage_of_all_cases": 0.488 | |
| }, | |
| { | |
| "threshold": 0.8509917855262756, | |
| "accepted": 245, | |
| "errors": 51, | |
| "risk": 0.20816326530612245, | |
| "coverage": 0.49, | |
| "coverage_of_all_cases": 0.49 | |
| }, | |
| { | |
| "threshold": 0.850156843662262, | |
| "accepted": 246, | |
| "errors": 51, | |
| "risk": 0.2073170731707317, | |
| "coverage": 0.492, | |
| "coverage_of_all_cases": 0.492 | |
| }, | |
| { | |
| "threshold": 0.8483202457427979, | |
| "accepted": 247, | |
| "errors": 52, | |
| "risk": 0.21052631578947367, | |
| "coverage": 0.494, | |
| "coverage_of_all_cases": 0.494 | |
| }, | |
| { | |
| "threshold": 0.8479805588722229, | |
| "accepted": 248, | |
| "errors": 52, | |
| "risk": 0.20967741935483872, | |
| "coverage": 0.496, | |
| "coverage_of_all_cases": 0.496 | |
| }, | |
| { | |
| "threshold": 0.8475456833839417, | |
| "accepted": 249, | |
| "errors": 53, | |
| "risk": 0.21285140562248997, | |
| "coverage": 0.498, | |
| "coverage_of_all_cases": 0.498 | |
| }, | |
| { | |
| "threshold": 0.8449054956436157, | |
| "accepted": 250, | |
| "errors": 53, | |
| "risk": 0.212, | |
| "coverage": 0.5, | |
| "coverage_of_all_cases": 0.5 | |
| }, | |
| { | |
| "threshold": 0.8358612060546875, | |
| "accepted": 251, | |
| "errors": 53, | |
| "risk": 0.21115537848605578, | |
| "coverage": 0.502, | |
| "coverage_of_all_cases": 0.502 | |
| }, | |
| { | |
| "threshold": 0.8354835510253906, | |
| "accepted": 256, | |
| "errors": 53, | |
| "risk": 0.20703125, | |
| "coverage": 0.512, | |
| "coverage_of_all_cases": 0.512 | |
| }, | |
| { | |
| "threshold": 0.8353829383850098, | |
| "accepted": 257, | |
| "errors": 53, | |
| "risk": 0.20622568093385213, | |
| "coverage": 0.514, | |
| "coverage_of_all_cases": 0.514 | |
| }, | |
| { | |
| "threshold": 0.8350332379341125, | |
| "accepted": 258, | |
| "errors": 54, | |
| "risk": 0.20930232558139536, | |
| "coverage": 0.516, | |
| "coverage_of_all_cases": 0.516 | |
| }, | |
| { | |
| "threshold": 0.833845317363739, | |
| "accepted": 259, | |
| "errors": 54, | |
| "risk": 0.2084942084942085, | |
| "coverage": 0.518, | |
| "coverage_of_all_cases": 0.518 | |
| }, | |
| { | |
| "threshold": 0.8238583207130432, | |
| "accepted": 260, | |
| "errors": 54, | |
| "risk": 0.2076923076923077, | |
| "coverage": 0.52, | |
| "coverage_of_all_cases": 0.52 | |
| }, | |
| { | |
| "threshold": 0.8214952945709229, | |
| "accepted": 261, | |
| "errors": 54, | |
| "risk": 0.20689655172413793, | |
| "coverage": 0.522, | |
| "coverage_of_all_cases": 0.522 | |
| }, | |
| { | |
| "threshold": 0.8175744414329529, | |
| "accepted": 265, | |
| "errors": 55, | |
| "risk": 0.20754716981132076, | |
| "coverage": 0.53, | |
| "coverage_of_all_cases": 0.53 | |
| }, | |
| { | |
| "threshold": 0.8173485994338989, | |
| "accepted": 266, | |
| "errors": 55, | |
| "risk": 0.20676691729323307, | |
| "coverage": 0.532, | |
| "coverage_of_all_cases": 0.532 | |
| }, | |
| { | |
| "threshold": 0.8149234652519226, | |
| "accepted": 267, | |
| "errors": 55, | |
| "risk": 0.20599250936329588, | |
| "coverage": 0.534, | |
| "coverage_of_all_cases": 0.534 | |
| }, | |
| { | |
| "threshold": 0.811832070350647, | |
| "accepted": 268, | |
| "errors": 56, | |
| "risk": 0.208955223880597, | |
| "coverage": 0.536, | |
| "coverage_of_all_cases": 0.536 | |
| }, | |
| { | |
| "threshold": 0.8110701441764832, | |
| "accepted": 269, | |
| "errors": 56, | |
| "risk": 0.20817843866171004, | |
| "coverage": 0.538, | |
| "coverage_of_all_cases": 0.538 | |
| }, | |
| { | |
| "threshold": 0.8079490661621094, | |
| "accepted": 270, | |
| "errors": 56, | |
| "risk": 0.2074074074074074, | |
| "coverage": 0.54, | |
| "coverage_of_all_cases": 0.54 | |
| }, | |
| { | |
| "threshold": 0.807915449142456, | |
| "accepted": 271, | |
| "errors": 56, | |
| "risk": 0.2066420664206642, | |
| "coverage": 0.542, | |
| "coverage_of_all_cases": 0.542 | |
| }, | |
| { | |
| "threshold": 0.8055123686790466, | |
| "accepted": 272, | |
| "errors": 56, | |
| "risk": 0.20588235294117646, | |
| "coverage": 0.544, | |
| "coverage_of_all_cases": 0.544 | |
| }, | |
| { | |
| "threshold": 0.8008213043212891, | |
| "accepted": 273, | |
| "errors": 56, | |
| "risk": 0.20512820512820512, | |
| "coverage": 0.546, | |
| "coverage_of_all_cases": 0.546 | |
| }, | |
| { | |
| "threshold": 0.7982318997383118, | |
| "accepted": 274, | |
| "errors": 56, | |
| "risk": 0.20437956204379562, | |
| "coverage": 0.548, | |
| "coverage_of_all_cases": 0.548 | |
| }, | |
| { | |
| "threshold": 0.7981867790222168, | |
| "accepted": 282, | |
| "errors": 59, | |
| "risk": 0.20921985815602837, | |
| "coverage": 0.564, | |
| "coverage_of_all_cases": 0.564 | |
| }, | |
| { | |
| "threshold": 0.7979016304016113, | |
| "accepted": 283, | |
| "errors": 59, | |
| "risk": 0.20848056537102475, | |
| "coverage": 0.566, | |
| "coverage_of_all_cases": 0.566 | |
| }, | |
| { | |
| "threshold": 0.7969599366188049, | |
| "accepted": 284, | |
| "errors": 60, | |
| "risk": 0.2112676056338028, | |
| "coverage": 0.568, | |
| "coverage_of_all_cases": 0.568 | |
| }, | |
| { | |
| "threshold": 0.7958788871765137, | |
| "accepted": 285, | |
| "errors": 61, | |
| "risk": 0.21403508771929824, | |
| "coverage": 0.57, | |
| "coverage_of_all_cases": 0.57 | |
| }, | |
| { | |
| "threshold": 0.7953245639801025, | |
| "accepted": 286, | |
| "errors": 61, | |
| "risk": 0.21328671328671328, | |
| "coverage": 0.572, | |
| "coverage_of_all_cases": 0.572 | |
| }, | |
| { | |
| "threshold": 0.7924529910087585, | |
| "accepted": 287, | |
| "errors": 62, | |
| "risk": 0.21602787456445993, | |
| "coverage": 0.574, | |
| "coverage_of_all_cases": 0.574 | |
| }, | |
| { | |
| "threshold": 0.7892103791236877, | |
| "accepted": 288, | |
| "errors": 62, | |
| "risk": 0.2152777777777778, | |
| "coverage": 0.576, | |
| "coverage_of_all_cases": 0.576 | |
| }, | |
| { | |
| "threshold": 0.7869812846183777, | |
| "accepted": 289, | |
| "errors": 62, | |
| "risk": 0.21453287197231835, | |
| "coverage": 0.578, | |
| "coverage_of_all_cases": 0.578 | |
| }, | |
| { | |
| "threshold": 0.7866860032081604, | |
| "accepted": 290, | |
| "errors": 62, | |
| "risk": 0.21379310344827587, | |
| "coverage": 0.58, | |
| "coverage_of_all_cases": 0.58 | |
| }, | |
| { | |
| "threshold": 0.7853311896324158, | |
| "accepted": 291, | |
| "errors": 62, | |
| "risk": 0.21305841924398625, | |
| "coverage": 0.582, | |
| "coverage_of_all_cases": 0.582 | |
| }, | |
| { | |
| "threshold": 0.782604992389679, | |
| "accepted": 292, | |
| "errors": 63, | |
| "risk": 0.21575342465753425, | |
| "coverage": 0.584, | |
| "coverage_of_all_cases": 0.584 | |
| }, | |
| { | |
| "threshold": 0.7808530926704407, | |
| "accepted": 293, | |
| "errors": 63, | |
| "risk": 0.2150170648464164, | |
| "coverage": 0.586, | |
| "coverage_of_all_cases": 0.586 | |
| }, | |
| { | |
| "threshold": 0.7782387137413025, | |
| "accepted": 294, | |
| "errors": 63, | |
| "risk": 0.21428571428571427, | |
| "coverage": 0.588, | |
| "coverage_of_all_cases": 0.588 | |
| }, | |
| { | |
| "threshold": 0.7772998809814453, | |
| "accepted": 298, | |
| "errors": 65, | |
| "risk": 0.2181208053691275, | |
| "coverage": 0.596, | |
| "coverage_of_all_cases": 0.596 | |
| }, | |
| { | |
| "threshold": 0.775666356086731, | |
| "accepted": 299, | |
| "errors": 65, | |
| "risk": 0.21739130434782608, | |
| "coverage": 0.598, | |
| "coverage_of_all_cases": 0.598 | |
| }, | |
| { | |
| "threshold": 0.7699633836746216, | |
| "accepted": 300, | |
| "errors": 65, | |
| "risk": 0.21666666666666667, | |
| "coverage": 0.6, | |
| "coverage_of_all_cases": 0.6 | |
| }, | |
| { | |
| "threshold": 0.7661572098731995, | |
| "accepted": 301, | |
| "errors": 66, | |
| "risk": 0.21926910299003322, | |
| "coverage": 0.602, | |
| "coverage_of_all_cases": 0.602 | |
| }, | |
| { | |
| "threshold": 0.7596794962882996, | |
| "accepted": 302, | |
| "errors": 66, | |
| "risk": 0.2185430463576159, | |
| "coverage": 0.604, | |
| "coverage_of_all_cases": 0.604 | |
| }, | |
| { | |
| "threshold": 0.759253978729248, | |
| "accepted": 303, | |
| "errors": 66, | |
| "risk": 0.21782178217821782, | |
| "coverage": 0.606, | |
| "coverage_of_all_cases": 0.606 | |
| }, | |
| { | |
| "threshold": 0.7549149990081787, | |
| "accepted": 312, | |
| "errors": 72, | |
| "risk": 0.23076923076923078, | |
| "coverage": 0.624, | |
| "coverage_of_all_cases": 0.624 | |
| }, | |
| { | |
| "threshold": 0.7547596096992493, | |
| "accepted": 313, | |
| "errors": 73, | |
| "risk": 0.23322683706070288, | |
| "coverage": 0.626, | |
| "coverage_of_all_cases": 0.626 | |
| }, | |
| { | |
| "threshold": 0.7493689656257629, | |
| "accepted": 314, | |
| "errors": 73, | |
| "risk": 0.23248407643312102, | |
| "coverage": 0.628, | |
| "coverage_of_all_cases": 0.628 | |
| }, | |
| { | |
| "threshold": 0.7470859885215759, | |
| "accepted": 315, | |
| "errors": 73, | |
| "risk": 0.23174603174603176, | |
| "coverage": 0.63, | |
| "coverage_of_all_cases": 0.63 | |
| }, | |
| { | |
| "threshold": 0.7417448163032532, | |
| "accepted": 316, | |
| "errors": 74, | |
| "risk": 0.23417721518987342, | |
| "coverage": 0.632, | |
| "coverage_of_all_cases": 0.632 | |
| }, | |
| { | |
| "threshold": 0.7405944466590881, | |
| "accepted": 317, | |
| "errors": 74, | |
| "risk": 0.2334384858044164, | |
| "coverage": 0.634, | |
| "coverage_of_all_cases": 0.634 | |
| }, | |
| { | |
| "threshold": 0.7376227378845215, | |
| "accepted": 318, | |
| "errors": 74, | |
| "risk": 0.23270440251572327, | |
| "coverage": 0.636, | |
| "coverage_of_all_cases": 0.636 | |
| }, | |
| { | |
| "threshold": 0.7310585379600525, | |
| "accepted": 326, | |
| "errors": 78, | |
| "risk": 0.2392638036809816, | |
| "coverage": 0.652, | |
| "coverage_of_all_cases": 0.652 | |
| }, | |
| { | |
| "threshold": 0.7305024862289429, | |
| "accepted": 327, | |
| "errors": 78, | |
| "risk": 0.23853211009174313, | |
| "coverage": 0.654, | |
| "coverage_of_all_cases": 0.654 | |
| }, | |
| { | |
| "threshold": 0.7288795709609985, | |
| "accepted": 328, | |
| "errors": 78, | |
| "risk": 0.23780487804878048, | |
| "coverage": 0.656, | |
| "coverage_of_all_cases": 0.656 | |
| }, | |
| { | |
| "threshold": 0.7270479798316956, | |
| "accepted": 329, | |
| "errors": 78, | |
| "risk": 0.23708206686930092, | |
| "coverage": 0.658, | |
| "coverage_of_all_cases": 0.658 | |
| }, | |
| { | |
| "threshold": 0.726463794708252, | |
| "accepted": 330, | |
| "errors": 78, | |
| "risk": 0.23636363636363636, | |
| "coverage": 0.66, | |
| "coverage_of_all_cases": 0.66 | |
| }, | |
| { | |
| "threshold": 0.7228278517723083, | |
| "accepted": 331, | |
| "errors": 78, | |
| "risk": 0.23564954682779457, | |
| "coverage": 0.662, | |
| "coverage_of_all_cases": 0.662 | |
| }, | |
| { | |
| "threshold": 0.7215002775192261, | |
| "accepted": 332, | |
| "errors": 78, | |
| "risk": 0.23493975903614459, | |
| "coverage": 0.664, | |
| "coverage_of_all_cases": 0.664 | |
| }, | |
| { | |
| "threshold": 0.7171269655227661, | |
| "accepted": 333, | |
| "errors": 79, | |
| "risk": 0.23723723723723725, | |
| "coverage": 0.666, | |
| "coverage_of_all_cases": 0.666 | |
| }, | |
| { | |
| "threshold": 0.7160753011703491, | |
| "accepted": 334, | |
| "errors": 80, | |
| "risk": 0.23952095808383234, | |
| "coverage": 0.668, | |
| "coverage_of_all_cases": 0.668 | |
| }, | |
| { | |
| "threshold": 0.7132772207260132, | |
| "accepted": 335, | |
| "errors": 81, | |
| "risk": 0.2417910447761194, | |
| "coverage": 0.67, | |
| "coverage_of_all_cases": 0.67 | |
| }, | |
| { | |
| "threshold": 0.7057850360870361, | |
| "accepted": 348, | |
| "errors": 89, | |
| "risk": 0.2557471264367816, | |
| "coverage": 0.696, | |
| "coverage_of_all_cases": 0.696 | |
| }, | |
| { | |
| "threshold": 0.7039512991905212, | |
| "accepted": 349, | |
| "errors": 90, | |
| "risk": 0.25787965616045844, | |
| "coverage": 0.698, | |
| "coverage_of_all_cases": 0.698 | |
| }, | |
| { | |
| "threshold": 0.7036925554275513, | |
| "accepted": 350, | |
| "errors": 91, | |
| "risk": 0.26, | |
| "coverage": 0.7, | |
| "coverage_of_all_cases": 0.7 | |
| }, | |
| { | |
| "threshold": 0.7033140063285828, | |
| "accepted": 351, | |
| "errors": 91, | |
| "risk": 0.25925925925925924, | |
| "coverage": 0.702, | |
| "coverage_of_all_cases": 0.702 | |
| }, | |
| { | |
| "threshold": 0.699731171131134, | |
| "accepted": 352, | |
| "errors": 91, | |
| "risk": 0.2585227272727273, | |
| "coverage": 0.704, | |
| "coverage_of_all_cases": 0.704 | |
| }, | |
| { | |
| "threshold": 0.6969991326332092, | |
| "accepted": 353, | |
| "errors": 91, | |
| "risk": 0.2577903682719547, | |
| "coverage": 0.706, | |
| "coverage_of_all_cases": 0.706 | |
| }, | |
| { | |
| "threshold": 0.6961797475814819, | |
| "accepted": 354, | |
| "errors": 92, | |
| "risk": 0.2598870056497175, | |
| "coverage": 0.708, | |
| "coverage_of_all_cases": 0.708 | |
| }, | |
| { | |
| "threshold": 0.6951413154602051, | |
| "accepted": 355, | |
| "errors": 92, | |
| "risk": 0.2591549295774648, | |
| "coverage": 0.71, | |
| "coverage_of_all_cases": 0.71 | |
| }, | |
| { | |
| "threshold": 0.6927552819252014, | |
| "accepted": 356, | |
| "errors": 93, | |
| "risk": 0.2612359550561798, | |
| "coverage": 0.712, | |
| "coverage_of_all_cases": 0.712 | |
| }, | |
| { | |
| "threshold": 0.6860982179641724, | |
| "accepted": 357, | |
| "errors": 93, | |
| "risk": 0.2605042016806723, | |
| "coverage": 0.714, | |
| "coverage_of_all_cases": 0.714 | |
| }, | |
| { | |
| "threshold": 0.6848007440567017, | |
| "accepted": 358, | |
| "errors": 93, | |
| "risk": 0.25977653631284914, | |
| "coverage": 0.716, | |
| "coverage_of_all_cases": 0.716 | |
| }, | |
| { | |
| "threshold": 0.6818263530731201, | |
| "accepted": 359, | |
| "errors": 94, | |
| "risk": 0.2618384401114206, | |
| "coverage": 0.718, | |
| "coverage_of_all_cases": 0.718 | |
| }, | |
| { | |
| "threshold": 0.6798250675201416, | |
| "accepted": 360, | |
| "errors": 95, | |
| "risk": 0.2638888888888889, | |
| "coverage": 0.72, | |
| "coverage_of_all_cases": 0.72 | |
| }, | |
| { | |
| "threshold": 0.6791787147521973, | |
| "accepted": 364, | |
| "errors": 97, | |
| "risk": 0.2664835164835165, | |
| "coverage": 0.728, | |
| "coverage_of_all_cases": 0.728 | |
| }, | |
| { | |
| "threshold": 0.678562581539154, | |
| "accepted": 365, | |
| "errors": 97, | |
| "risk": 0.26575342465753427, | |
| "coverage": 0.73, | |
| "coverage_of_all_cases": 0.73 | |
| }, | |
| { | |
| "threshold": 0.6783665418624878, | |
| "accepted": 366, | |
| "errors": 97, | |
| "risk": 0.2650273224043716, | |
| "coverage": 0.732, | |
| "coverage_of_all_cases": 0.732 | |
| }, | |
| { | |
| "threshold": 0.6777920126914978, | |
| "accepted": 367, | |
| "errors": 97, | |
| "risk": 0.26430517711171664, | |
| "coverage": 0.734, | |
| "coverage_of_all_cases": 0.734 | |
| }, | |
| { | |
| "threshold": 0.6759727597236633, | |
| "accepted": 368, | |
| "errors": 97, | |
| "risk": 0.26358695652173914, | |
| "coverage": 0.736, | |
| "coverage_of_all_cases": 0.736 | |
| }, | |
| { | |
| "threshold": 0.6735917329788208, | |
| "accepted": 369, | |
| "errors": 98, | |
| "risk": 0.26558265582655827, | |
| "coverage": 0.738, | |
| "coverage_of_all_cases": 0.738 | |
| }, | |
| { | |
| "threshold": 0.6723964214324951, | |
| "accepted": 370, | |
| "errors": 98, | |
| "risk": 0.2648648648648649, | |
| "coverage": 0.74, | |
| "coverage_of_all_cases": 0.74 | |
| }, | |
| { | |
| "threshold": 0.658189594745636, | |
| "accepted": 371, | |
| "errors": 99, | |
| "risk": 0.2668463611859838, | |
| "coverage": 0.742, | |
| "coverage_of_all_cases": 0.742 | |
| }, | |
| { | |
| "threshold": 0.6521506905555725, | |
| "accepted": 372, | |
| "errors": 100, | |
| "risk": 0.26881720430107525, | |
| "coverage": 0.744, | |
| "coverage_of_all_cases": 0.744 | |
| }, | |
| { | |
| "threshold": 0.6515308022499084, | |
| "accepted": 373, | |
| "errors": 100, | |
| "risk": 0.2680965147453083, | |
| "coverage": 0.746, | |
| "coverage_of_all_cases": 0.746 | |
| }, | |
| { | |
| "threshold": 0.6513549089431763, | |
| "accepted": 384, | |
| "errors": 105, | |
| "risk": 0.2734375, | |
| "coverage": 0.768, | |
| "coverage_of_all_cases": 0.768 | |
| }, | |
| { | |
| "threshold": 0.6502076983451843, | |
| "accepted": 385, | |
| "errors": 106, | |
| "risk": 0.2753246753246753, | |
| "coverage": 0.77, | |
| "coverage_of_all_cases": 0.77 | |
| }, | |
| { | |
| "threshold": 0.648850679397583, | |
| "accepted": 386, | |
| "errors": 107, | |
| "risk": 0.2772020725388601, | |
| "coverage": 0.772, | |
| "coverage_of_all_cases": 0.772 | |
| }, | |
| { | |
| "threshold": 0.6476922631263733, | |
| "accepted": 387, | |
| "errors": 108, | |
| "risk": 0.27906976744186046, | |
| "coverage": 0.774, | |
| "coverage_of_all_cases": 0.774 | |
| }, | |
| { | |
| "threshold": 0.6469538807868958, | |
| "accepted": 388, | |
| "errors": 108, | |
| "risk": 0.27835051546391754, | |
| "coverage": 0.776, | |
| "coverage_of_all_cases": 0.776 | |
| }, | |
| { | |
| "threshold": 0.6428712010383606, | |
| "accepted": 389, | |
| "errors": 109, | |
| "risk": 0.2802056555269923, | |
| "coverage": 0.778, | |
| "coverage_of_all_cases": 0.778 | |
| }, | |
| { | |
| "threshold": 0.6399102210998535, | |
| "accepted": 390, | |
| "errors": 110, | |
| "risk": 0.28205128205128205, | |
| "coverage": 0.78, | |
| "coverage_of_all_cases": 0.78 | |
| }, | |
| { | |
| "threshold": 0.6349480748176575, | |
| "accepted": 391, | |
| "errors": 110, | |
| "risk": 0.2813299232736573, | |
| "coverage": 0.782, | |
| "coverage_of_all_cases": 0.782 | |
| }, | |
| { | |
| "threshold": 0.6336116194725037, | |
| "accepted": 392, | |
| "errors": 110, | |
| "risk": 0.28061224489795916, | |
| "coverage": 0.784, | |
| "coverage_of_all_cases": 0.784 | |
| }, | |
| { | |
| "threshold": 0.6309390068054199, | |
| "accepted": 393, | |
| "errors": 110, | |
| "risk": 0.27989821882951654, | |
| "coverage": 0.786, | |
| "coverage_of_all_cases": 0.786 | |
| }, | |
| { | |
| "threshold": 0.6286793947219849, | |
| "accepted": 394, | |
| "errors": 110, | |
| "risk": 0.27918781725888325, | |
| "coverage": 0.788, | |
| "coverage_of_all_cases": 0.788 | |
| }, | |
| { | |
| "threshold": 0.6278160214424133, | |
| "accepted": 395, | |
| "errors": 111, | |
| "risk": 0.2810126582278481, | |
| "coverage": 0.79, | |
| "coverage_of_all_cases": 0.79 | |
| }, | |
| { | |
| "threshold": 0.622459352016449, | |
| "accepted": 406, | |
| "errors": 113, | |
| "risk": 0.27832512315270935, | |
| "coverage": 0.812, | |
| "coverage_of_all_cases": 0.812 | |
| }, | |
| { | |
| "threshold": 0.6215793490409851, | |
| "accepted": 407, | |
| "errors": 113, | |
| "risk": 0.27764127764127766, | |
| "coverage": 0.814, | |
| "coverage_of_all_cases": 0.814 | |
| }, | |
| { | |
| "threshold": 0.620661735534668, | |
| "accepted": 408, | |
| "errors": 113, | |
| "risk": 0.2769607843137255, | |
| "coverage": 0.816, | |
| "coverage_of_all_cases": 0.816 | |
| }, | |
| { | |
| "threshold": 0.6155123114585876, | |
| "accepted": 409, | |
| "errors": 113, | |
| "risk": 0.2762836185819071, | |
| "coverage": 0.818, | |
| "coverage_of_all_cases": 0.818 | |
| }, | |
| { | |
| "threshold": 0.6044544577598572, | |
| "accepted": 411, | |
| "errors": 114, | |
| "risk": 0.2773722627737226, | |
| "coverage": 0.822, | |
| "coverage_of_all_cases": 0.822 | |
| }, | |
| { | |
| "threshold": 0.6023641228675842, | |
| "accepted": 412, | |
| "errors": 114, | |
| "risk": 0.2766990291262136, | |
| "coverage": 0.824, | |
| "coverage_of_all_cases": 0.824 | |
| }, | |
| { | |
| "threshold": 0.6013421416282654, | |
| "accepted": 414, | |
| "errors": 115, | |
| "risk": 0.2777777777777778, | |
| "coverage": 0.828, | |
| "coverage_of_all_cases": 0.828 | |
| }, | |
| { | |
| "threshold": 0.5997083187103271, | |
| "accepted": 415, | |
| "errors": 115, | |
| "risk": 0.27710843373493976, | |
| "coverage": 0.83, | |
| "coverage_of_all_cases": 0.83 | |
| }, | |
| { | |
| "threshold": 0.5985885262489319, | |
| "accepted": 416, | |
| "errors": 115, | |
| "risk": 0.2764423076923077, | |
| "coverage": 0.832, | |
| "coverage_of_all_cases": 0.832 | |
| }, | |
| { | |
| "threshold": 0.5926666259765625, | |
| "accepted": 425, | |
| "errors": 120, | |
| "risk": 0.2823529411764706, | |
| "coverage": 0.85, | |
| "coverage_of_all_cases": 0.85 | |
| }, | |
| { | |
| "threshold": 0.5924387574195862, | |
| "accepted": 426, | |
| "errors": 121, | |
| "risk": 0.284037558685446, | |
| "coverage": 0.852, | |
| "coverage_of_all_cases": 0.852 | |
| }, | |
| { | |
| "threshold": 0.5898645520210266, | |
| "accepted": 427, | |
| "errors": 122, | |
| "risk": 0.2857142857142857, | |
| "coverage": 0.854, | |
| "coverage_of_all_cases": 0.854 | |
| }, | |
| { | |
| "threshold": 0.5874818563461304, | |
| "accepted": 428, | |
| "errors": 122, | |
| "risk": 0.2850467289719626, | |
| "coverage": 0.856, | |
| "coverage_of_all_cases": 0.856 | |
| }, | |
| { | |
| "threshold": 0.5870726108551025, | |
| "accepted": 429, | |
| "errors": 122, | |
| "risk": 0.28438228438228436, | |
| "coverage": 0.858, | |
| "coverage_of_all_cases": 0.858 | |
| }, | |
| { | |
| "threshold": 0.5838938355445862, | |
| "accepted": 430, | |
| "errors": 122, | |
| "risk": 0.2837209302325581, | |
| "coverage": 0.86, | |
| "coverage_of_all_cases": 0.86 | |
| }, | |
| { | |
| "threshold": 0.5776252746582031, | |
| "accepted": 431, | |
| "errors": 123, | |
| "risk": 0.2853828306264501, | |
| "coverage": 0.862, | |
| "coverage_of_all_cases": 0.862 | |
| }, | |
| { | |
| "threshold": 0.577561616897583, | |
| "accepted": 432, | |
| "errors": 123, | |
| "risk": 0.2847222222222222, | |
| "coverage": 0.864, | |
| "coverage_of_all_cases": 0.864 | |
| }, | |
| { | |
| "threshold": 0.5750440359115601, | |
| "accepted": 433, | |
| "errors": 124, | |
| "risk": 0.2863741339491917, | |
| "coverage": 0.866, | |
| "coverage_of_all_cases": 0.866 | |
| }, | |
| { | |
| "threshold": 0.5734913945198059, | |
| "accepted": 434, | |
| "errors": 125, | |
| "risk": 0.2880184331797235, | |
| "coverage": 0.868, | |
| "coverage_of_all_cases": 0.868 | |
| }, | |
| { | |
| "threshold": 0.5728051662445068, | |
| "accepted": 435, | |
| "errors": 126, | |
| "risk": 0.2896551724137931, | |
| "coverage": 0.87, | |
| "coverage_of_all_cases": 0.87 | |
| }, | |
| { | |
| "threshold": 0.5712754130363464, | |
| "accepted": 436, | |
| "errors": 127, | |
| "risk": 0.29128440366972475, | |
| "coverage": 0.872, | |
| "coverage_of_all_cases": 0.872 | |
| }, | |
| { | |
| "threshold": 0.5682692527770996, | |
| "accepted": 437, | |
| "errors": 128, | |
| "risk": 0.2929061784897025, | |
| "coverage": 0.874, | |
| "coverage_of_all_cases": 0.874 | |
| }, | |
| { | |
| "threshold": 0.5667107701301575, | |
| "accepted": 438, | |
| "errors": 129, | |
| "risk": 0.2945205479452055, | |
| "coverage": 0.876, | |
| "coverage_of_all_cases": 0.876 | |
| }, | |
| { | |
| "threshold": 0.562176525592804, | |
| "accepted": 441, | |
| "errors": 130, | |
| "risk": 0.2947845804988662, | |
| "coverage": 0.882, | |
| "coverage_of_all_cases": 0.882 | |
| }, | |
| { | |
| "threshold": 0.5617018938064575, | |
| "accepted": 442, | |
| "errors": 130, | |
| "risk": 0.29411764705882354, | |
| "coverage": 0.884, | |
| "coverage_of_all_cases": 0.884 | |
| }, | |
| { | |
| "threshold": 0.5617015957832336, | |
| "accepted": 443, | |
| "errors": 130, | |
| "risk": 0.29345372460496616, | |
| "coverage": 0.886, | |
| "coverage_of_all_cases": 0.886 | |
| }, | |
| { | |
| "threshold": 0.5521643757820129, | |
| "accepted": 444, | |
| "errors": 131, | |
| "risk": 0.29504504504504503, | |
| "coverage": 0.888, | |
| "coverage_of_all_cases": 0.888 | |
| }, | |
| { | |
| "threshold": 0.5486593246459961, | |
| "accepted": 445, | |
| "errors": 132, | |
| "risk": 0.2966292134831461, | |
| "coverage": 0.89, | |
| "coverage_of_all_cases": 0.89 | |
| }, | |
| { | |
| "threshold": 0.5486252903938293, | |
| "accepted": 446, | |
| "errors": 132, | |
| "risk": 0.29596412556053814, | |
| "coverage": 0.892, | |
| "coverage_of_all_cases": 0.892 | |
| }, | |
| { | |
| "threshold": 0.5346283316612244, | |
| "accepted": 447, | |
| "errors": 133, | |
| "risk": 0.2975391498881432, | |
| "coverage": 0.894, | |
| "coverage_of_all_cases": 0.894 | |
| }, | |
| { | |
| "threshold": 0.531209409236908, | |
| "accepted": 458, | |
| "errors": 140, | |
| "risk": 0.3056768558951965, | |
| "coverage": 0.916, | |
| "coverage_of_all_cases": 0.916 | |
| }, | |
| { | |
| "threshold": 0.5295794010162354, | |
| "accepted": 459, | |
| "errors": 140, | |
| "risk": 0.30501089324618735, | |
| "coverage": 0.918, | |
| "coverage_of_all_cases": 0.918 | |
| }, | |
| { | |
| "threshold": 0.5293165445327759, | |
| "accepted": 460, | |
| "errors": 141, | |
| "risk": 0.3065217391304348, | |
| "coverage": 0.92, | |
| "coverage_of_all_cases": 0.92 | |
| }, | |
| { | |
| "threshold": 0.5283081531524658, | |
| "accepted": 461, | |
| "errors": 141, | |
| "risk": 0.30585683297180044, | |
| "coverage": 0.922, | |
| "coverage_of_all_cases": 0.922 | |
| }, | |
| { | |
| "threshold": 0.5234452486038208, | |
| "accepted": 463, | |
| "errors": 143, | |
| "risk": 0.30885529157667385, | |
| "coverage": 0.926, | |
| "coverage_of_all_cases": 0.926 | |
| }, | |
| { | |
| "threshold": 0.5183353424072266, | |
| "accepted": 464, | |
| "errors": 143, | |
| "risk": 0.3081896551724138, | |
| "coverage": 0.928, | |
| "coverage_of_all_cases": 0.928 | |
| }, | |
| { | |
| "threshold": 0.5159762501716614, | |
| "accepted": 465, | |
| "errors": 144, | |
| "risk": 0.3096774193548387, | |
| "coverage": 0.93, | |
| "coverage_of_all_cases": 0.93 | |
| }, | |
| { | |
| "threshold": 0.5142093896865845, | |
| "accepted": 466, | |
| "errors": 145, | |
| "risk": 0.3111587982832618, | |
| "coverage": 0.932, | |
| "coverage_of_all_cases": 0.932 | |
| }, | |
| { | |
| "threshold": 0.5028401017189026, | |
| "accepted": 467, | |
| "errors": 145, | |
| "risk": 0.31049250535331907, | |
| "coverage": 0.934, | |
| "coverage_of_all_cases": 0.934 | |
| }, | |
| { | |
| "threshold": 0.5, | |
| "accepted": 468, | |
| "errors": 145, | |
| "risk": 0.30982905982905984, | |
| "coverage": 0.936, | |
| "coverage_of_all_cases": 0.936 | |
| }, | |
| { | |
| "threshold": 0.4995180368423462, | |
| "accepted": 469, | |
| "errors": 146, | |
| "risk": 0.31130063965884863, | |
| "coverage": 0.938, | |
| "coverage_of_all_cases": 0.938 | |
| }, | |
| { | |
| "threshold": 0.4963313341140747, | |
| "accepted": 470, | |
| "errors": 146, | |
| "risk": 0.31063829787234043, | |
| "coverage": 0.94, | |
| "coverage_of_all_cases": 0.94 | |
| }, | |
| { | |
| "threshold": 0.4951087534427643, | |
| "accepted": 471, | |
| "errors": 146, | |
| "risk": 0.3099787685774947, | |
| "coverage": 0.942, | |
| "coverage_of_all_cases": 0.942 | |
| }, | |
| { | |
| "threshold": 0.48796969652175903, | |
| "accepted": 472, | |
| "errors": 146, | |
| "risk": 0.3093220338983051, | |
| "coverage": 0.944, | |
| "coverage_of_all_cases": 0.944 | |
| }, | |
| { | |
| "threshold": 0.4849589169025421, | |
| "accepted": 473, | |
| "errors": 146, | |
| "risk": 0.3086680761099366, | |
| "coverage": 0.946, | |
| "coverage_of_all_cases": 0.946 | |
| }, | |
| { | |
| "threshold": 0.47835803031921387, | |
| "accepted": 474, | |
| "errors": 147, | |
| "risk": 0.310126582278481, | |
| "coverage": 0.948, | |
| "coverage_of_all_cases": 0.948 | |
| }, | |
| { | |
| "threshold": 0.4711873531341553, | |
| "accepted": 475, | |
| "errors": 147, | |
| "risk": 0.3094736842105263, | |
| "coverage": 0.95, | |
| "coverage_of_all_cases": 0.95 | |
| }, | |
| { | |
| "threshold": 0.4707532823085785, | |
| "accepted": 476, | |
| "errors": 148, | |
| "risk": 0.31092436974789917, | |
| "coverage": 0.952, | |
| "coverage_of_all_cases": 0.952 | |
| }, | |
| { | |
| "threshold": 0.4652557671070099, | |
| "accepted": 477, | |
| "errors": 149, | |
| "risk": 0.31236897274633124, | |
| "coverage": 0.954, | |
| "coverage_of_all_cases": 0.954 | |
| }, | |
| { | |
| "threshold": 0.4648013710975647, | |
| "accepted": 478, | |
| "errors": 150, | |
| "risk": 0.3138075313807531, | |
| "coverage": 0.956, | |
| "coverage_of_all_cases": 0.956 | |
| }, | |
| { | |
| "threshold": 0.4643915891647339, | |
| "accepted": 479, | |
| "errors": 150, | |
| "risk": 0.31315240083507306, | |
| "coverage": 0.958, | |
| "coverage_of_all_cases": 0.958 | |
| }, | |
| { | |
| "threshold": 0.46136876940727234, | |
| "accepted": 480, | |
| "errors": 151, | |
| "risk": 0.3145833333333333, | |
| "coverage": 0.96, | |
| "coverage_of_all_cases": 0.96 | |
| }, | |
| { | |
| "threshold": 0.4602774381637573, | |
| "accepted": 481, | |
| "errors": 152, | |
| "risk": 0.316008316008316, | |
| "coverage": 0.962, | |
| "coverage_of_all_cases": 0.962 | |
| }, | |
| { | |
| "threshold": 0.45307305455207825, | |
| "accepted": 482, | |
| "errors": 152, | |
| "risk": 0.3153526970954357, | |
| "coverage": 0.964, | |
| "coverage_of_all_cases": 0.964 | |
| }, | |
| { | |
| "threshold": 0.45186275243759155, | |
| "accepted": 483, | |
| "errors": 152, | |
| "risk": 0.3146997929606625, | |
| "coverage": 0.966, | |
| "coverage_of_all_cases": 0.966 | |
| }, | |
| { | |
| "threshold": 0.4499334692955017, | |
| "accepted": 484, | |
| "errors": 152, | |
| "risk": 0.3140495867768595, | |
| "coverage": 0.968, | |
| "coverage_of_all_cases": 0.968 | |
| }, | |
| { | |
| "threshold": 0.44951876997947693, | |
| "accepted": 485, | |
| "errors": 152, | |
| "risk": 0.3134020618556701, | |
| "coverage": 0.97, | |
| "coverage_of_all_cases": 0.97 | |
| }, | |
| { | |
| "threshold": 0.4395256042480469, | |
| "accepted": 486, | |
| "errors": 152, | |
| "risk": 0.31275720164609055, | |
| "coverage": 0.972, | |
| "coverage_of_all_cases": 0.972 | |
| }, | |
| { | |
| "threshold": 0.4381036162376404, | |
| "accepted": 487, | |
| "errors": 153, | |
| "risk": 0.3141683778234086, | |
| "coverage": 0.974, | |
| "coverage_of_all_cases": 0.974 | |
| }, | |
| { | |
| "threshold": 0.43734875321388245, | |
| "accepted": 488, | |
| "errors": 153, | |
| "risk": 0.3135245901639344, | |
| "coverage": 0.976, | |
| "coverage_of_all_cases": 0.976 | |
| }, | |
| { | |
| "threshold": 0.4192289710044861, | |
| "accepted": 489, | |
| "errors": 153, | |
| "risk": 0.3128834355828221, | |
| "coverage": 0.978, | |
| "coverage_of_all_cases": 0.978 | |
| }, | |
| { | |
| "threshold": 0.4056156873703003, | |
| "accepted": 490, | |
| "errors": 154, | |
| "risk": 0.3142857142857143, | |
| "coverage": 0.98, | |
| "coverage_of_all_cases": 0.98 | |
| }, | |
| { | |
| "threshold": 0.405500203371048, | |
| "accepted": 491, | |
| "errors": 155, | |
| "risk": 0.31568228105906315, | |
| "coverage": 0.982, | |
| "coverage_of_all_cases": 0.982 | |
| }, | |
| { | |
| "threshold": 0.40176334977149963, | |
| "accepted": 492, | |
| "errors": 155, | |
| "risk": 0.3150406504065041, | |
| "coverage": 0.984, | |
| "coverage_of_all_cases": 0.984 | |
| }, | |
| { | |
| "threshold": 0.3933780789375305, | |
| "accepted": 493, | |
| "errors": 155, | |
| "risk": 0.3144016227180527, | |
| "coverage": 0.986, | |
| "coverage_of_all_cases": 0.986 | |
| }, | |
| { | |
| "threshold": 0.3836517333984375, | |
| "accepted": 494, | |
| "errors": 155, | |
| "risk": 0.31376518218623484, | |
| "coverage": 0.988, | |
| "coverage_of_all_cases": 0.988 | |
| }, | |
| { | |
| "threshold": 0.3728675842285156, | |
| "accepted": 495, | |
| "errors": 155, | |
| "risk": 0.31313131313131315, | |
| "coverage": 0.99, | |
| "coverage_of_all_cases": 0.99 | |
| }, | |
| { | |
| "threshold": 0.35986748337745667, | |
| "accepted": 497, | |
| "errors": 156, | |
| "risk": 0.31388329979879276, | |
| "coverage": 0.994, | |
| "coverage_of_all_cases": 0.994 | |
| }, | |
| { | |
| "threshold": 0.3014598786830902, | |
| "accepted": 498, | |
| "errors": 157, | |
| "risk": 0.3152610441767068, | |
| "coverage": 0.996, | |
| "coverage_of_all_cases": 0.996 | |
| }, | |
| { | |
| "threshold": 0.2975444197654724, | |
| "accepted": 499, | |
| "errors": 158, | |
| "risk": 0.3166332665330661, | |
| "coverage": 0.998, | |
| "coverage_of_all_cases": 0.998 | |
| }, | |
| { | |
| "threshold": 0.2939724028110504, | |
| "accepted": 500, | |
| "errors": 159, | |
| "risk": 0.318, | |
| "coverage": 1.0, | |
| "coverage_of_all_cases": 1.0 | |
| } | |
| ] | |
| }, | |
| "probability_incomplete": 0, | |
| "latency_ms": { | |
| "count": 500, | |
| "mean": 13.859870177722769, | |
| "p50": 13.106927995977458, | |
| "p95": 13.293078549031634, | |
| "min": 12.791913992259651, | |
| "max": 380.5269500007853 | |
| }, | |
| "wall_latency_ms": { | |
| "count": 500, | |
| "mean": 15.610583784407936, | |
| "p50": 14.08684750640532, | |
| "p95": 18.031452509603696, | |
| "min": 13.394960988080129, | |
| "max": 398.8930360064842 | |
| }, | |
| "input_tokens": { | |
| "count": 500, | |
| "mean": 309.888, | |
| "p50": 202.0, | |
| "p95": 888.1499999999999, | |
| "min": 108.0, | |
| "max": 1631.0 | |
| }, | |
| "state_characters": { | |
| "count": 500, | |
| "mean": 571.486, | |
| "p50": 199.5, | |
| "p95": 2825.1, | |
| "min": 10.0, | |
| "max": 6317.0 | |
| }, | |
| "notes": [ | |
| "accuracy_all counts errors and skips as incorrect", | |
| "accuracy_attempted and family macro count errors as wrong and exclude intentional skips", | |
| "family defaults to source; latency_ms is local forward-pass or hosted HTTP time", | |
| "wall_latency_ms includes per-record scorer preprocessing and inference; no warmup excluded", | |
| "F1 uses semantic option keys, never shuffled answer letters", | |
| "Probability metrics only include explicitly complete distributions" | |
| ] | |
| }, | |
| "qwen": { | |
| "count": 500, | |
| "attempted": 500, | |
| "scored": 500, | |
| "errors": 0, | |
| "skipped": 0, | |
| "accuracy_all": 0.562, | |
| "accuracy_attempted": 0.562, | |
| "accuracy_scored": 0.562, | |
| "accuracy_family_macro": 0.562, | |
| "accuracy_by_family": { | |
| "clinc150": 0.67, | |
| "go_emotions": 0.52, | |
| "helpsteer2": 0.63, | |
| "paws": 0.44, | |
| "vitaminc": 0.55 | |
| }, | |
| "by_source": { | |
| "clinc150": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.67, | |
| "accuracy_attempted": 0.67, | |
| "macro_f1_scored": 0.5351598173515981, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "go_emotions": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.52, | |
| "accuracy_attempted": 0.52, | |
| "macro_f1_scored": 0.5169082125603865, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "helpsteer2": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.63, | |
| "accuracy_attempted": 0.63, | |
| "macro_f1_scored": 0.22059950416948387, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "paws": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.44, | |
| "accuracy_attempted": 0.44, | |
| "macro_f1_scored": 0.34548854604955587, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "vitaminc": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.55, | |
| "accuracy_attempted": 0.55, | |
| "macro_f1_scored": 0.23655913978494625, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| } | |
| }, | |
| "probability_metrics": { | |
| "count": 500, | |
| "brier_multiclass_sum": 0.6494455165714786, | |
| "nll": 1.3442728106100041, | |
| "infinite_nll_cases": 0, | |
| "ece": 0.21848675349354746, | |
| "ece_equal_width_bins": 15, | |
| "aurc": 0.3719029798279875, | |
| "coverage_at_error": { | |
| "0.01": 0.02, | |
| "0.05": 0.02, | |
| "0.1": 0.026 | |
| }, | |
| "risk_coverage_note": "Empirical diagnostic, not a held-out error guarantee; whole ties accepted.", | |
| "risk_coverage": [ | |
| { | |
| "threshold": 0.9988589286804199, | |
| "accepted": 1, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.002, | |
| "coverage_of_all_cases": 0.002 | |
| }, | |
| { | |
| "threshold": 0.9988552331924438, | |
| "accepted": 2, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.004, | |
| "coverage_of_all_cases": 0.004 | |
| }, | |
| { | |
| "threshold": 0.9983415603637695, | |
| "accepted": 3, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.006, | |
| "coverage_of_all_cases": 0.006 | |
| }, | |
| { | |
| "threshold": 0.9982959628105164, | |
| "accepted": 4, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.008, | |
| "coverage_of_all_cases": 0.008 | |
| }, | |
| { | |
| "threshold": 0.9981414079666138, | |
| "accepted": 5, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.01, | |
| "coverage_of_all_cases": 0.01 | |
| }, | |
| { | |
| "threshold": 0.9981153011322021, | |
| "accepted": 6, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.012, | |
| "coverage_of_all_cases": 0.012 | |
| }, | |
| { | |
| "threshold": 0.9978705644607544, | |
| "accepted": 7, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.014, | |
| "coverage_of_all_cases": 0.014 | |
| }, | |
| { | |
| "threshold": 0.9977912902832031, | |
| "accepted": 8, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.016, | |
| "coverage_of_all_cases": 0.016 | |
| }, | |
| { | |
| "threshold": 0.9973316192626953, | |
| "accepted": 9, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.018, | |
| "coverage_of_all_cases": 0.018 | |
| }, | |
| { | |
| "threshold": 0.9970990419387817, | |
| "accepted": 10, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.02, | |
| "coverage_of_all_cases": 0.02 | |
| }, | |
| { | |
| "threshold": 0.9967895150184631, | |
| "accepted": 11, | |
| "errors": 1, | |
| "risk": 0.09090909090909091, | |
| "coverage": 0.022, | |
| "coverage_of_all_cases": 0.022 | |
| }, | |
| { | |
| "threshold": 0.9964494705200195, | |
| "accepted": 12, | |
| "errors": 1, | |
| "risk": 0.08333333333333333, | |
| "coverage": 0.024, | |
| "coverage_of_all_cases": 0.024 | |
| }, | |
| { | |
| "threshold": 0.9963995218276978, | |
| "accepted": 13, | |
| "errors": 1, | |
| "risk": 0.07692307692307693, | |
| "coverage": 0.026, | |
| "coverage_of_all_cases": 0.026 | |
| }, | |
| { | |
| "threshold": 0.996392548084259, | |
| "accepted": 14, | |
| "errors": 2, | |
| "risk": 0.14285714285714285, | |
| "coverage": 0.028, | |
| "coverage_of_all_cases": 0.028 | |
| }, | |
| { | |
| "threshold": 0.9961221814155579, | |
| "accepted": 15, | |
| "errors": 3, | |
| "risk": 0.2, | |
| "coverage": 0.03, | |
| "coverage_of_all_cases": 0.03 | |
| }, | |
| { | |
| "threshold": 0.9960734844207764, | |
| "accepted": 16, | |
| "errors": 3, | |
| "risk": 0.1875, | |
| "coverage": 0.032, | |
| "coverage_of_all_cases": 0.032 | |
| }, | |
| { | |
| "threshold": 0.9959220886230469, | |
| "accepted": 17, | |
| "errors": 3, | |
| "risk": 0.17647058823529413, | |
| "coverage": 0.034, | |
| "coverage_of_all_cases": 0.034 | |
| }, | |
| { | |
| "threshold": 0.99578458070755, | |
| "accepted": 19, | |
| "errors": 5, | |
| "risk": 0.2631578947368421, | |
| "coverage": 0.038, | |
| "coverage_of_all_cases": 0.038 | |
| }, | |
| { | |
| "threshold": 0.9957062602043152, | |
| "accepted": 20, | |
| "errors": 5, | |
| "risk": 0.25, | |
| "coverage": 0.04, | |
| "coverage_of_all_cases": 0.04 | |
| }, | |
| { | |
| "threshold": 0.9956652522087097, | |
| "accepted": 21, | |
| "errors": 6, | |
| "risk": 0.2857142857142857, | |
| "coverage": 0.042, | |
| "coverage_of_all_cases": 0.042 | |
| }, | |
| { | |
| "threshold": 0.9956440925598145, | |
| "accepted": 22, | |
| "errors": 6, | |
| "risk": 0.2727272727272727, | |
| "coverage": 0.044, | |
| "coverage_of_all_cases": 0.044 | |
| }, | |
| { | |
| "threshold": 0.9953904151916504, | |
| "accepted": 24, | |
| "errors": 7, | |
| "risk": 0.2916666666666667, | |
| "coverage": 0.048, | |
| "coverage_of_all_cases": 0.048 | |
| }, | |
| { | |
| "threshold": 0.9951777458190918, | |
| "accepted": 25, | |
| "errors": 7, | |
| "risk": 0.28, | |
| "coverage": 0.05, | |
| "coverage_of_all_cases": 0.05 | |
| }, | |
| { | |
| "threshold": 0.9951322674751282, | |
| "accepted": 27, | |
| "errors": 7, | |
| "risk": 0.25925925925925924, | |
| "coverage": 0.054, | |
| "coverage_of_all_cases": 0.054 | |
| }, | |
| { | |
| "threshold": 0.9949070811271667, | |
| "accepted": 28, | |
| "errors": 7, | |
| "risk": 0.25, | |
| "coverage": 0.056, | |
| "coverage_of_all_cases": 0.056 | |
| }, | |
| { | |
| "threshold": 0.9948720335960388, | |
| "accepted": 29, | |
| "errors": 7, | |
| "risk": 0.2413793103448276, | |
| "coverage": 0.058, | |
| "coverage_of_all_cases": 0.058 | |
| }, | |
| { | |
| "threshold": 0.9947178959846497, | |
| "accepted": 30, | |
| "errors": 8, | |
| "risk": 0.26666666666666666, | |
| "coverage": 0.06, | |
| "coverage_of_all_cases": 0.06 | |
| }, | |
| { | |
| "threshold": 0.9945299029350281, | |
| "accepted": 31, | |
| "errors": 8, | |
| "risk": 0.25806451612903225, | |
| "coverage": 0.062, | |
| "coverage_of_all_cases": 0.062 | |
| }, | |
| { | |
| "threshold": 0.9944137334823608, | |
| "accepted": 32, | |
| "errors": 8, | |
| "risk": 0.25, | |
| "coverage": 0.064, | |
| "coverage_of_all_cases": 0.064 | |
| }, | |
| { | |
| "threshold": 0.9942429661750793, | |
| "accepted": 33, | |
| "errors": 8, | |
| "risk": 0.24242424242424243, | |
| "coverage": 0.066, | |
| "coverage_of_all_cases": 0.066 | |
| }, | |
| { | |
| "threshold": 0.9938784241676331, | |
| "accepted": 34, | |
| "errors": 8, | |
| "risk": 0.23529411764705882, | |
| "coverage": 0.068, | |
| "coverage_of_all_cases": 0.068 | |
| }, | |
| { | |
| "threshold": 0.9936226010322571, | |
| "accepted": 35, | |
| "errors": 9, | |
| "risk": 0.2571428571428571, | |
| "coverage": 0.07, | |
| "coverage_of_all_cases": 0.07 | |
| }, | |
| { | |
| "threshold": 0.9935426712036133, | |
| "accepted": 36, | |
| "errors": 10, | |
| "risk": 0.2777777777777778, | |
| "coverage": 0.072, | |
| "coverage_of_all_cases": 0.072 | |
| }, | |
| { | |
| "threshold": 0.9933071732521057, | |
| "accepted": 37, | |
| "errors": 11, | |
| "risk": 0.2972972972972973, | |
| "coverage": 0.074, | |
| "coverage_of_all_cases": 0.074 | |
| }, | |
| { | |
| "threshold": 0.9931516647338867, | |
| "accepted": 38, | |
| "errors": 11, | |
| "risk": 0.2894736842105263, | |
| "coverage": 0.076, | |
| "coverage_of_all_cases": 0.076 | |
| }, | |
| { | |
| "threshold": 0.992779552936554, | |
| "accepted": 39, | |
| "errors": 12, | |
| "risk": 0.3076923076923077, | |
| "coverage": 0.078, | |
| "coverage_of_all_cases": 0.078 | |
| }, | |
| { | |
| "threshold": 0.9923654198646545, | |
| "accepted": 40, | |
| "errors": 13, | |
| "risk": 0.325, | |
| "coverage": 0.08, | |
| "coverage_of_all_cases": 0.08 | |
| }, | |
| { | |
| "threshold": 0.9919997453689575, | |
| "accepted": 41, | |
| "errors": 13, | |
| "risk": 0.3170731707317073, | |
| "coverage": 0.082, | |
| "coverage_of_all_cases": 0.082 | |
| }, | |
| { | |
| "threshold": 0.9918298125267029, | |
| "accepted": 42, | |
| "errors": 14, | |
| "risk": 0.3333333333333333, | |
| "coverage": 0.084, | |
| "coverage_of_all_cases": 0.084 | |
| }, | |
| { | |
| "threshold": 0.9918259382247925, | |
| "accepted": 43, | |
| "errors": 14, | |
| "risk": 0.32558139534883723, | |
| "coverage": 0.086, | |
| "coverage_of_all_cases": 0.086 | |
| }, | |
| { | |
| "threshold": 0.9914224743843079, | |
| "accepted": 45, | |
| "errors": 15, | |
| "risk": 0.3333333333333333, | |
| "coverage": 0.09, | |
| "coverage_of_all_cases": 0.09 | |
| }, | |
| { | |
| "threshold": 0.9914060831069946, | |
| "accepted": 46, | |
| "errors": 16, | |
| "risk": 0.34782608695652173, | |
| "coverage": 0.092, | |
| "coverage_of_all_cases": 0.092 | |
| }, | |
| { | |
| "threshold": 0.9913210272789001, | |
| "accepted": 47, | |
| "errors": 16, | |
| "risk": 0.3404255319148936, | |
| "coverage": 0.094, | |
| "coverage_of_all_cases": 0.094 | |
| }, | |
| { | |
| "threshold": 0.9911177158355713, | |
| "accepted": 48, | |
| "errors": 16, | |
| "risk": 0.3333333333333333, | |
| "coverage": 0.096, | |
| "coverage_of_all_cases": 0.096 | |
| }, | |
| { | |
| "threshold": 0.990752100944519, | |
| "accepted": 49, | |
| "errors": 16, | |
| "risk": 0.32653061224489793, | |
| "coverage": 0.098, | |
| "coverage_of_all_cases": 0.098 | |
| }, | |
| { | |
| "threshold": 0.9905250668525696, | |
| "accepted": 50, | |
| "errors": 16, | |
| "risk": 0.32, | |
| "coverage": 0.1, | |
| "coverage_of_all_cases": 0.1 | |
| }, | |
| { | |
| "threshold": 0.9902915358543396, | |
| "accepted": 51, | |
| "errors": 16, | |
| "risk": 0.3137254901960784, | |
| "coverage": 0.102, | |
| "coverage_of_all_cases": 0.102 | |
| }, | |
| { | |
| "threshold": 0.9897945523262024, | |
| "accepted": 52, | |
| "errors": 16, | |
| "risk": 0.3076923076923077, | |
| "coverage": 0.104, | |
| "coverage_of_all_cases": 0.104 | |
| }, | |
| { | |
| "threshold": 0.989291250705719, | |
| "accepted": 53, | |
| "errors": 16, | |
| "risk": 0.3018867924528302, | |
| "coverage": 0.106, | |
| "coverage_of_all_cases": 0.106 | |
| }, | |
| { | |
| "threshold": 0.9890130758285522, | |
| "accepted": 54, | |
| "errors": 16, | |
| "risk": 0.2962962962962963, | |
| "coverage": 0.108, | |
| "coverage_of_all_cases": 0.108 | |
| }, | |
| { | |
| "threshold": 0.9889920949935913, | |
| "accepted": 55, | |
| "errors": 16, | |
| "risk": 0.2909090909090909, | |
| "coverage": 0.11, | |
| "coverage_of_all_cases": 0.11 | |
| }, | |
| { | |
| "threshold": 0.98875892162323, | |
| "accepted": 57, | |
| "errors": 18, | |
| "risk": 0.3157894736842105, | |
| "coverage": 0.114, | |
| "coverage_of_all_cases": 0.114 | |
| }, | |
| { | |
| "threshold": 0.9884139895439148, | |
| "accepted": 58, | |
| "errors": 19, | |
| "risk": 0.3275862068965517, | |
| "coverage": 0.116, | |
| "coverage_of_all_cases": 0.116 | |
| }, | |
| { | |
| "threshold": 0.9883038997650146, | |
| "accepted": 59, | |
| "errors": 19, | |
| "risk": 0.3220338983050847, | |
| "coverage": 0.118, | |
| "coverage_of_all_cases": 0.118 | |
| }, | |
| { | |
| "threshold": 0.9881219863891602, | |
| "accepted": 60, | |
| "errors": 20, | |
| "risk": 0.3333333333333333, | |
| "coverage": 0.12, | |
| "coverage_of_all_cases": 0.12 | |
| }, | |
| { | |
| "threshold": 0.9878901839256287, | |
| "accepted": 61, | |
| "errors": 20, | |
| "risk": 0.32786885245901637, | |
| "coverage": 0.122, | |
| "coverage_of_all_cases": 0.122 | |
| }, | |
| { | |
| "threshold": 0.9878826141357422, | |
| "accepted": 62, | |
| "errors": 21, | |
| "risk": 0.3387096774193548, | |
| "coverage": 0.124, | |
| "coverage_of_all_cases": 0.124 | |
| }, | |
| { | |
| "threshold": 0.9875683188438416, | |
| "accepted": 63, | |
| "errors": 21, | |
| "risk": 0.3333333333333333, | |
| "coverage": 0.126, | |
| "coverage_of_all_cases": 0.126 | |
| }, | |
| { | |
| "threshold": 0.986877977848053, | |
| "accepted": 64, | |
| "errors": 22, | |
| "risk": 0.34375, | |
| "coverage": 0.128, | |
| "coverage_of_all_cases": 0.128 | |
| }, | |
| { | |
| "threshold": 0.9867032766342163, | |
| "accepted": 65, | |
| "errors": 22, | |
| "risk": 0.3384615384615385, | |
| "coverage": 0.13, | |
| "coverage_of_all_cases": 0.13 | |
| }, | |
| { | |
| "threshold": 0.9862732291221619, | |
| "accepted": 67, | |
| "errors": 22, | |
| "risk": 0.3283582089552239, | |
| "coverage": 0.134, | |
| "coverage_of_all_cases": 0.134 | |
| }, | |
| { | |
| "threshold": 0.9859364032745361, | |
| "accepted": 68, | |
| "errors": 22, | |
| "risk": 0.3235294117647059, | |
| "coverage": 0.136, | |
| "coverage_of_all_cases": 0.136 | |
| }, | |
| { | |
| "threshold": 0.985909640789032, | |
| "accepted": 71, | |
| "errors": 24, | |
| "risk": 0.3380281690140845, | |
| "coverage": 0.142, | |
| "coverage_of_all_cases": 0.142 | |
| }, | |
| { | |
| "threshold": 0.9857708215713501, | |
| "accepted": 72, | |
| "errors": 24, | |
| "risk": 0.3333333333333333, | |
| "coverage": 0.144, | |
| "coverage_of_all_cases": 0.144 | |
| }, | |
| { | |
| "threshold": 0.9854394793510437, | |
| "accepted": 73, | |
| "errors": 25, | |
| "risk": 0.3424657534246575, | |
| "coverage": 0.146, | |
| "coverage_of_all_cases": 0.146 | |
| }, | |
| { | |
| "threshold": 0.9851720333099365, | |
| "accepted": 74, | |
| "errors": 26, | |
| "risk": 0.35135135135135137, | |
| "coverage": 0.148, | |
| "coverage_of_all_cases": 0.148 | |
| }, | |
| { | |
| "threshold": 0.9848435521125793, | |
| "accepted": 75, | |
| "errors": 27, | |
| "risk": 0.36, | |
| "coverage": 0.15, | |
| "coverage_of_all_cases": 0.15 | |
| }, | |
| { | |
| "threshold": 0.9846483469009399, | |
| "accepted": 76, | |
| "errors": 28, | |
| "risk": 0.3684210526315789, | |
| "coverage": 0.152, | |
| "coverage_of_all_cases": 0.152 | |
| }, | |
| { | |
| "threshold": 0.9840936064720154, | |
| "accepted": 78, | |
| "errors": 30, | |
| "risk": 0.38461538461538464, | |
| "coverage": 0.156, | |
| "coverage_of_all_cases": 0.156 | |
| }, | |
| { | |
| "threshold": 0.9840633869171143, | |
| "accepted": 79, | |
| "errors": 31, | |
| "risk": 0.3924050632911392, | |
| "coverage": 0.158, | |
| "coverage_of_all_cases": 0.158 | |
| }, | |
| { | |
| "threshold": 0.984039843082428, | |
| "accepted": 80, | |
| "errors": 31, | |
| "risk": 0.3875, | |
| "coverage": 0.16, | |
| "coverage_of_all_cases": 0.16 | |
| }, | |
| { | |
| "threshold": 0.9837517738342285, | |
| "accepted": 81, | |
| "errors": 31, | |
| "risk": 0.38271604938271603, | |
| "coverage": 0.162, | |
| "coverage_of_all_cases": 0.162 | |
| }, | |
| { | |
| "threshold": 0.9835985898971558, | |
| "accepted": 82, | |
| "errors": 31, | |
| "risk": 0.3780487804878049, | |
| "coverage": 0.164, | |
| "coverage_of_all_cases": 0.164 | |
| }, | |
| { | |
| "threshold": 0.9832308292388916, | |
| "accepted": 83, | |
| "errors": 32, | |
| "risk": 0.3855421686746988, | |
| "coverage": 0.166, | |
| "coverage_of_all_cases": 0.166 | |
| }, | |
| { | |
| "threshold": 0.9820137619972229, | |
| "accepted": 86, | |
| "errors": 33, | |
| "risk": 0.38372093023255816, | |
| "coverage": 0.172, | |
| "coverage_of_all_cases": 0.172 | |
| }, | |
| { | |
| "threshold": 0.9813809394836426, | |
| "accepted": 87, | |
| "errors": 33, | |
| "risk": 0.3793103448275862, | |
| "coverage": 0.174, | |
| "coverage_of_all_cases": 0.174 | |
| }, | |
| { | |
| "threshold": 0.9808351993560791, | |
| "accepted": 88, | |
| "errors": 33, | |
| "risk": 0.375, | |
| "coverage": 0.176, | |
| "coverage_of_all_cases": 0.176 | |
| }, | |
| { | |
| "threshold": 0.9806132316589355, | |
| "accepted": 89, | |
| "errors": 34, | |
| "risk": 0.38202247191011235, | |
| "coverage": 0.178, | |
| "coverage_of_all_cases": 0.178 | |
| }, | |
| { | |
| "threshold": 0.9799087643623352, | |
| "accepted": 90, | |
| "errors": 34, | |
| "risk": 0.37777777777777777, | |
| "coverage": 0.18, | |
| "coverage_of_all_cases": 0.18 | |
| }, | |
| { | |
| "threshold": 0.9796676635742188, | |
| "accepted": 91, | |
| "errors": 35, | |
| "risk": 0.38461538461538464, | |
| "coverage": 0.182, | |
| "coverage_of_all_cases": 0.182 | |
| }, | |
| { | |
| "threshold": 0.9784191846847534, | |
| "accepted": 92, | |
| "errors": 35, | |
| "risk": 0.3804347826086957, | |
| "coverage": 0.184, | |
| "coverage_of_all_cases": 0.184 | |
| }, | |
| { | |
| "threshold": 0.9782649278640747, | |
| "accepted": 93, | |
| "errors": 35, | |
| "risk": 0.3763440860215054, | |
| "coverage": 0.186, | |
| "coverage_of_all_cases": 0.186 | |
| }, | |
| { | |
| "threshold": 0.9775974154472351, | |
| "accepted": 94, | |
| "errors": 35, | |
| "risk": 0.3723404255319149, | |
| "coverage": 0.188, | |
| "coverage_of_all_cases": 0.188 | |
| }, | |
| { | |
| "threshold": 0.9775681495666504, | |
| "accepted": 96, | |
| "errors": 36, | |
| "risk": 0.375, | |
| "coverage": 0.192, | |
| "coverage_of_all_cases": 0.192 | |
| }, | |
| { | |
| "threshold": 0.977022647857666, | |
| "accepted": 97, | |
| "errors": 36, | |
| "risk": 0.3711340206185567, | |
| "coverage": 0.194, | |
| "coverage_of_all_cases": 0.194 | |
| }, | |
| { | |
| "threshold": 0.9752432107925415, | |
| "accepted": 98, | |
| "errors": 36, | |
| "risk": 0.3673469387755102, | |
| "coverage": 0.196, | |
| "coverage_of_all_cases": 0.196 | |
| }, | |
| { | |
| "threshold": 0.9746571779251099, | |
| "accepted": 99, | |
| "errors": 37, | |
| "risk": 0.37373737373737376, | |
| "coverage": 0.198, | |
| "coverage_of_all_cases": 0.198 | |
| }, | |
| { | |
| "threshold": 0.9740425944328308, | |
| "accepted": 103, | |
| "errors": 38, | |
| "risk": 0.36893203883495146, | |
| "coverage": 0.206, | |
| "coverage_of_all_cases": 0.206 | |
| }, | |
| { | |
| "threshold": 0.9737408757209778, | |
| "accepted": 104, | |
| "errors": 38, | |
| "risk": 0.36538461538461536, | |
| "coverage": 0.208, | |
| "coverage_of_all_cases": 0.208 | |
| }, | |
| { | |
| "threshold": 0.9726318120956421, | |
| "accepted": 105, | |
| "errors": 38, | |
| "risk": 0.3619047619047619, | |
| "coverage": 0.21, | |
| "coverage_of_all_cases": 0.21 | |
| }, | |
| { | |
| "threshold": 0.9719475507736206, | |
| "accepted": 106, | |
| "errors": 38, | |
| "risk": 0.3584905660377358, | |
| "coverage": 0.212, | |
| "coverage_of_all_cases": 0.212 | |
| }, | |
| { | |
| "threshold": 0.9714164137840271, | |
| "accepted": 107, | |
| "errors": 38, | |
| "risk": 0.35514018691588783, | |
| "coverage": 0.214, | |
| "coverage_of_all_cases": 0.214 | |
| }, | |
| { | |
| "threshold": 0.970687747001648, | |
| "accepted": 114, | |
| "errors": 42, | |
| "risk": 0.3684210526315789, | |
| "coverage": 0.228, | |
| "coverage_of_all_cases": 0.228 | |
| }, | |
| { | |
| "threshold": 0.9703481197357178, | |
| "accepted": 115, | |
| "errors": 43, | |
| "risk": 0.3739130434782609, | |
| "coverage": 0.23, | |
| "coverage_of_all_cases": 0.23 | |
| }, | |
| { | |
| "threshold": 0.9690893292427063, | |
| "accepted": 116, | |
| "errors": 44, | |
| "risk": 0.3793103448275862, | |
| "coverage": 0.232, | |
| "coverage_of_all_cases": 0.232 | |
| }, | |
| { | |
| "threshold": 0.9685763120651245, | |
| "accepted": 117, | |
| "errors": 44, | |
| "risk": 0.37606837606837606, | |
| "coverage": 0.234, | |
| "coverage_of_all_cases": 0.234 | |
| }, | |
| { | |
| "threshold": 0.9683578610420227, | |
| "accepted": 118, | |
| "errors": 44, | |
| "risk": 0.3728813559322034, | |
| "coverage": 0.236, | |
| "coverage_of_all_cases": 0.236 | |
| }, | |
| { | |
| "threshold": 0.9669140577316284, | |
| "accepted": 122, | |
| "errors": 44, | |
| "risk": 0.36065573770491804, | |
| "coverage": 0.244, | |
| "coverage_of_all_cases": 0.244 | |
| }, | |
| { | |
| "threshold": 0.9661662578582764, | |
| "accepted": 124, | |
| "errors": 44, | |
| "risk": 0.3548387096774194, | |
| "coverage": 0.248, | |
| "coverage_of_all_cases": 0.248 | |
| }, | |
| { | |
| "threshold": 0.9636157155036926, | |
| "accepted": 125, | |
| "errors": 45, | |
| "risk": 0.36, | |
| "coverage": 0.25, | |
| "coverage_of_all_cases": 0.25 | |
| }, | |
| { | |
| "threshold": 0.9635935425758362, | |
| "accepted": 126, | |
| "errors": 46, | |
| "risk": 0.36507936507936506, | |
| "coverage": 0.252, | |
| "coverage_of_all_cases": 0.252 | |
| }, | |
| { | |
| "threshold": 0.963546633720398, | |
| "accepted": 127, | |
| "errors": 47, | |
| "risk": 0.3700787401574803, | |
| "coverage": 0.254, | |
| "coverage_of_all_cases": 0.254 | |
| }, | |
| { | |
| "threshold": 0.9626730680465698, | |
| "accepted": 129, | |
| "errors": 48, | |
| "risk": 0.37209302325581395, | |
| "coverage": 0.258, | |
| "coverage_of_all_cases": 0.258 | |
| }, | |
| { | |
| "threshold": 0.9603321552276611, | |
| "accepted": 130, | |
| "errors": 49, | |
| "risk": 0.3769230769230769, | |
| "coverage": 0.26, | |
| "coverage_of_all_cases": 0.26 | |
| }, | |
| { | |
| "threshold": 0.957912266254425, | |
| "accepted": 132, | |
| "errors": 49, | |
| "risk": 0.3712121212121212, | |
| "coverage": 0.264, | |
| "coverage_of_all_cases": 0.264 | |
| }, | |
| { | |
| "threshold": 0.9571253061294556, | |
| "accepted": 133, | |
| "errors": 49, | |
| "risk": 0.3684210526315789, | |
| "coverage": 0.266, | |
| "coverage_of_all_cases": 0.266 | |
| }, | |
| { | |
| "threshold": 0.9564689993858337, | |
| "accepted": 134, | |
| "errors": 50, | |
| "risk": 0.373134328358209, | |
| "coverage": 0.268, | |
| "coverage_of_all_cases": 0.268 | |
| }, | |
| { | |
| "threshold": 0.9552866220474243, | |
| "accepted": 135, | |
| "errors": 51, | |
| "risk": 0.37777777777777777, | |
| "coverage": 0.27, | |
| "coverage_of_all_cases": 0.27 | |
| }, | |
| { | |
| "threshold": 0.9547419548034668, | |
| "accepted": 136, | |
| "errors": 51, | |
| "risk": 0.375, | |
| "coverage": 0.272, | |
| "coverage_of_all_cases": 0.272 | |
| }, | |
| { | |
| "threshold": 0.9525741338729858, | |
| "accepted": 139, | |
| "errors": 52, | |
| "risk": 0.37410071942446044, | |
| "coverage": 0.278, | |
| "coverage_of_all_cases": 0.278 | |
| }, | |
| { | |
| "threshold": 0.950957179069519, | |
| "accepted": 140, | |
| "errors": 52, | |
| "risk": 0.37142857142857144, | |
| "coverage": 0.28, | |
| "coverage_of_all_cases": 0.28 | |
| }, | |
| { | |
| "threshold": 0.9508392214775085, | |
| "accepted": 141, | |
| "errors": 52, | |
| "risk": 0.36879432624113473, | |
| "coverage": 0.282, | |
| "coverage_of_all_cases": 0.282 | |
| }, | |
| { | |
| "threshold": 0.950482964515686, | |
| "accepted": 142, | |
| "errors": 52, | |
| "risk": 0.36619718309859156, | |
| "coverage": 0.284, | |
| "coverage_of_all_cases": 0.284 | |
| }, | |
| { | |
| "threshold": 0.9490001201629639, | |
| "accepted": 143, | |
| "errors": 52, | |
| "risk": 0.36363636363636365, | |
| "coverage": 0.286, | |
| "coverage_of_all_cases": 0.286 | |
| }, | |
| { | |
| "threshold": 0.9478920698165894, | |
| "accepted": 144, | |
| "errors": 52, | |
| "risk": 0.3611111111111111, | |
| "coverage": 0.288, | |
| "coverage_of_all_cases": 0.288 | |
| }, | |
| { | |
| "threshold": 0.9465966820716858, | |
| "accepted": 147, | |
| "errors": 54, | |
| "risk": 0.3673469387755102, | |
| "coverage": 0.294, | |
| "coverage_of_all_cases": 0.294 | |
| }, | |
| { | |
| "threshold": 0.9426250457763672, | |
| "accepted": 148, | |
| "errors": 55, | |
| "risk": 0.3716216216216216, | |
| "coverage": 0.296, | |
| "coverage_of_all_cases": 0.296 | |
| }, | |
| { | |
| "threshold": 0.9418172240257263, | |
| "accepted": 149, | |
| "errors": 55, | |
| "risk": 0.3691275167785235, | |
| "coverage": 0.298, | |
| "coverage_of_all_cases": 0.298 | |
| }, | |
| { | |
| "threshold": 0.9399133324623108, | |
| "accepted": 154, | |
| "errors": 57, | |
| "risk": 0.37012987012987014, | |
| "coverage": 0.308, | |
| "coverage_of_all_cases": 0.308 | |
| }, | |
| { | |
| "threshold": 0.9392393827438354, | |
| "accepted": 155, | |
| "errors": 57, | |
| "risk": 0.36774193548387096, | |
| "coverage": 0.31, | |
| "coverage_of_all_cases": 0.31 | |
| }, | |
| { | |
| "threshold": 0.9372748732566833, | |
| "accepted": 156, | |
| "errors": 57, | |
| "risk": 0.36538461538461536, | |
| "coverage": 0.312, | |
| "coverage_of_all_cases": 0.312 | |
| }, | |
| { | |
| "threshold": 0.937218427658081, | |
| "accepted": 157, | |
| "errors": 57, | |
| "risk": 0.3630573248407643, | |
| "coverage": 0.314, | |
| "coverage_of_all_cases": 0.314 | |
| }, | |
| { | |
| "threshold": 0.9360596537590027, | |
| "accepted": 158, | |
| "errors": 57, | |
| "risk": 0.36075949367088606, | |
| "coverage": 0.316, | |
| "coverage_of_all_cases": 0.316 | |
| }, | |
| { | |
| "threshold": 0.9324532747268677, | |
| "accepted": 161, | |
| "errors": 58, | |
| "risk": 0.36024844720496896, | |
| "coverage": 0.322, | |
| "coverage_of_all_cases": 0.322 | |
| }, | |
| { | |
| "threshold": 0.9310221076011658, | |
| "accepted": 162, | |
| "errors": 58, | |
| "risk": 0.35802469135802467, | |
| "coverage": 0.324, | |
| "coverage_of_all_cases": 0.324 | |
| }, | |
| { | |
| "threshold": 0.9304646849632263, | |
| "accepted": 163, | |
| "errors": 58, | |
| "risk": 0.3558282208588957, | |
| "coverage": 0.326, | |
| "coverage_of_all_cases": 0.326 | |
| }, | |
| { | |
| "threshold": 0.9289225339889526, | |
| "accepted": 164, | |
| "errors": 59, | |
| "risk": 0.3597560975609756, | |
| "coverage": 0.328, | |
| "coverage_of_all_cases": 0.328 | |
| }, | |
| { | |
| "threshold": 0.9241418242454529, | |
| "accepted": 169, | |
| "errors": 60, | |
| "risk": 0.35502958579881655, | |
| "coverage": 0.338, | |
| "coverage_of_all_cases": 0.338 | |
| }, | |
| { | |
| "threshold": 0.9236072897911072, | |
| "accepted": 170, | |
| "errors": 61, | |
| "risk": 0.3588235294117647, | |
| "coverage": 0.34, | |
| "coverage_of_all_cases": 0.34 | |
| }, | |
| { | |
| "threshold": 0.9233053922653198, | |
| "accepted": 171, | |
| "errors": 61, | |
| "risk": 0.3567251461988304, | |
| "coverage": 0.342, | |
| "coverage_of_all_cases": 0.342 | |
| }, | |
| { | |
| "threshold": 0.9223835468292236, | |
| "accepted": 172, | |
| "errors": 61, | |
| "risk": 0.3546511627906977, | |
| "coverage": 0.344, | |
| "coverage_of_all_cases": 0.344 | |
| }, | |
| { | |
| "threshold": 0.9202904105186462, | |
| "accepted": 173, | |
| "errors": 62, | |
| "risk": 0.3583815028901734, | |
| "coverage": 0.346, | |
| "coverage_of_all_cases": 0.346 | |
| }, | |
| { | |
| "threshold": 0.9202137589454651, | |
| "accepted": 174, | |
| "errors": 62, | |
| "risk": 0.3563218390804598, | |
| "coverage": 0.348, | |
| "coverage_of_all_cases": 0.348 | |
| }, | |
| { | |
| "threshold": 0.9186437129974365, | |
| "accepted": 175, | |
| "errors": 63, | |
| "risk": 0.36, | |
| "coverage": 0.35, | |
| "coverage_of_all_cases": 0.35 | |
| }, | |
| { | |
| "threshold": 0.9169458150863647, | |
| "accepted": 176, | |
| "errors": 64, | |
| "risk": 0.36363636363636365, | |
| "coverage": 0.352, | |
| "coverage_of_all_cases": 0.352 | |
| }, | |
| { | |
| "threshold": 0.9149009585380554, | |
| "accepted": 180, | |
| "errors": 66, | |
| "risk": 0.36666666666666664, | |
| "coverage": 0.36, | |
| "coverage_of_all_cases": 0.36 | |
| }, | |
| { | |
| "threshold": 0.9046505093574524, | |
| "accepted": 187, | |
| "errors": 69, | |
| "risk": 0.3689839572192513, | |
| "coverage": 0.374, | |
| "coverage_of_all_cases": 0.374 | |
| }, | |
| { | |
| "threshold": 0.903552234172821, | |
| "accepted": 188, | |
| "errors": 69, | |
| "risk": 0.3670212765957447, | |
| "coverage": 0.376, | |
| "coverage_of_all_cases": 0.376 | |
| }, | |
| { | |
| "threshold": 0.8981395363807678, | |
| "accepted": 189, | |
| "errors": 69, | |
| "risk": 0.36507936507936506, | |
| "coverage": 0.378, | |
| "coverage_of_all_cases": 0.378 | |
| }, | |
| { | |
| "threshold": 0.8954285979270935, | |
| "accepted": 190, | |
| "errors": 70, | |
| "risk": 0.3684210526315789, | |
| "coverage": 0.38, | |
| "coverage_of_all_cases": 0.38 | |
| }, | |
| { | |
| "threshold": 0.8949751257896423, | |
| "accepted": 191, | |
| "errors": 70, | |
| "risk": 0.36649214659685864, | |
| "coverage": 0.382, | |
| "coverage_of_all_cases": 0.382 | |
| }, | |
| { | |
| "threshold": 0.8941022753715515, | |
| "accepted": 192, | |
| "errors": 70, | |
| "risk": 0.3645833333333333, | |
| "coverage": 0.384, | |
| "coverage_of_all_cases": 0.384 | |
| }, | |
| { | |
| "threshold": 0.8938770294189453, | |
| "accepted": 193, | |
| "errors": 70, | |
| "risk": 0.3626943005181347, | |
| "coverage": 0.386, | |
| "coverage_of_all_cases": 0.386 | |
| }, | |
| { | |
| "threshold": 0.8933094143867493, | |
| "accepted": 196, | |
| "errors": 73, | |
| "risk": 0.37244897959183676, | |
| "coverage": 0.392, | |
| "coverage_of_all_cases": 0.392 | |
| }, | |
| { | |
| "threshold": 0.8872338533401489, | |
| "accepted": 197, | |
| "errors": 74, | |
| "risk": 0.3756345177664975, | |
| "coverage": 0.394, | |
| "coverage_of_all_cases": 0.394 | |
| }, | |
| { | |
| "threshold": 0.8871284127235413, | |
| "accepted": 198, | |
| "errors": 74, | |
| "risk": 0.37373737373737376, | |
| "coverage": 0.396, | |
| "coverage_of_all_cases": 0.396 | |
| }, | |
| { | |
| "threshold": 0.8807970285415649, | |
| "accepted": 207, | |
| "errors": 79, | |
| "risk": 0.38164251207729466, | |
| "coverage": 0.414, | |
| "coverage_of_all_cases": 0.414 | |
| }, | |
| { | |
| "threshold": 0.880573570728302, | |
| "accepted": 208, | |
| "errors": 79, | |
| "risk": 0.3798076923076923, | |
| "coverage": 0.416, | |
| "coverage_of_all_cases": 0.416 | |
| }, | |
| { | |
| "threshold": 0.8792030215263367, | |
| "accepted": 209, | |
| "errors": 79, | |
| "risk": 0.37799043062200954, | |
| "coverage": 0.418, | |
| "coverage_of_all_cases": 0.418 | |
| }, | |
| { | |
| "threshold": 0.8670357465744019, | |
| "accepted": 215, | |
| "errors": 82, | |
| "risk": 0.3813953488372093, | |
| "coverage": 0.43, | |
| "coverage_of_all_cases": 0.43 | |
| }, | |
| { | |
| "threshold": 0.8659706115722656, | |
| "accepted": 216, | |
| "errors": 82, | |
| "risk": 0.37962962962962965, | |
| "coverage": 0.432, | |
| "coverage_of_all_cases": 0.432 | |
| }, | |
| { | |
| "threshold": 0.8643472790718079, | |
| "accepted": 217, | |
| "errors": 83, | |
| "risk": 0.3824884792626728, | |
| "coverage": 0.434, | |
| "coverage_of_all_cases": 0.434 | |
| }, | |
| { | |
| "threshold": 0.8607219457626343, | |
| "accepted": 218, | |
| "errors": 84, | |
| "risk": 0.3853211009174312, | |
| "coverage": 0.436, | |
| "coverage_of_all_cases": 0.436 | |
| }, | |
| { | |
| "threshold": 0.859687089920044, | |
| "accepted": 219, | |
| "errors": 85, | |
| "risk": 0.3881278538812785, | |
| "coverage": 0.438, | |
| "coverage_of_all_cases": 0.438 | |
| }, | |
| { | |
| "threshold": 0.8563401699066162, | |
| "accepted": 220, | |
| "errors": 86, | |
| "risk": 0.39090909090909093, | |
| "coverage": 0.44, | |
| "coverage_of_all_cases": 0.44 | |
| }, | |
| { | |
| "threshold": 0.8554590940475464, | |
| "accepted": 221, | |
| "errors": 86, | |
| "risk": 0.3891402714932127, | |
| "coverage": 0.442, | |
| "coverage_of_all_cases": 0.442 | |
| }, | |
| { | |
| "threshold": 0.8548048138618469, | |
| "accepted": 222, | |
| "errors": 86, | |
| "risk": 0.38738738738738737, | |
| "coverage": 0.444, | |
| "coverage_of_all_cases": 0.444 | |
| }, | |
| { | |
| "threshold": 0.851952850818634, | |
| "accepted": 223, | |
| "errors": 86, | |
| "risk": 0.38565022421524664, | |
| "coverage": 0.446, | |
| "coverage_of_all_cases": 0.446 | |
| }, | |
| { | |
| "threshold": 0.8515800833702087, | |
| "accepted": 224, | |
| "errors": 86, | |
| "risk": 0.38392857142857145, | |
| "coverage": 0.448, | |
| "coverage_of_all_cases": 0.448 | |
| }, | |
| { | |
| "threshold": 0.8500957489013672, | |
| "accepted": 225, | |
| "errors": 86, | |
| "risk": 0.38222222222222224, | |
| "coverage": 0.45, | |
| "coverage_of_all_cases": 0.45 | |
| }, | |
| { | |
| "threshold": 0.8432222008705139, | |
| "accepted": 226, | |
| "errors": 86, | |
| "risk": 0.3805309734513274, | |
| "coverage": 0.452, | |
| "coverage_of_all_cases": 0.452 | |
| }, | |
| { | |
| "threshold": 0.8389536738395691, | |
| "accepted": 227, | |
| "errors": 86, | |
| "risk": 0.3788546255506608, | |
| "coverage": 0.454, | |
| "coverage_of_all_cases": 0.454 | |
| }, | |
| { | |
| "threshold": 0.8376054763793945, | |
| "accepted": 228, | |
| "errors": 86, | |
| "risk": 0.37719298245614036, | |
| "coverage": 0.456, | |
| "coverage_of_all_cases": 0.456 | |
| }, | |
| { | |
| "threshold": 0.835835337638855, | |
| "accepted": 229, | |
| "errors": 86, | |
| "risk": 0.37554585152838427, | |
| "coverage": 0.458, | |
| "coverage_of_all_cases": 0.458 | |
| }, | |
| { | |
| "threshold": 0.8354835510253906, | |
| "accepted": 233, | |
| "errors": 87, | |
| "risk": 0.37339055793991416, | |
| "coverage": 0.466, | |
| "coverage_of_all_cases": 0.466 | |
| }, | |
| { | |
| "threshold": 0.8337540626525879, | |
| "accepted": 234, | |
| "errors": 87, | |
| "risk": 0.3717948717948718, | |
| "coverage": 0.468, | |
| "coverage_of_all_cases": 0.468 | |
| }, | |
| { | |
| "threshold": 0.8300923705101013, | |
| "accepted": 235, | |
| "errors": 87, | |
| "risk": 0.3702127659574468, | |
| "coverage": 0.47, | |
| "coverage_of_all_cases": 0.47 | |
| }, | |
| { | |
| "threshold": 0.8213374614715576, | |
| "accepted": 236, | |
| "errors": 87, | |
| "risk": 0.3686440677966102, | |
| "coverage": 0.472, | |
| "coverage_of_all_cases": 0.472 | |
| }, | |
| { | |
| "threshold": 0.8198679089546204, | |
| "accepted": 237, | |
| "errors": 87, | |
| "risk": 0.3670886075949367, | |
| "coverage": 0.474, | |
| "coverage_of_all_cases": 0.474 | |
| }, | |
| { | |
| "threshold": 0.8175744414329529, | |
| "accepted": 241, | |
| "errors": 89, | |
| "risk": 0.36929460580912865, | |
| "coverage": 0.482, | |
| "coverage_of_all_cases": 0.482 | |
| }, | |
| { | |
| "threshold": 0.8084703087806702, | |
| "accepted": 242, | |
| "errors": 89, | |
| "risk": 0.3677685950413223, | |
| "coverage": 0.484, | |
| "coverage_of_all_cases": 0.484 | |
| }, | |
| { | |
| "threshold": 0.808276891708374, | |
| "accepted": 243, | |
| "errors": 89, | |
| "risk": 0.3662551440329218, | |
| "coverage": 0.486, | |
| "coverage_of_all_cases": 0.486 | |
| }, | |
| { | |
| "threshold": 0.806610643863678, | |
| "accepted": 244, | |
| "errors": 89, | |
| "risk": 0.36475409836065575, | |
| "coverage": 0.488, | |
| "coverage_of_all_cases": 0.488 | |
| }, | |
| { | |
| "threshold": 0.7994853258132935, | |
| "accepted": 245, | |
| "errors": 90, | |
| "risk": 0.3673469387755102, | |
| "coverage": 0.49, | |
| "coverage_of_all_cases": 0.49 | |
| }, | |
| { | |
| "threshold": 0.7981867790222168, | |
| "accepted": 249, | |
| "errors": 93, | |
| "risk": 0.37349397590361444, | |
| "coverage": 0.498, | |
| "coverage_of_all_cases": 0.498 | |
| }, | |
| { | |
| "threshold": 0.790910005569458, | |
| "accepted": 250, | |
| "errors": 93, | |
| "risk": 0.372, | |
| "coverage": 0.5, | |
| "coverage_of_all_cases": 0.5 | |
| }, | |
| { | |
| "threshold": 0.7864030599594116, | |
| "accepted": 251, | |
| "errors": 93, | |
| "risk": 0.3705179282868526, | |
| "coverage": 0.502, | |
| "coverage_of_all_cases": 0.502 | |
| }, | |
| { | |
| "threshold": 0.7860057353973389, | |
| "accepted": 252, | |
| "errors": 93, | |
| "risk": 0.36904761904761907, | |
| "coverage": 0.504, | |
| "coverage_of_all_cases": 0.504 | |
| }, | |
| { | |
| "threshold": 0.782718300819397, | |
| "accepted": 253, | |
| "errors": 93, | |
| "risk": 0.3675889328063241, | |
| "coverage": 0.506, | |
| "coverage_of_all_cases": 0.506 | |
| }, | |
| { | |
| "threshold": 0.7783264517784119, | |
| "accepted": 254, | |
| "errors": 94, | |
| "risk": 0.3700787401574803, | |
| "coverage": 0.508, | |
| "coverage_of_all_cases": 0.508 | |
| }, | |
| { | |
| "threshold": 0.7772998809814453, | |
| "accepted": 255, | |
| "errors": 94, | |
| "risk": 0.3686274509803922, | |
| "coverage": 0.51, | |
| "coverage_of_all_cases": 0.51 | |
| }, | |
| { | |
| "threshold": 0.7730340957641602, | |
| "accepted": 256, | |
| "errors": 94, | |
| "risk": 0.3671875, | |
| "coverage": 0.512, | |
| "coverage_of_all_cases": 0.512 | |
| }, | |
| { | |
| "threshold": 0.7671470046043396, | |
| "accepted": 257, | |
| "errors": 94, | |
| "risk": 0.3657587548638132, | |
| "coverage": 0.514, | |
| "coverage_of_all_cases": 0.514 | |
| }, | |
| { | |
| "threshold": 0.766708493232727, | |
| "accepted": 258, | |
| "errors": 95, | |
| "risk": 0.3682170542635659, | |
| "coverage": 0.516, | |
| "coverage_of_all_cases": 0.516 | |
| }, | |
| { | |
| "threshold": 0.763678252696991, | |
| "accepted": 259, | |
| "errors": 96, | |
| "risk": 0.37065637065637064, | |
| "coverage": 0.518, | |
| "coverage_of_all_cases": 0.518 | |
| }, | |
| { | |
| "threshold": 0.757959246635437, | |
| "accepted": 260, | |
| "errors": 96, | |
| "risk": 0.36923076923076925, | |
| "coverage": 0.52, | |
| "coverage_of_all_cases": 0.52 | |
| }, | |
| { | |
| "threshold": 0.7568399906158447, | |
| "accepted": 261, | |
| "errors": 97, | |
| "risk": 0.3716475095785441, | |
| "coverage": 0.522, | |
| "coverage_of_all_cases": 0.522 | |
| }, | |
| { | |
| "threshold": 0.7562941908836365, | |
| "accepted": 262, | |
| "errors": 97, | |
| "risk": 0.3702290076335878, | |
| "coverage": 0.524, | |
| "coverage_of_all_cases": 0.524 | |
| }, | |
| { | |
| "threshold": 0.755923330783844, | |
| "accepted": 263, | |
| "errors": 98, | |
| "risk": 0.3726235741444867, | |
| "coverage": 0.526, | |
| "coverage_of_all_cases": 0.526 | |
| }, | |
| { | |
| "threshold": 0.7550525069236755, | |
| "accepted": 264, | |
| "errors": 98, | |
| "risk": 0.3712121212121212, | |
| "coverage": 0.528, | |
| "coverage_of_all_cases": 0.528 | |
| }, | |
| { | |
| "threshold": 0.7549149990081787, | |
| "accepted": 272, | |
| "errors": 104, | |
| "risk": 0.38235294117647056, | |
| "coverage": 0.544, | |
| "coverage_of_all_cases": 0.544 | |
| }, | |
| { | |
| "threshold": 0.7514601945877075, | |
| "accepted": 273, | |
| "errors": 104, | |
| "risk": 0.38095238095238093, | |
| "coverage": 0.546, | |
| "coverage_of_all_cases": 0.546 | |
| }, | |
| { | |
| "threshold": 0.7511835694313049, | |
| "accepted": 274, | |
| "errors": 105, | |
| "risk": 0.38321167883211676, | |
| "coverage": 0.548, | |
| "coverage_of_all_cases": 0.548 | |
| }, | |
| { | |
| "threshold": 0.749190092086792, | |
| "accepted": 275, | |
| "errors": 106, | |
| "risk": 0.38545454545454544, | |
| "coverage": 0.55, | |
| "coverage_of_all_cases": 0.55 | |
| }, | |
| { | |
| "threshold": 0.7486920952796936, | |
| "accepted": 276, | |
| "errors": 106, | |
| "risk": 0.38405797101449274, | |
| "coverage": 0.552, | |
| "coverage_of_all_cases": 0.552 | |
| }, | |
| { | |
| "threshold": 0.7479555606842041, | |
| "accepted": 277, | |
| "errors": 107, | |
| "risk": 0.3862815884476534, | |
| "coverage": 0.554, | |
| "coverage_of_all_cases": 0.554 | |
| }, | |
| { | |
| "threshold": 0.7465093731880188, | |
| "accepted": 278, | |
| "errors": 107, | |
| "risk": 0.38489208633093525, | |
| "coverage": 0.556, | |
| "coverage_of_all_cases": 0.556 | |
| }, | |
| { | |
| "threshold": 0.7461209297180176, | |
| "accepted": 279, | |
| "errors": 107, | |
| "risk": 0.3835125448028674, | |
| "coverage": 0.558, | |
| "coverage_of_all_cases": 0.558 | |
| }, | |
| { | |
| "threshold": 0.7444326281547546, | |
| "accepted": 280, | |
| "errors": 107, | |
| "risk": 0.3821428571428571, | |
| "coverage": 0.56, | |
| "coverage_of_all_cases": 0.56 | |
| }, | |
| { | |
| "threshold": 0.7438138127326965, | |
| "accepted": 281, | |
| "errors": 107, | |
| "risk": 0.3807829181494662, | |
| "coverage": 0.562, | |
| "coverage_of_all_cases": 0.562 | |
| }, | |
| { | |
| "threshold": 0.7430688142776489, | |
| "accepted": 282, | |
| "errors": 108, | |
| "risk": 0.3829787234042553, | |
| "coverage": 0.564, | |
| "coverage_of_all_cases": 0.564 | |
| }, | |
| { | |
| "threshold": 0.742014467716217, | |
| "accepted": 283, | |
| "errors": 108, | |
| "risk": 0.38162544169611307, | |
| "coverage": 0.566, | |
| "coverage_of_all_cases": 0.566 | |
| }, | |
| { | |
| "threshold": 0.741270124912262, | |
| "accepted": 284, | |
| "errors": 109, | |
| "risk": 0.38380281690140844, | |
| "coverage": 0.568, | |
| "coverage_of_all_cases": 0.568 | |
| }, | |
| { | |
| "threshold": 0.7368677258491516, | |
| "accepted": 285, | |
| "errors": 110, | |
| "risk": 0.38596491228070173, | |
| "coverage": 0.57, | |
| "coverage_of_all_cases": 0.57 | |
| }, | |
| { | |
| "threshold": 0.7339802980422974, | |
| "accepted": 286, | |
| "errors": 110, | |
| "risk": 0.38461538461538464, | |
| "coverage": 0.572, | |
| "coverage_of_all_cases": 0.572 | |
| }, | |
| { | |
| "threshold": 0.7335910797119141, | |
| "accepted": 287, | |
| "errors": 111, | |
| "risk": 0.3867595818815331, | |
| "coverage": 0.574, | |
| "coverage_of_all_cases": 0.574 | |
| }, | |
| { | |
| "threshold": 0.731936514377594, | |
| "accepted": 288, | |
| "errors": 111, | |
| "risk": 0.3854166666666667, | |
| "coverage": 0.576, | |
| "coverage_of_all_cases": 0.576 | |
| }, | |
| { | |
| "threshold": 0.7313528656959534, | |
| "accepted": 289, | |
| "errors": 111, | |
| "risk": 0.38408304498269896, | |
| "coverage": 0.578, | |
| "coverage_of_all_cases": 0.578 | |
| }, | |
| { | |
| "threshold": 0.7310585379600525, | |
| "accepted": 297, | |
| "errors": 117, | |
| "risk": 0.3939393939393939, | |
| "coverage": 0.594, | |
| "coverage_of_all_cases": 0.594 | |
| }, | |
| { | |
| "threshold": 0.7308873534202576, | |
| "accepted": 298, | |
| "errors": 117, | |
| "risk": 0.3926174496644295, | |
| "coverage": 0.596, | |
| "coverage_of_all_cases": 0.596 | |
| }, | |
| { | |
| "threshold": 0.7284591794013977, | |
| "accepted": 299, | |
| "errors": 117, | |
| "risk": 0.391304347826087, | |
| "coverage": 0.598, | |
| "coverage_of_all_cases": 0.598 | |
| }, | |
| { | |
| "threshold": 0.7269029021263123, | |
| "accepted": 300, | |
| "errors": 117, | |
| "risk": 0.39, | |
| "coverage": 0.6, | |
| "coverage_of_all_cases": 0.6 | |
| }, | |
| { | |
| "threshold": 0.7264076471328735, | |
| "accepted": 301, | |
| "errors": 117, | |
| "risk": 0.38870431893687707, | |
| "coverage": 0.602, | |
| "coverage_of_all_cases": 0.602 | |
| }, | |
| { | |
| "threshold": 0.7253871560096741, | |
| "accepted": 302, | |
| "errors": 117, | |
| "risk": 0.38741721854304634, | |
| "coverage": 0.604, | |
| "coverage_of_all_cases": 0.604 | |
| }, | |
| { | |
| "threshold": 0.7250226736068726, | |
| "accepted": 303, | |
| "errors": 118, | |
| "risk": 0.38943894389438943, | |
| "coverage": 0.606, | |
| "coverage_of_all_cases": 0.606 | |
| }, | |
| { | |
| "threshold": 0.7244352102279663, | |
| "accepted": 304, | |
| "errors": 118, | |
| "risk": 0.3881578947368421, | |
| "coverage": 0.608, | |
| "coverage_of_all_cases": 0.608 | |
| }, | |
| { | |
| "threshold": 0.7180502414703369, | |
| "accepted": 305, | |
| "errors": 119, | |
| "risk": 0.3901639344262295, | |
| "coverage": 0.61, | |
| "coverage_of_all_cases": 0.61 | |
| }, | |
| { | |
| "threshold": 0.711898148059845, | |
| "accepted": 306, | |
| "errors": 120, | |
| "risk": 0.39215686274509803, | |
| "coverage": 0.612, | |
| "coverage_of_all_cases": 0.612 | |
| }, | |
| { | |
| "threshold": 0.711210310459137, | |
| "accepted": 307, | |
| "errors": 120, | |
| "risk": 0.39087947882736157, | |
| "coverage": 0.614, | |
| "coverage_of_all_cases": 0.614 | |
| }, | |
| { | |
| "threshold": 0.7057850360870361, | |
| "accepted": 317, | |
| "errors": 123, | |
| "risk": 0.38801261829652994, | |
| "coverage": 0.634, | |
| "coverage_of_all_cases": 0.634 | |
| }, | |
| { | |
| "threshold": 0.7018497586250305, | |
| "accepted": 318, | |
| "errors": 123, | |
| "risk": 0.3867924528301887, | |
| "coverage": 0.636, | |
| "coverage_of_all_cases": 0.636 | |
| }, | |
| { | |
| "threshold": 0.7015446424484253, | |
| "accepted": 319, | |
| "errors": 123, | |
| "risk": 0.38557993730407525, | |
| "coverage": 0.638, | |
| "coverage_of_all_cases": 0.638 | |
| }, | |
| { | |
| "threshold": 0.7007359266281128, | |
| "accepted": 320, | |
| "errors": 123, | |
| "risk": 0.384375, | |
| "coverage": 0.64, | |
| "coverage_of_all_cases": 0.64 | |
| }, | |
| { | |
| "threshold": 0.6953479647636414, | |
| "accepted": 321, | |
| "errors": 123, | |
| "risk": 0.38317757009345793, | |
| "coverage": 0.642, | |
| "coverage_of_all_cases": 0.642 | |
| }, | |
| { | |
| "threshold": 0.6939518451690674, | |
| "accepted": 322, | |
| "errors": 124, | |
| "risk": 0.38509316770186336, | |
| "coverage": 0.644, | |
| "coverage_of_all_cases": 0.644 | |
| }, | |
| { | |
| "threshold": 0.6886867880821228, | |
| "accepted": 323, | |
| "errors": 124, | |
| "risk": 0.38390092879256965, | |
| "coverage": 0.646, | |
| "coverage_of_all_cases": 0.646 | |
| }, | |
| { | |
| "threshold": 0.6791787147521973, | |
| "accepted": 335, | |
| "errors": 133, | |
| "risk": 0.3970149253731343, | |
| "coverage": 0.67, | |
| "coverage_of_all_cases": 0.67 | |
| }, | |
| { | |
| "threshold": 0.6781145334243774, | |
| "accepted": 336, | |
| "errors": 134, | |
| "risk": 0.39880952380952384, | |
| "coverage": 0.672, | |
| "coverage_of_all_cases": 0.672 | |
| }, | |
| { | |
| "threshold": 0.6772987842559814, | |
| "accepted": 337, | |
| "errors": 134, | |
| "risk": 0.39762611275964393, | |
| "coverage": 0.674, | |
| "coverage_of_all_cases": 0.674 | |
| }, | |
| { | |
| "threshold": 0.6756038069725037, | |
| "accepted": 338, | |
| "errors": 135, | |
| "risk": 0.3994082840236686, | |
| "coverage": 0.676, | |
| "coverage_of_all_cases": 0.676 | |
| }, | |
| { | |
| "threshold": 0.6679286956787109, | |
| "accepted": 339, | |
| "errors": 135, | |
| "risk": 0.39823008849557523, | |
| "coverage": 0.678, | |
| "coverage_of_all_cases": 0.678 | |
| }, | |
| { | |
| "threshold": 0.6666761636734009, | |
| "accepted": 340, | |
| "errors": 136, | |
| "risk": 0.4, | |
| "coverage": 0.68, | |
| "coverage_of_all_cases": 0.68 | |
| }, | |
| { | |
| "threshold": 0.6609349250793457, | |
| "accepted": 341, | |
| "errors": 137, | |
| "risk": 0.40175953079178883, | |
| "coverage": 0.682, | |
| "coverage_of_all_cases": 0.682 | |
| }, | |
| { | |
| "threshold": 0.6595908403396606, | |
| "accepted": 342, | |
| "errors": 137, | |
| "risk": 0.40058479532163743, | |
| "coverage": 0.684, | |
| "coverage_of_all_cases": 0.684 | |
| }, | |
| { | |
| "threshold": 0.6579158902168274, | |
| "accepted": 343, | |
| "errors": 138, | |
| "risk": 0.40233236151603496, | |
| "coverage": 0.686, | |
| "coverage_of_all_cases": 0.686 | |
| }, | |
| { | |
| "threshold": 0.6523692011833191, | |
| "accepted": 344, | |
| "errors": 138, | |
| "risk": 0.4011627906976744, | |
| "coverage": 0.688, | |
| "coverage_of_all_cases": 0.688 | |
| }, | |
| { | |
| "threshold": 0.6513549089431763, | |
| "accepted": 356, | |
| "errors": 146, | |
| "risk": 0.4101123595505618, | |
| "coverage": 0.712, | |
| "coverage_of_all_cases": 0.712 | |
| }, | |
| { | |
| "threshold": 0.6486443877220154, | |
| "accepted": 357, | |
| "errors": 146, | |
| "risk": 0.40896358543417366, | |
| "coverage": 0.714, | |
| "coverage_of_all_cases": 0.714 | |
| }, | |
| { | |
| "threshold": 0.6449442505836487, | |
| "accepted": 358, | |
| "errors": 146, | |
| "risk": 0.40782122905027934, | |
| "coverage": 0.716, | |
| "coverage_of_all_cases": 0.716 | |
| }, | |
| { | |
| "threshold": 0.6363654136657715, | |
| "accepted": 359, | |
| "errors": 146, | |
| "risk": 0.40668523676880225, | |
| "coverage": 0.718, | |
| "coverage_of_all_cases": 0.718 | |
| }, | |
| { | |
| "threshold": 0.6322428584098816, | |
| "accepted": 360, | |
| "errors": 146, | |
| "risk": 0.40555555555555556, | |
| "coverage": 0.72, | |
| "coverage_of_all_cases": 0.72 | |
| }, | |
| { | |
| "threshold": 0.6307764053344727, | |
| "accepted": 361, | |
| "errors": 146, | |
| "risk": 0.40443213296398894, | |
| "coverage": 0.722, | |
| "coverage_of_all_cases": 0.722 | |
| }, | |
| { | |
| "threshold": 0.6274750828742981, | |
| "accepted": 362, | |
| "errors": 147, | |
| "risk": 0.40607734806629836, | |
| "coverage": 0.724, | |
| "coverage_of_all_cases": 0.724 | |
| }, | |
| { | |
| "threshold": 0.6267033815383911, | |
| "accepted": 363, | |
| "errors": 148, | |
| "risk": 0.40771349862258954, | |
| "coverage": 0.726, | |
| "coverage_of_all_cases": 0.726 | |
| }, | |
| { | |
| "threshold": 0.6227180361747742, | |
| "accepted": 364, | |
| "errors": 148, | |
| "risk": 0.4065934065934066, | |
| "coverage": 0.728, | |
| "coverage_of_all_cases": 0.728 | |
| }, | |
| { | |
| "threshold": 0.622459352016449, | |
| "accepted": 376, | |
| "errors": 154, | |
| "risk": 0.4095744680851064, | |
| "coverage": 0.752, | |
| "coverage_of_all_cases": 0.752 | |
| }, | |
| { | |
| "threshold": 0.6134899854660034, | |
| "accepted": 377, | |
| "errors": 155, | |
| "risk": 0.41114058355437666, | |
| "coverage": 0.754, | |
| "coverage_of_all_cases": 0.754 | |
| }, | |
| { | |
| "threshold": 0.6112003922462463, | |
| "accepted": 378, | |
| "errors": 155, | |
| "risk": 0.41005291005291006, | |
| "coverage": 0.756, | |
| "coverage_of_all_cases": 0.756 | |
| }, | |
| { | |
| "threshold": 0.6031033396720886, | |
| "accepted": 379, | |
| "errors": 156, | |
| "risk": 0.41160949868073876, | |
| "coverage": 0.758, | |
| "coverage_of_all_cases": 0.758 | |
| }, | |
| { | |
| "threshold": 0.5993398427963257, | |
| "accepted": 380, | |
| "errors": 157, | |
| "risk": 0.4131578947368421, | |
| "coverage": 0.76, | |
| "coverage_of_all_cases": 0.76 | |
| }, | |
| { | |
| "threshold": 0.5938220620155334, | |
| "accepted": 381, | |
| "errors": 158, | |
| "risk": 0.4146981627296588, | |
| "coverage": 0.762, | |
| "coverage_of_all_cases": 0.762 | |
| }, | |
| { | |
| "threshold": 0.5926666259765625, | |
| "accepted": 389, | |
| "errors": 165, | |
| "risk": 0.4241645244215938, | |
| "coverage": 0.778, | |
| "coverage_of_all_cases": 0.778 | |
| }, | |
| { | |
| "threshold": 0.5918123722076416, | |
| "accepted": 390, | |
| "errors": 165, | |
| "risk": 0.4230769230769231, | |
| "coverage": 0.78, | |
| "coverage_of_all_cases": 0.78 | |
| }, | |
| { | |
| "threshold": 0.5917949676513672, | |
| "accepted": 391, | |
| "errors": 165, | |
| "risk": 0.4219948849104859, | |
| "coverage": 0.782, | |
| "coverage_of_all_cases": 0.782 | |
| }, | |
| { | |
| "threshold": 0.5908620357513428, | |
| "accepted": 392, | |
| "errors": 165, | |
| "risk": 0.42091836734693877, | |
| "coverage": 0.784, | |
| "coverage_of_all_cases": 0.784 | |
| }, | |
| { | |
| "threshold": 0.5671053528785706, | |
| "accepted": 393, | |
| "errors": 165, | |
| "risk": 0.4198473282442748, | |
| "coverage": 0.786, | |
| "coverage_of_all_cases": 0.786 | |
| }, | |
| { | |
| "threshold": 0.562176525592804, | |
| "accepted": 403, | |
| "errors": 169, | |
| "risk": 0.41935483870967744, | |
| "coverage": 0.806, | |
| "coverage_of_all_cases": 0.806 | |
| }, | |
| { | |
| "threshold": 0.5611987113952637, | |
| "accepted": 404, | |
| "errors": 169, | |
| "risk": 0.4183168316831683, | |
| "coverage": 0.808, | |
| "coverage_of_all_cases": 0.808 | |
| }, | |
| { | |
| "threshold": 0.5589726567268372, | |
| "accepted": 405, | |
| "errors": 170, | |
| "risk": 0.41975308641975306, | |
| "coverage": 0.81, | |
| "coverage_of_all_cases": 0.81 | |
| }, | |
| { | |
| "threshold": 0.5530118942260742, | |
| "accepted": 406, | |
| "errors": 170, | |
| "risk": 0.4187192118226601, | |
| "coverage": 0.812, | |
| "coverage_of_all_cases": 0.812 | |
| }, | |
| { | |
| "threshold": 0.5517231822013855, | |
| "accepted": 407, | |
| "errors": 170, | |
| "risk": 0.4176904176904177, | |
| "coverage": 0.814, | |
| "coverage_of_all_cases": 0.814 | |
| }, | |
| { | |
| "threshold": 0.551541805267334, | |
| "accepted": 408, | |
| "errors": 170, | |
| "risk": 0.4166666666666667, | |
| "coverage": 0.816, | |
| "coverage_of_all_cases": 0.816 | |
| }, | |
| { | |
| "threshold": 0.5458376407623291, | |
| "accepted": 409, | |
| "errors": 171, | |
| "risk": 0.4180929095354523, | |
| "coverage": 0.818, | |
| "coverage_of_all_cases": 0.818 | |
| }, | |
| { | |
| "threshold": 0.5322266221046448, | |
| "accepted": 410, | |
| "errors": 172, | |
| "risk": 0.4195121951219512, | |
| "coverage": 0.82, | |
| "coverage_of_all_cases": 0.82 | |
| }, | |
| { | |
| "threshold": 0.531209409236908, | |
| "accepted": 429, | |
| "errors": 183, | |
| "risk": 0.42657342657342656, | |
| "coverage": 0.858, | |
| "coverage_of_all_cases": 0.858 | |
| }, | |
| { | |
| "threshold": 0.5276584029197693, | |
| "accepted": 430, | |
| "errors": 183, | |
| "risk": 0.4255813953488372, | |
| "coverage": 0.86, | |
| "coverage_of_all_cases": 0.86 | |
| }, | |
| { | |
| "threshold": 0.5233758091926575, | |
| "accepted": 431, | |
| "errors": 184, | |
| "risk": 0.42691415313225056, | |
| "coverage": 0.862, | |
| "coverage_of_all_cases": 0.862 | |
| }, | |
| { | |
| "threshold": 0.5232104063034058, | |
| "accepted": 432, | |
| "errors": 184, | |
| "risk": 0.42592592592592593, | |
| "coverage": 0.864, | |
| "coverage_of_all_cases": 0.864 | |
| }, | |
| { | |
| "threshold": 0.5189152359962463, | |
| "accepted": 433, | |
| "errors": 185, | |
| "risk": 0.42725173210161665, | |
| "coverage": 0.866, | |
| "coverage_of_all_cases": 0.866 | |
| }, | |
| { | |
| "threshold": 0.5183603763580322, | |
| "accepted": 434, | |
| "errors": 185, | |
| "risk": 0.42626728110599077, | |
| "coverage": 0.868, | |
| "coverage_of_all_cases": 0.868 | |
| }, | |
| { | |
| "threshold": 0.5116807222366333, | |
| "accepted": 435, | |
| "errors": 185, | |
| "risk": 0.42528735632183906, | |
| "coverage": 0.87, | |
| "coverage_of_all_cases": 0.87 | |
| }, | |
| { | |
| "threshold": 0.5094732046127319, | |
| "accepted": 436, | |
| "errors": 185, | |
| "risk": 0.4243119266055046, | |
| "coverage": 0.872, | |
| "coverage_of_all_cases": 0.872 | |
| }, | |
| { | |
| "threshold": 0.5089282393455505, | |
| "accepted": 437, | |
| "errors": 185, | |
| "risk": 0.4233409610983982, | |
| "coverage": 0.874, | |
| "coverage_of_all_cases": 0.874 | |
| }, | |
| { | |
| "threshold": 0.5075972676277161, | |
| "accepted": 438, | |
| "errors": 185, | |
| "risk": 0.4223744292237443, | |
| "coverage": 0.876, | |
| "coverage_of_all_cases": 0.876 | |
| }, | |
| { | |
| "threshold": 0.5008364915847778, | |
| "accepted": 439, | |
| "errors": 185, | |
| "risk": 0.4214123006833713, | |
| "coverage": 0.878, | |
| "coverage_of_all_cases": 0.878 | |
| }, | |
| { | |
| "threshold": 0.5, | |
| "accepted": 443, | |
| "errors": 187, | |
| "risk": 0.4221218961625282, | |
| "coverage": 0.886, | |
| "coverage_of_all_cases": 0.886 | |
| }, | |
| { | |
| "threshold": 0.4995827078819275, | |
| "accepted": 444, | |
| "errors": 187, | |
| "risk": 0.42117117117117114, | |
| "coverage": 0.888, | |
| "coverage_of_all_cases": 0.888 | |
| }, | |
| { | |
| "threshold": 0.49904268980026245, | |
| "accepted": 445, | |
| "errors": 188, | |
| "risk": 0.42247191011235957, | |
| "coverage": 0.89, | |
| "coverage_of_all_cases": 0.89 | |
| }, | |
| { | |
| "threshold": 0.4959777295589447, | |
| "accepted": 446, | |
| "errors": 189, | |
| "risk": 0.42376681614349776, | |
| "coverage": 0.892, | |
| "coverage_of_all_cases": 0.892 | |
| }, | |
| { | |
| "threshold": 0.49295759201049805, | |
| "accepted": 447, | |
| "errors": 190, | |
| "risk": 0.4250559284116331, | |
| "coverage": 0.894, | |
| "coverage_of_all_cases": 0.894 | |
| }, | |
| { | |
| "threshold": 0.4927632808685303, | |
| "accepted": 448, | |
| "errors": 191, | |
| "risk": 0.4263392857142857, | |
| "coverage": 0.896, | |
| "coverage_of_all_cases": 0.896 | |
| }, | |
| { | |
| "threshold": 0.4887027442455292, | |
| "accepted": 449, | |
| "errors": 191, | |
| "risk": 0.42538975501113585, | |
| "coverage": 0.898, | |
| "coverage_of_all_cases": 0.898 | |
| }, | |
| { | |
| "threshold": 0.48547816276550293, | |
| "accepted": 450, | |
| "errors": 192, | |
| "risk": 0.4266666666666667, | |
| "coverage": 0.9, | |
| "coverage_of_all_cases": 0.9 | |
| }, | |
| { | |
| "threshold": 0.4829995036125183, | |
| "accepted": 451, | |
| "errors": 192, | |
| "risk": 0.42572062084257206, | |
| "coverage": 0.902, | |
| "coverage_of_all_cases": 0.902 | |
| }, | |
| { | |
| "threshold": 0.48047542572021484, | |
| "accepted": 452, | |
| "errors": 192, | |
| "risk": 0.4247787610619469, | |
| "coverage": 0.904, | |
| "coverage_of_all_cases": 0.904 | |
| }, | |
| { | |
| "threshold": 0.4799308776855469, | |
| "accepted": 453, | |
| "errors": 192, | |
| "risk": 0.423841059602649, | |
| "coverage": 0.906, | |
| "coverage_of_all_cases": 0.906 | |
| }, | |
| { | |
| "threshold": 0.4744885265827179, | |
| "accepted": 454, | |
| "errors": 193, | |
| "risk": 0.4251101321585903, | |
| "coverage": 0.908, | |
| "coverage_of_all_cases": 0.908 | |
| }, | |
| { | |
| "threshold": 0.47312700748443604, | |
| "accepted": 455, | |
| "errors": 193, | |
| "risk": 0.42417582417582417, | |
| "coverage": 0.91, | |
| "coverage_of_all_cases": 0.91 | |
| }, | |
| { | |
| "threshold": 0.467061847448349, | |
| "accepted": 456, | |
| "errors": 194, | |
| "risk": 0.42543859649122806, | |
| "coverage": 0.912, | |
| "coverage_of_all_cases": 0.912 | |
| }, | |
| { | |
| "threshold": 0.4606798589229584, | |
| "accepted": 457, | |
| "errors": 194, | |
| "risk": 0.424507658643326, | |
| "coverage": 0.914, | |
| "coverage_of_all_cases": 0.914 | |
| }, | |
| { | |
| "threshold": 0.4592236876487732, | |
| "accepted": 458, | |
| "errors": 195, | |
| "risk": 0.425764192139738, | |
| "coverage": 0.916, | |
| "coverage_of_all_cases": 0.916 | |
| }, | |
| { | |
| "threshold": 0.45840150117874146, | |
| "accepted": 459, | |
| "errors": 196, | |
| "risk": 0.42701525054466233, | |
| "coverage": 0.918, | |
| "coverage_of_all_cases": 0.918 | |
| }, | |
| { | |
| "threshold": 0.4578132927417755, | |
| "accepted": 460, | |
| "errors": 197, | |
| "risk": 0.4282608695652174, | |
| "coverage": 0.92, | |
| "coverage_of_all_cases": 0.92 | |
| }, | |
| { | |
| "threshold": 0.4528372883796692, | |
| "accepted": 461, | |
| "errors": 198, | |
| "risk": 0.42950108459869846, | |
| "coverage": 0.922, | |
| "coverage_of_all_cases": 0.922 | |
| }, | |
| { | |
| "threshold": 0.4507998526096344, | |
| "accepted": 462, | |
| "errors": 199, | |
| "risk": 0.43073593073593075, | |
| "coverage": 0.924, | |
| "coverage_of_all_cases": 0.924 | |
| }, | |
| { | |
| "threshold": 0.45054611563682556, | |
| "accepted": 463, | |
| "errors": 199, | |
| "risk": 0.4298056155507559, | |
| "coverage": 0.926, | |
| "coverage_of_all_cases": 0.926 | |
| }, | |
| { | |
| "threshold": 0.4486235976219177, | |
| "accepted": 464, | |
| "errors": 199, | |
| "risk": 0.42887931034482757, | |
| "coverage": 0.928, | |
| "coverage_of_all_cases": 0.928 | |
| }, | |
| { | |
| "threshold": 0.4485408365726471, | |
| "accepted": 465, | |
| "errors": 199, | |
| "risk": 0.42795698924731185, | |
| "coverage": 0.93, | |
| "coverage_of_all_cases": 0.93 | |
| }, | |
| { | |
| "threshold": 0.44471532106399536, | |
| "accepted": 466, | |
| "errors": 200, | |
| "risk": 0.4291845493562232, | |
| "coverage": 0.932, | |
| "coverage_of_all_cases": 0.932 | |
| }, | |
| { | |
| "threshold": 0.44102469086647034, | |
| "accepted": 467, | |
| "errors": 200, | |
| "risk": 0.4282655246252677, | |
| "coverage": 0.934, | |
| "coverage_of_all_cases": 0.934 | |
| }, | |
| { | |
| "threshold": 0.4407407343387604, | |
| "accepted": 468, | |
| "errors": 201, | |
| "risk": 0.42948717948717946, | |
| "coverage": 0.936, | |
| "coverage_of_all_cases": 0.936 | |
| }, | |
| { | |
| "threshold": 0.4385104775428772, | |
| "accepted": 469, | |
| "errors": 202, | |
| "risk": 0.43070362473347545, | |
| "coverage": 0.938, | |
| "coverage_of_all_cases": 0.938 | |
| }, | |
| { | |
| "threshold": 0.4384525418281555, | |
| "accepted": 470, | |
| "errors": 203, | |
| "risk": 0.4319148936170213, | |
| "coverage": 0.94, | |
| "coverage_of_all_cases": 0.94 | |
| }, | |
| { | |
| "threshold": 0.4366549551486969, | |
| "accepted": 471, | |
| "errors": 203, | |
| "risk": 0.4309978768577495, | |
| "coverage": 0.942, | |
| "coverage_of_all_cases": 0.942 | |
| }, | |
| { | |
| "threshold": 0.4295373260974884, | |
| "accepted": 472, | |
| "errors": 203, | |
| "risk": 0.4300847457627119, | |
| "coverage": 0.944, | |
| "coverage_of_all_cases": 0.944 | |
| }, | |
| { | |
| "threshold": 0.41273167729377747, | |
| "accepted": 473, | |
| "errors": 204, | |
| "risk": 0.4312896405919662, | |
| "coverage": 0.946, | |
| "coverage_of_all_cases": 0.946 | |
| }, | |
| { | |
| "threshold": 0.4120121896266937, | |
| "accepted": 474, | |
| "errors": 205, | |
| "risk": 0.43248945147679324, | |
| "coverage": 0.948, | |
| "coverage_of_all_cases": 0.948 | |
| }, | |
| { | |
| "threshold": 0.4117083251476288, | |
| "accepted": 475, | |
| "errors": 206, | |
| "risk": 0.4336842105263158, | |
| "coverage": 0.95, | |
| "coverage_of_all_cases": 0.95 | |
| }, | |
| { | |
| "threshold": 0.4114023745059967, | |
| "accepted": 476, | |
| "errors": 206, | |
| "risk": 0.4327731092436975, | |
| "coverage": 0.952, | |
| "coverage_of_all_cases": 0.952 | |
| }, | |
| { | |
| "threshold": 0.4086155593395233, | |
| "accepted": 477, | |
| "errors": 206, | |
| "risk": 0.43186582809224316, | |
| "coverage": 0.954, | |
| "coverage_of_all_cases": 0.954 | |
| }, | |
| { | |
| "threshold": 0.4078390300273895, | |
| "accepted": 478, | |
| "errors": 207, | |
| "risk": 0.4330543933054393, | |
| "coverage": 0.956, | |
| "coverage_of_all_cases": 0.956 | |
| }, | |
| { | |
| "threshold": 0.40543511509895325, | |
| "accepted": 479, | |
| "errors": 208, | |
| "risk": 0.4342379958246347, | |
| "coverage": 0.958, | |
| "coverage_of_all_cases": 0.958 | |
| }, | |
| { | |
| "threshold": 0.40363508462905884, | |
| "accepted": 480, | |
| "errors": 209, | |
| "risk": 0.4354166666666667, | |
| "coverage": 0.96, | |
| "coverage_of_all_cases": 0.96 | |
| }, | |
| { | |
| "threshold": 0.39988386631011963, | |
| "accepted": 481, | |
| "errors": 209, | |
| "risk": 0.43451143451143454, | |
| "coverage": 0.962, | |
| "coverage_of_all_cases": 0.962 | |
| }, | |
| { | |
| "threshold": 0.39853549003601074, | |
| "accepted": 482, | |
| "errors": 209, | |
| "risk": 0.4336099585062241, | |
| "coverage": 0.964, | |
| "coverage_of_all_cases": 0.964 | |
| }, | |
| { | |
| "threshold": 0.39815688133239746, | |
| "accepted": 483, | |
| "errors": 209, | |
| "risk": 0.432712215320911, | |
| "coverage": 0.966, | |
| "coverage_of_all_cases": 0.966 | |
| }, | |
| { | |
| "threshold": 0.3924981653690338, | |
| "accepted": 484, | |
| "errors": 209, | |
| "risk": 0.4318181818181818, | |
| "coverage": 0.968, | |
| "coverage_of_all_cases": 0.968 | |
| }, | |
| { | |
| "threshold": 0.38822588324546814, | |
| "accepted": 485, | |
| "errors": 210, | |
| "risk": 0.4329896907216495, | |
| "coverage": 0.97, | |
| "coverage_of_all_cases": 0.97 | |
| }, | |
| { | |
| "threshold": 0.37634944915771484, | |
| "accepted": 486, | |
| "errors": 210, | |
| "risk": 0.43209876543209874, | |
| "coverage": 0.972, | |
| "coverage_of_all_cases": 0.972 | |
| }, | |
| { | |
| "threshold": 0.37376707792282104, | |
| "accepted": 487, | |
| "errors": 210, | |
| "risk": 0.43121149897330596, | |
| "coverage": 0.974, | |
| "coverage_of_all_cases": 0.974 | |
| }, | |
| { | |
| "threshold": 0.37324216961860657, | |
| "accepted": 488, | |
| "errors": 211, | |
| "risk": 0.4323770491803279, | |
| "coverage": 0.976, | |
| "coverage_of_all_cases": 0.976 | |
| }, | |
| { | |
| "threshold": 0.3670387864112854, | |
| "accepted": 489, | |
| "errors": 212, | |
| "risk": 0.4335378323108384, | |
| "coverage": 0.978, | |
| "coverage_of_all_cases": 0.978 | |
| }, | |
| { | |
| "threshold": 0.3566589057445526, | |
| "accepted": 490, | |
| "errors": 212, | |
| "risk": 0.4326530612244898, | |
| "coverage": 0.98, | |
| "coverage_of_all_cases": 0.98 | |
| }, | |
| { | |
| "threshold": 0.3427278399467468, | |
| "accepted": 491, | |
| "errors": 212, | |
| "risk": 0.4317718940936864, | |
| "coverage": 0.982, | |
| "coverage_of_all_cases": 0.982 | |
| }, | |
| { | |
| "threshold": 0.3412012755870819, | |
| "accepted": 492, | |
| "errors": 213, | |
| "risk": 0.4329268292682927, | |
| "coverage": 0.984, | |
| "coverage_of_all_cases": 0.984 | |
| }, | |
| { | |
| "threshold": 0.33939439058303833, | |
| "accepted": 493, | |
| "errors": 214, | |
| "risk": 0.4340770791075051, | |
| "coverage": 0.986, | |
| "coverage_of_all_cases": 0.986 | |
| }, | |
| { | |
| "threshold": 0.3313635587692261, | |
| "accepted": 494, | |
| "errors": 215, | |
| "risk": 0.4352226720647773, | |
| "coverage": 0.988, | |
| "coverage_of_all_cases": 0.988 | |
| }, | |
| { | |
| "threshold": 0.3242751955986023, | |
| "accepted": 495, | |
| "errors": 216, | |
| "risk": 0.43636363636363634, | |
| "coverage": 0.99, | |
| "coverage_of_all_cases": 0.99 | |
| }, | |
| { | |
| "threshold": 0.32388773560523987, | |
| "accepted": 496, | |
| "errors": 217, | |
| "risk": 0.4375, | |
| "coverage": 0.992, | |
| "coverage_of_all_cases": 0.992 | |
| }, | |
| { | |
| "threshold": 0.3165428340435028, | |
| "accepted": 497, | |
| "errors": 217, | |
| "risk": 0.43661971830985913, | |
| "coverage": 0.994, | |
| "coverage_of_all_cases": 0.994 | |
| }, | |
| { | |
| "threshold": 0.30359888076782227, | |
| "accepted": 498, | |
| "errors": 218, | |
| "risk": 0.43775100401606426, | |
| "coverage": 0.996, | |
| "coverage_of_all_cases": 0.996 | |
| }, | |
| { | |
| "threshold": 0.29851505160331726, | |
| "accepted": 499, | |
| "errors": 218, | |
| "risk": 0.43687374749499, | |
| "coverage": 0.998, | |
| "coverage_of_all_cases": 0.998 | |
| }, | |
| { | |
| "threshold": 0.2401656061410904, | |
| "accepted": 500, | |
| "errors": 219, | |
| "risk": 0.438, | |
| "coverage": 1.0, | |
| "coverage_of_all_cases": 1.0 | |
| } | |
| ] | |
| }, | |
| "probability_incomplete": 0, | |
| "latency_ms": { | |
| "count": 500, | |
| "mean": 13.88489899187698, | |
| "p50": 13.126238001859747, | |
| "p95": 13.366747045802185, | |
| "min": 12.821044001611881, | |
| "max": 381.0723770002369 | |
| }, | |
| "wall_latency_ms": { | |
| "count": 500, | |
| "mean": 15.640008546062745, | |
| "p50": 14.080548004130833, | |
| "p95": 18.12442850350635, | |
| "min": 13.435001004836522, | |
| "max": 399.4759330089437 | |
| }, | |
| "input_tokens": { | |
| "count": 500, | |
| "mean": 309.888, | |
| "p50": 202.0, | |
| "p95": 888.1499999999999, | |
| "min": 108.0, | |
| "max": 1631.0 | |
| }, | |
| "state_characters": { | |
| "count": 500, | |
| "mean": 571.486, | |
| "p50": 199.5, | |
| "p95": 2825.1, | |
| "min": 10.0, | |
| "max": 6317.0 | |
| }, | |
| "notes": [ | |
| "accuracy_all counts errors and skips as incorrect", | |
| "accuracy_attempted and family macro count errors as wrong and exclude intentional skips", | |
| "family defaults to source; latency_ms is local forward-pass or hosted HTTP time", | |
| "wall_latency_ms includes per-record scorer preprocessing and inference; no warmup excluded", | |
| "F1 uses semantic option keys, never shuffled answer letters", | |
| "Probability metrics only include explicitly complete distributions" | |
| ] | |
| }, | |
| "decision": { | |
| "count": 500, | |
| "attempted": 500, | |
| "scored": 500, | |
| "errors": 0, | |
| "skipped": 0, | |
| "accuracy_all": 0.796, | |
| "accuracy_attempted": 0.796, | |
| "accuracy_scored": 0.796, | |
| "accuracy_family_macro": 0.796, | |
| "accuracy_by_family": { | |
| "clinc150": 0.89, | |
| "go_emotions": 0.82, | |
| "helpsteer2": 0.47, | |
| "paws": 0.92, | |
| "vitaminc": 0.88 | |
| }, | |
| "by_source": { | |
| "clinc150": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.89, | |
| "accuracy_attempted": 0.89, | |
| "macro_f1_scored": 0.8532776100920981, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "go_emotions": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.82, | |
| "accuracy_attempted": 0.82, | |
| "macro_f1_scored": 0.8197115384615384, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "helpsteer2": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.47, | |
| "accuracy_attempted": 0.47, | |
| "macro_f1_scored": 0.24495552607007715, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "paws": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.92, | |
| "accuracy_attempted": 0.92, | |
| "macro_f1_scored": 0.9184006527947777, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| }, | |
| "vitaminc": { | |
| "count": 100, | |
| "scored": 100, | |
| "accuracy_all": 0.88, | |
| "accuracy_attempted": 0.88, | |
| "macro_f1_scored": 0.8224019167415394, | |
| "macro_f1_note": "Semantic option keys on successful cases; undefined for keys without shared semantics." | |
| } | |
| }, | |
| "probability_metrics": { | |
| "count": 500, | |
| "brier_multiclass_sum": 0.2777899383756419, | |
| "nll": 0.505363078857301, | |
| "infinite_nll_cases": 0, | |
| "ece": 0.06087935093045237, | |
| "ece_equal_width_bins": 15, | |
| "aurc": 0.059849012978785913, | |
| "coverage_at_error": { | |
| "0.01": 0.224, | |
| "0.05": 0.538, | |
| "0.1": 0.736 | |
| }, | |
| "risk_coverage_note": "Empirical diagnostic, not a held-out error guarantee; whole ties accepted.", | |
| "risk_coverage": [ | |
| { | |
| "threshold": 0.9999735355377197, | |
| "accepted": 1, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.002, | |
| "coverage_of_all_cases": 0.002 | |
| }, | |
| { | |
| "threshold": 0.9999445676803589, | |
| "accepted": 2, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.004, | |
| "coverage_of_all_cases": 0.004 | |
| }, | |
| { | |
| "threshold": 0.9999101161956787, | |
| "accepted": 3, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.006, | |
| "coverage_of_all_cases": 0.006 | |
| }, | |
| { | |
| "threshold": 0.9998934268951416, | |
| "accepted": 4, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.008, | |
| "coverage_of_all_cases": 0.008 | |
| }, | |
| { | |
| "threshold": 0.9998823404312134, | |
| "accepted": 5, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.01, | |
| "coverage_of_all_cases": 0.01 | |
| }, | |
| { | |
| "threshold": 0.9998712539672852, | |
| "accepted": 6, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.012, | |
| "coverage_of_all_cases": 0.012 | |
| }, | |
| { | |
| "threshold": 0.9998680353164673, | |
| "accepted": 7, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.014, | |
| "coverage_of_all_cases": 0.014 | |
| }, | |
| { | |
| "threshold": 0.9998672008514404, | |
| "accepted": 8, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.016, | |
| "coverage_of_all_cases": 0.016 | |
| }, | |
| { | |
| "threshold": 0.9998639822006226, | |
| "accepted": 9, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.018, | |
| "coverage_of_all_cases": 0.018 | |
| }, | |
| { | |
| "threshold": 0.9998088479042053, | |
| "accepted": 10, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.02, | |
| "coverage_of_all_cases": 0.02 | |
| }, | |
| { | |
| "threshold": 0.9997724890708923, | |
| "accepted": 11, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.022, | |
| "coverage_of_all_cases": 0.022 | |
| }, | |
| { | |
| "threshold": 0.9997699856758118, | |
| "accepted": 12, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.024, | |
| "coverage_of_all_cases": 0.024 | |
| }, | |
| { | |
| "threshold": 0.9997448325157166, | |
| "accepted": 13, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.026, | |
| "coverage_of_all_cases": 0.026 | |
| }, | |
| { | |
| "threshold": 0.9997394680976868, | |
| "accepted": 14, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.028, | |
| "coverage_of_all_cases": 0.028 | |
| }, | |
| { | |
| "threshold": 0.9997389912605286, | |
| "accepted": 15, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.03, | |
| "coverage_of_all_cases": 0.03 | |
| }, | |
| { | |
| "threshold": 0.9997261166572571, | |
| "accepted": 16, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.032, | |
| "coverage_of_all_cases": 0.032 | |
| }, | |
| { | |
| "threshold": 0.9996552467346191, | |
| "accepted": 17, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.034, | |
| "coverage_of_all_cases": 0.034 | |
| }, | |
| { | |
| "threshold": 0.9996521472930908, | |
| "accepted": 18, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.036, | |
| "coverage_of_all_cases": 0.036 | |
| }, | |
| { | |
| "threshold": 0.9996479749679565, | |
| "accepted": 19, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.038, | |
| "coverage_of_all_cases": 0.038 | |
| }, | |
| { | |
| "threshold": 0.9996206760406494, | |
| "accepted": 20, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.04, | |
| "coverage_of_all_cases": 0.04 | |
| }, | |
| { | |
| "threshold": 0.9996199607849121, | |
| "accepted": 21, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.042, | |
| "coverage_of_all_cases": 0.042 | |
| }, | |
| { | |
| "threshold": 0.9996001124382019, | |
| "accepted": 22, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.044, | |
| "coverage_of_all_cases": 0.044 | |
| }, | |
| { | |
| "threshold": 0.9995810389518738, | |
| "accepted": 23, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.046, | |
| "coverage_of_all_cases": 0.046 | |
| }, | |
| { | |
| "threshold": 0.9995785355567932, | |
| "accepted": 24, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.048, | |
| "coverage_of_all_cases": 0.048 | |
| }, | |
| { | |
| "threshold": 0.9995694756507874, | |
| "accepted": 25, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.05, | |
| "coverage_of_all_cases": 0.05 | |
| }, | |
| { | |
| "threshold": 0.9995132684707642, | |
| "accepted": 26, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.052, | |
| "coverage_of_all_cases": 0.052 | |
| }, | |
| { | |
| "threshold": 0.9995096921920776, | |
| "accepted": 27, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.054, | |
| "coverage_of_all_cases": 0.054 | |
| }, | |
| { | |
| "threshold": 0.9994853734970093, | |
| "accepted": 28, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.056, | |
| "coverage_of_all_cases": 0.056 | |
| }, | |
| { | |
| "threshold": 0.9994520545005798, | |
| "accepted": 29, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.058, | |
| "coverage_of_all_cases": 0.058 | |
| }, | |
| { | |
| "threshold": 0.9994262456893921, | |
| "accepted": 30, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.06, | |
| "coverage_of_all_cases": 0.06 | |
| }, | |
| { | |
| "threshold": 0.9993928670883179, | |
| "accepted": 31, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.062, | |
| "coverage_of_all_cases": 0.062 | |
| }, | |
| { | |
| "threshold": 0.9993686079978943, | |
| "accepted": 32, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.064, | |
| "coverage_of_all_cases": 0.064 | |
| }, | |
| { | |
| "threshold": 0.9993294477462769, | |
| "accepted": 33, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.066, | |
| "coverage_of_all_cases": 0.066 | |
| }, | |
| { | |
| "threshold": 0.9991907477378845, | |
| "accepted": 34, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.068, | |
| "coverage_of_all_cases": 0.068 | |
| }, | |
| { | |
| "threshold": 0.999158501625061, | |
| "accepted": 35, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.07, | |
| "coverage_of_all_cases": 0.07 | |
| }, | |
| { | |
| "threshold": 0.9991039633750916, | |
| "accepted": 36, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.072, | |
| "coverage_of_all_cases": 0.072 | |
| }, | |
| { | |
| "threshold": 0.9991016387939453, | |
| "accepted": 37, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.074, | |
| "coverage_of_all_cases": 0.074 | |
| }, | |
| { | |
| "threshold": 0.9990731477737427, | |
| "accepted": 38, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.076, | |
| "coverage_of_all_cases": 0.076 | |
| }, | |
| { | |
| "threshold": 0.9990518689155579, | |
| "accepted": 39, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.078, | |
| "coverage_of_all_cases": 0.078 | |
| }, | |
| { | |
| "threshold": 0.9990272521972656, | |
| "accepted": 40, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.08, | |
| "coverage_of_all_cases": 0.08 | |
| }, | |
| { | |
| "threshold": 0.9990222454071045, | |
| "accepted": 41, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.082, | |
| "coverage_of_all_cases": 0.082 | |
| }, | |
| { | |
| "threshold": 0.9989677667617798, | |
| "accepted": 42, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.084, | |
| "coverage_of_all_cases": 0.084 | |
| }, | |
| { | |
| "threshold": 0.9989210367202759, | |
| "accepted": 43, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.086, | |
| "coverage_of_all_cases": 0.086 | |
| }, | |
| { | |
| "threshold": 0.9988304972648621, | |
| "accepted": 47, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.094, | |
| "coverage_of_all_cases": 0.094 | |
| }, | |
| { | |
| "threshold": 0.9987542629241943, | |
| "accepted": 48, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.096, | |
| "coverage_of_all_cases": 0.096 | |
| }, | |
| { | |
| "threshold": 0.9987351298332214, | |
| "accepted": 49, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.098, | |
| "coverage_of_all_cases": 0.098 | |
| }, | |
| { | |
| "threshold": 0.9986749291419983, | |
| "accepted": 50, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.1, | |
| "coverage_of_all_cases": 0.1 | |
| }, | |
| { | |
| "threshold": 0.9986598491668701, | |
| "accepted": 51, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.102, | |
| "coverage_of_all_cases": 0.102 | |
| }, | |
| { | |
| "threshold": 0.998505711555481, | |
| "accepted": 52, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.104, | |
| "coverage_of_all_cases": 0.104 | |
| }, | |
| { | |
| "threshold": 0.998498797416687, | |
| "accepted": 56, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.112, | |
| "coverage_of_all_cases": 0.112 | |
| }, | |
| { | |
| "threshold": 0.9983491897583008, | |
| "accepted": 57, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.114, | |
| "coverage_of_all_cases": 0.114 | |
| }, | |
| { | |
| "threshold": 0.9980939030647278, | |
| "accepted": 58, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.116, | |
| "coverage_of_all_cases": 0.116 | |
| }, | |
| { | |
| "threshold": 0.9980732202529907, | |
| "accepted": 61, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.122, | |
| "coverage_of_all_cases": 0.122 | |
| }, | |
| { | |
| "threshold": 0.9979864358901978, | |
| "accepted": 62, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.124, | |
| "coverage_of_all_cases": 0.124 | |
| }, | |
| { | |
| "threshold": 0.9978172779083252, | |
| "accepted": 64, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.128, | |
| "coverage_of_all_cases": 0.128 | |
| }, | |
| { | |
| "threshold": 0.9977349042892456, | |
| "accepted": 65, | |
| "errors": 0, | |
| "risk": 0.0, | |
| "coverage": 0.13, | |
| "coverage_of_all_cases": 0.13 | |
| }, | |
| { | |
| "threshold": 0.9975274205207825, | |
| "accepted": 67, | |
| "errors": 1, | |
| "risk": 0.014925373134328358, | |
| "coverage": 0.134, | |
| "coverage_of_all_cases": 0.134 | |
| }, | |
| { | |
| "threshold": 0.997403085231781, | |
| "accepted": 68, | |
| "errors": 1, | |
| "risk": 0.014705882352941176, | |
| "coverage": 0.136, | |
| "coverage_of_all_cases": 0.136 | |
| }, | |
| { | |
| "threshold": 0.9973710775375366, | |
| "accepted": 69, | |
| "errors": 1, | |
| "risk": 0.014492753623188406, | |
| "coverage": 0.138, | |
| "coverage_of_all_cases": 0.138 | |
| }, | |
| { | |
| "threshold": 0.9972979426383972, | |
| "accepted": 70, | |
| "errors": 1, | |
| "risk": 0.014285714285714285, | |
| "coverage": 0.14, | |
| "coverage_of_all_cases": 0.14 | |
| }, | |
| { | |
| "threshold": 0.9971990585327148, | |
| "accepted": 75, | |
| "errors": 1, | |
| "risk": 0.013333333333333334, | |
| "coverage": 0.15, | |
| "coverage_of_all_cases": 0.15 | |
| }, | |
| { | |
| "threshold": 0.9971904158592224, | |
| "accepted": 76, | |
| "errors": 1, | |
| "risk": 0.013157894736842105, | |
| "coverage": 0.152, | |
| "coverage_of_all_cases": 0.152 | |
| }, | |
| { | |
| "threshold": 0.9971832633018494, | |
| "accepted": 77, | |
| "errors": 1, | |
| "risk": 0.012987012987012988, | |
| "coverage": 0.154, | |
| "coverage_of_all_cases": 0.154 | |
| }, | |
| { | |
| "threshold": 0.997177004814148, | |
| "accepted": 78, | |
| "errors": 1, | |
| "risk": 0.01282051282051282, | |
| "coverage": 0.156, | |
| "coverage_of_all_cases": 0.156 | |
| }, | |
| { | |
| "threshold": 0.9971215128898621, | |
| "accepted": 79, | |
| "errors": 1, | |
| "risk": 0.012658227848101266, | |
| "coverage": 0.158, | |
| "coverage_of_all_cases": 0.158 | |
| }, | |
| { | |
| "threshold": 0.9968273043632507, | |
| "accepted": 81, | |
| "errors": 1, | |
| "risk": 0.012345679012345678, | |
| "coverage": 0.162, | |
| "coverage_of_all_cases": 0.162 | |
| }, | |
| { | |
| "threshold": 0.9968018531799316, | |
| "accepted": 82, | |
| "errors": 1, | |
| "risk": 0.012195121951219513, | |
| "coverage": 0.164, | |
| "coverage_of_all_cases": 0.164 | |
| }, | |
| { | |
| "threshold": 0.9967477321624756, | |
| "accepted": 83, | |
| "errors": 1, | |
| "risk": 0.012048192771084338, | |
| "coverage": 0.166, | |
| "coverage_of_all_cases": 0.166 | |
| }, | |
| { | |
| "threshold": 0.9964063763618469, | |
| "accepted": 86, | |
| "errors": 1, | |
| "risk": 0.011627906976744186, | |
| "coverage": 0.172, | |
| "coverage_of_all_cases": 0.172 | |
| }, | |
| { | |
| "threshold": 0.9963178634643555, | |
| "accepted": 87, | |
| "errors": 1, | |
| "risk": 0.011494252873563218, | |
| "coverage": 0.174, | |
| "coverage_of_all_cases": 0.174 | |
| }, | |
| { | |
| "threshold": 0.9962736368179321, | |
| "accepted": 88, | |
| "errors": 1, | |
| "risk": 0.011363636363636364, | |
| "coverage": 0.176, | |
| "coverage_of_all_cases": 0.176 | |
| }, | |
| { | |
| "threshold": 0.9962105751037598, | |
| "accepted": 89, | |
| "errors": 1, | |
| "risk": 0.011235955056179775, | |
| "coverage": 0.178, | |
| "coverage_of_all_cases": 0.178 | |
| }, | |
| { | |
| "threshold": 0.996036946773529, | |
| "accepted": 90, | |
| "errors": 1, | |
| "risk": 0.011111111111111112, | |
| "coverage": 0.18, | |
| "coverage_of_all_cases": 0.18 | |
| }, | |
| { | |
| "threshold": 0.9960172772407532, | |
| "accepted": 91, | |
| "errors": 1, | |
| "risk": 0.01098901098901099, | |
| "coverage": 0.182, | |
| "coverage_of_all_cases": 0.182 | |
| }, | |
| { | |
| "threshold": 0.9959298968315125, | |
| "accepted": 94, | |
| "errors": 1, | |
| "risk": 0.010638297872340425, | |
| "coverage": 0.188, | |
| "coverage_of_all_cases": 0.188 | |
| }, | |
| { | |
| "threshold": 0.995895266532898, | |
| "accepted": 95, | |
| "errors": 1, | |
| "risk": 0.010526315789473684, | |
| "coverage": 0.19, | |
| "coverage_of_all_cases": 0.19 | |
| }, | |
| { | |
| "threshold": 0.9957205653190613, | |
| "accepted": 96, | |
| "errors": 1, | |
| "risk": 0.010416666666666666, | |
| "coverage": 0.192, | |
| "coverage_of_all_cases": 0.192 | |
| }, | |
| { | |
| "threshold": 0.9954147338867188, | |
| "accepted": 97, | |
| "errors": 1, | |
| "risk": 0.010309278350515464, | |
| "coverage": 0.194, | |
| "coverage_of_all_cases": 0.194 | |
| }, | |
| { | |
| "threshold": 0.9953904151916504, | |
| "accepted": 100, | |
| "errors": 1, | |
| "risk": 0.01, | |
| "coverage": 0.2, | |
| "coverage_of_all_cases": 0.2 | |
| }, | |
| { | |
| "threshold": 0.9953085780143738, | |
| "accepted": 101, | |
| "errors": 1, | |
| "risk": 0.009900990099009901, | |
| "coverage": 0.202, | |
| "coverage_of_all_cases": 0.202 | |
| }, | |
| { | |
| "threshold": 0.9952681660652161, | |
| "accepted": 102, | |
| "errors": 1, | |
| "risk": 0.00980392156862745, | |
| "coverage": 0.204, | |
| "coverage_of_all_cases": 0.204 | |
| }, | |
| { | |
| "threshold": 0.9949561953544617, | |
| "accepted": 103, | |
| "errors": 1, | |
| "risk": 0.009708737864077669, | |
| "coverage": 0.206, | |
| "coverage_of_all_cases": 0.206 | |
| }, | |
| { | |
| "threshold": 0.9947799444198608, | |
| "accepted": 104, | |
| "errors": 1, | |
| "risk": 0.009615384615384616, | |
| "coverage": 0.208, | |
| "coverage_of_all_cases": 0.208 | |
| }, | |
| { | |
| "threshold": 0.9946382641792297, | |
| "accepted": 105, | |
| "errors": 1, | |
| "risk": 0.009523809523809525, | |
| "coverage": 0.21, | |
| "coverage_of_all_cases": 0.21 | |
| }, | |
| { | |
| "threshold": 0.9941325783729553, | |
| "accepted": 106, | |
| "errors": 1, | |
| "risk": 0.009433962264150943, | |
| "coverage": 0.212, | |
| "coverage_of_all_cases": 0.212 | |
| }, | |
| { | |
| "threshold": 0.9940890073776245, | |
| "accepted": 111, | |
| "errors": 1, | |
| "risk": 0.009009009009009009, | |
| "coverage": 0.222, | |
| "coverage_of_all_cases": 0.222 | |
| }, | |
| { | |
| "threshold": 0.9940752983093262, | |
| "accepted": 112, | |
| "errors": 1, | |
| "risk": 0.008928571428571428, | |
| "coverage": 0.224, | |
| "coverage_of_all_cases": 0.224 | |
| }, | |
| { | |
| "threshold": 0.9935334920883179, | |
| "accepted": 113, | |
| "errors": 2, | |
| "risk": 0.017699115044247787, | |
| "coverage": 0.226, | |
| "coverage_of_all_cases": 0.226 | |
| }, | |
| { | |
| "threshold": 0.9933071732521057, | |
| "accepted": 119, | |
| "errors": 2, | |
| "risk": 0.01680672268907563, | |
| "coverage": 0.238, | |
| "coverage_of_all_cases": 0.238 | |
| }, | |
| { | |
| "threshold": 0.9931272268295288, | |
| "accepted": 120, | |
| "errors": 2, | |
| "risk": 0.016666666666666666, | |
| "coverage": 0.24, | |
| "coverage_of_all_cases": 0.24 | |
| }, | |
| { | |
| "threshold": 0.9930804371833801, | |
| "accepted": 121, | |
| "errors": 2, | |
| "risk": 0.01652892561983471, | |
| "coverage": 0.242, | |
| "coverage_of_all_cases": 0.242 | |
| }, | |
| { | |
| "threshold": 0.9929484128952026, | |
| "accepted": 122, | |
| "errors": 2, | |
| "risk": 0.01639344262295082, | |
| "coverage": 0.244, | |
| "coverage_of_all_cases": 0.244 | |
| }, | |
| { | |
| "threshold": 0.9924227595329285, | |
| "accepted": 125, | |
| "errors": 2, | |
| "risk": 0.016, | |
| "coverage": 0.25, | |
| "coverage_of_all_cases": 0.25 | |
| }, | |
| { | |
| "threshold": 0.9924039244651794, | |
| "accepted": 126, | |
| "errors": 2, | |
| "risk": 0.015873015873015872, | |
| "coverage": 0.252, | |
| "coverage_of_all_cases": 0.252 | |
| }, | |
| { | |
| "threshold": 0.9918530583381653, | |
| "accepted": 127, | |
| "errors": 2, | |
| "risk": 0.015748031496062992, | |
| "coverage": 0.254, | |
| "coverage_of_all_cases": 0.254 | |
| }, | |
| { | |
| "threshold": 0.9914741516113281, | |
| "accepted": 128, | |
| "errors": 2, | |
| "risk": 0.015625, | |
| "coverage": 0.256, | |
| "coverage_of_all_cases": 0.256 | |
| }, | |
| { | |
| "threshold": 0.9914224743843079, | |
| "accepted": 133, | |
| "errors": 2, | |
| "risk": 0.015037593984962405, | |
| "coverage": 0.266, | |
| "coverage_of_all_cases": 0.266 | |
| }, | |
| { | |
| "threshold": 0.9902915358543396, | |
| "accepted": 137, | |
| "errors": 2, | |
| "risk": 0.014598540145985401, | |
| "coverage": 0.274, | |
| "coverage_of_all_cases": 0.274 | |
| }, | |
| { | |
| "threshold": 0.9901788234710693, | |
| "accepted": 138, | |
| "errors": 2, | |
| "risk": 0.014492753623188406, | |
| "coverage": 0.276, | |
| "coverage_of_all_cases": 0.276 | |
| }, | |
| { | |
| "threshold": 0.9900166392326355, | |
| "accepted": 139, | |
| "errors": 2, | |
| "risk": 0.014388489208633094, | |
| "coverage": 0.278, | |
| "coverage_of_all_cases": 0.278 | |
| }, | |
| { | |
| "threshold": 0.9890130758285522, | |
| "accepted": 143, | |
| "errors": 3, | |
| "risk": 0.02097902097902098, | |
| "coverage": 0.286, | |
| "coverage_of_all_cases": 0.286 | |
| }, | |
| { | |
| "threshold": 0.988907516002655, | |
| "accepted": 144, | |
| "errors": 4, | |
| "risk": 0.027777777777777776, | |
| "coverage": 0.288, | |
| "coverage_of_all_cases": 0.288 | |
| }, | |
| { | |
| "threshold": 0.9888833165168762, | |
| "accepted": 145, | |
| "errors": 4, | |
| "risk": 0.027586206896551724, | |
| "coverage": 0.29, | |
| "coverage_of_all_cases": 0.29 | |
| }, | |
| { | |
| "threshold": 0.9887046217918396, | |
| "accepted": 146, | |
| "errors": 4, | |
| "risk": 0.0273972602739726, | |
| "coverage": 0.292, | |
| "coverage_of_all_cases": 0.292 | |
| }, | |
| { | |
| "threshold": 0.9886802434921265, | |
| "accepted": 147, | |
| "errors": 4, | |
| "risk": 0.027210884353741496, | |
| "coverage": 0.294, | |
| "coverage_of_all_cases": 0.294 | |
| }, | |
| { | |
| "threshold": 0.9881565570831299, | |
| "accepted": 148, | |
| "errors": 4, | |
| "risk": 0.02702702702702703, | |
| "coverage": 0.296, | |
| "coverage_of_all_cases": 0.296 | |
| }, | |
| { | |
| "threshold": 0.9875683188438416, | |
| "accepted": 152, | |
| "errors": 4, | |
| "risk": 0.02631578947368421, | |
| "coverage": 0.304, | |
| "coverage_of_all_cases": 0.304 | |
| }, | |
| { | |
| "threshold": 0.9871735572814941, | |
| "accepted": 153, | |
| "errors": 4, | |
| "risk": 0.026143790849673203, | |
| "coverage": 0.306, | |
| "coverage_of_all_cases": 0.306 | |
| }, | |
| { | |
| "threshold": 0.9866006970405579, | |
| "accepted": 154, | |
| "errors": 4, | |
| "risk": 0.025974025974025976, | |
| "coverage": 0.308, | |
| "coverage_of_all_cases": 0.308 | |
| }, | |
| { | |
| "threshold": 0.9862913489341736, | |
| "accepted": 155, | |
| "errors": 4, | |
| "risk": 0.025806451612903226, | |
| "coverage": 0.31, | |
| "coverage_of_all_cases": 0.31 | |
| }, | |
| { | |
| "threshold": 0.9859364032745361, | |
| "accepted": 158, | |
| "errors": 4, | |
| "risk": 0.02531645569620253, | |
| "coverage": 0.316, | |
| "coverage_of_all_cases": 0.316 | |
| }, | |
| { | |
| "threshold": 0.985612154006958, | |
| "accepted": 159, | |
| "errors": 4, | |
| "risk": 0.025157232704402517, | |
| "coverage": 0.318, | |
| "coverage_of_all_cases": 0.318 | |
| }, | |
| { | |
| "threshold": 0.9849594235420227, | |
| "accepted": 160, | |
| "errors": 4, | |
| "risk": 0.025, | |
| "coverage": 0.32, | |
| "coverage_of_all_cases": 0.32 | |
| }, | |
| { | |
| "threshold": 0.9840936064720154, | |
| "accepted": 167, | |
| "errors": 4, | |
| "risk": 0.023952095808383235, | |
| "coverage": 0.334, | |
| "coverage_of_all_cases": 0.334 | |
| }, | |
| { | |
| "threshold": 0.9835327863693237, | |
| "accepted": 168, | |
| "errors": 4, | |
| "risk": 0.023809523809523808, | |
| "coverage": 0.336, | |
| "coverage_of_all_cases": 0.336 | |
| }, | |
| { | |
| "threshold": 0.9820137619972229, | |
| "accepted": 172, | |
| "errors": 4, | |
| "risk": 0.023255813953488372, | |
| "coverage": 0.344, | |
| "coverage_of_all_cases": 0.344 | |
| }, | |
| { | |
| "threshold": 0.9819797277450562, | |
| "accepted": 173, | |
| "errors": 4, | |
| "risk": 0.023121387283236993, | |
| "coverage": 0.346, | |
| "coverage_of_all_cases": 0.346 | |
| }, | |
| { | |
| "threshold": 0.9816007614135742, | |
| "accepted": 174, | |
| "errors": 4, | |
| "risk": 0.022988505747126436, | |
| "coverage": 0.348, | |
| "coverage_of_all_cases": 0.348 | |
| }, | |
| { | |
| "threshold": 0.9813809394836426, | |
| "accepted": 175, | |
| "errors": 4, | |
| "risk": 0.022857142857142857, | |
| "coverage": 0.35, | |
| "coverage_of_all_cases": 0.35 | |
| }, | |
| { | |
| "threshold": 0.9810402989387512, | |
| "accepted": 176, | |
| "errors": 4, | |
| "risk": 0.022727272727272728, | |
| "coverage": 0.352, | |
| "coverage_of_all_cases": 0.352 | |
| }, | |
| { | |
| "threshold": 0.980177640914917, | |
| "accepted": 177, | |
| "errors": 4, | |
| "risk": 0.022598870056497175, | |
| "coverage": 0.354, | |
| "coverage_of_all_cases": 0.354 | |
| }, | |
| { | |
| "threshold": 0.9796676635742188, | |
| "accepted": 178, | |
| "errors": 4, | |
| "risk": 0.02247191011235955, | |
| "coverage": 0.356, | |
| "coverage_of_all_cases": 0.356 | |
| }, | |
| { | |
| "threshold": 0.9794042110443115, | |
| "accepted": 179, | |
| "errors": 4, | |
| "risk": 0.0223463687150838, | |
| "coverage": 0.358, | |
| "coverage_of_all_cases": 0.358 | |
| }, | |
| { | |
| "threshold": 0.9792018532752991, | |
| "accepted": 180, | |
| "errors": 4, | |
| "risk": 0.022222222222222223, | |
| "coverage": 0.36, | |
| "coverage_of_all_cases": 0.36 | |
| }, | |
| { | |
| "threshold": 0.9782649278640747, | |
| "accepted": 182, | |
| "errors": 4, | |
| "risk": 0.02197802197802198, | |
| "coverage": 0.364, | |
| "coverage_of_all_cases": 0.364 | |
| }, | |
| { | |
| "threshold": 0.9775974154472351, | |
| "accepted": 183, | |
| "errors": 4, | |
| "risk": 0.02185792349726776, | |
| "coverage": 0.366, | |
| "coverage_of_all_cases": 0.366 | |
| }, | |
| { | |
| "threshold": 0.977022647857666, | |
| "accepted": 187, | |
| "errors": 5, | |
| "risk": 0.026737967914438502, | |
| "coverage": 0.374, | |
| "coverage_of_all_cases": 0.374 | |
| }, | |
| { | |
| "threshold": 0.9769793152809143, | |
| "accepted": 188, | |
| "errors": 5, | |
| "risk": 0.026595744680851064, | |
| "coverage": 0.376, | |
| "coverage_of_all_cases": 0.376 | |
| }, | |
| { | |
| "threshold": 0.9752546548843384, | |
| "accepted": 189, | |
| "errors": 5, | |
| "risk": 0.026455026455026454, | |
| "coverage": 0.378, | |
| "coverage_of_all_cases": 0.378 | |
| }, | |
| { | |
| "threshold": 0.9747056365013123, | |
| "accepted": 190, | |
| "errors": 5, | |
| "risk": 0.02631578947368421, | |
| "coverage": 0.38, | |
| "coverage_of_all_cases": 0.38 | |
| }, | |
| { | |
| "threshold": 0.974348783493042, | |
| "accepted": 192, | |
| "errors": 5, | |
| "risk": 0.026041666666666668, | |
| "coverage": 0.384, | |
| "coverage_of_all_cases": 0.384 | |
| }, | |
| { | |
| "threshold": 0.9740425944328308, | |
| "accepted": 197, | |
| "errors": 5, | |
| "risk": 0.025380710659898477, | |
| "coverage": 0.394, | |
| "coverage_of_all_cases": 0.394 | |
| }, | |
| { | |
| "threshold": 0.9737407565116882, | |
| "accepted": 198, | |
| "errors": 5, | |
| "risk": 0.025252525252525252, | |
| "coverage": 0.396, | |
| "coverage_of_all_cases": 0.396 | |
| }, | |
| { | |
| "threshold": 0.9735919833183289, | |
| "accepted": 199, | |
| "errors": 5, | |
| "risk": 0.02512562814070352, | |
| "coverage": 0.398, | |
| "coverage_of_all_cases": 0.398 | |
| }, | |
| { | |
| "threshold": 0.973451554775238, | |
| "accepted": 200, | |
| "errors": 5, | |
| "risk": 0.025, | |
| "coverage": 0.4, | |
| "coverage_of_all_cases": 0.4 | |
| }, | |
| { | |
| "threshold": 0.9720931649208069, | |
| "accepted": 201, | |
| "errors": 5, | |
| "risk": 0.024875621890547265, | |
| "coverage": 0.402, | |
| "coverage_of_all_cases": 0.402 | |
| }, | |
| { | |
| "threshold": 0.9720519185066223, | |
| "accepted": 202, | |
| "errors": 5, | |
| "risk": 0.024752475247524754, | |
| "coverage": 0.404, | |
| "coverage_of_all_cases": 0.404 | |
| }, | |
| { | |
| "threshold": 0.970687747001648, | |
| "accepted": 205, | |
| "errors": 5, | |
| "risk": 0.024390243902439025, | |
| "coverage": 0.41, | |
| "coverage_of_all_cases": 0.41 | |
| }, | |
| { | |
| "threshold": 0.9706328511238098, | |
| "accepted": 206, | |
| "errors": 5, | |
| "risk": 0.024271844660194174, | |
| "coverage": 0.412, | |
| "coverage_of_all_cases": 0.412 | |
| }, | |
| { | |
| "threshold": 0.9691205620765686, | |
| "accepted": 207, | |
| "errors": 5, | |
| "risk": 0.024154589371980676, | |
| "coverage": 0.414, | |
| "coverage_of_all_cases": 0.414 | |
| }, | |
| { | |
| "threshold": 0.9690893292427063, | |
| "accepted": 208, | |
| "errors": 5, | |
| "risk": 0.02403846153846154, | |
| "coverage": 0.416, | |
| "coverage_of_all_cases": 0.416 | |
| }, | |
| { | |
| "threshold": 0.9687411785125732, | |
| "accepted": 209, | |
| "errors": 6, | |
| "risk": 0.028708133971291867, | |
| "coverage": 0.418, | |
| "coverage_of_all_cases": 0.418 | |
| }, | |
| { | |
| "threshold": 0.9669140577316284, | |
| "accepted": 212, | |
| "errors": 6, | |
| "risk": 0.02830188679245283, | |
| "coverage": 0.424, | |
| "coverage_of_all_cases": 0.424 | |
| }, | |
| { | |
| "threshold": 0.9661662578582764, | |
| "accepted": 213, | |
| "errors": 6, | |
| "risk": 0.028169014084507043, | |
| "coverage": 0.426, | |
| "coverage_of_all_cases": 0.426 | |
| }, | |
| { | |
| "threshold": 0.964396595954895, | |
| "accepted": 215, | |
| "errors": 6, | |
| "risk": 0.027906976744186046, | |
| "coverage": 0.43, | |
| "coverage_of_all_cases": 0.43 | |
| }, | |
| { | |
| "threshold": 0.9636157155036926, | |
| "accepted": 216, | |
| "errors": 6, | |
| "risk": 0.027777777777777776, | |
| "coverage": 0.432, | |
| "coverage_of_all_cases": 0.432 | |
| }, | |
| { | |
| "threshold": 0.9635935425758362, | |
| "accepted": 219, | |
| "errors": 6, | |
| "risk": 0.0273972602739726, | |
| "coverage": 0.438, | |
| "coverage_of_all_cases": 0.438 | |
| }, | |
| { | |
| "threshold": 0.9626730680465698, | |
| "accepted": 223, | |
| "errors": 6, | |
| "risk": 0.026905829596412557, | |
| "coverage": 0.446, | |
| "coverage_of_all_cases": 0.446 | |
| }, | |
| { | |
| "threshold": 0.9626038074493408, | |
| "accepted": 224, | |
| "errors": 6, | |
| "risk": 0.026785714285714284, | |
| "coverage": 0.448, | |
| "coverage_of_all_cases": 0.448 | |
| }, | |
| { | |
| "threshold": 0.9618332982063293, | |
| "accepted": 225, | |
| "errors": 6, | |
| "risk": 0.02666666666666667, | |
| "coverage": 0.45, | |
| "coverage_of_all_cases": 0.45 | |
| }, | |
| { | |
| "threshold": 0.9615374803543091, | |
| "accepted": 226, | |
| "errors": 6, | |
| "risk": 0.02654867256637168, | |
| "coverage": 0.452, | |
| "coverage_of_all_cases": 0.452 | |
| }, | |
| { | |
| "threshold": 0.9601456522941589, | |
| "accepted": 227, | |
| "errors": 6, | |
| "risk": 0.02643171806167401, | |
| "coverage": 0.454, | |
| "coverage_of_all_cases": 0.454 | |
| }, | |
| { | |
| "threshold": 0.9589699506759644, | |
| "accepted": 228, | |
| "errors": 6, | |
| "risk": 0.02631578947368421, | |
| "coverage": 0.456, | |
| "coverage_of_all_cases": 0.456 | |
| }, | |
| { | |
| "threshold": 0.957912266254425, | |
| "accepted": 236, | |
| "errors": 7, | |
| "risk": 0.029661016949152543, | |
| "coverage": 0.472, | |
| "coverage_of_all_cases": 0.472 | |
| }, | |
| { | |
| "threshold": 0.9553418159484863, | |
| "accepted": 237, | |
| "errors": 8, | |
| "risk": 0.03375527426160337, | |
| "coverage": 0.474, | |
| "coverage_of_all_cases": 0.474 | |
| }, | |
| { | |
| "threshold": 0.9536817073822021, | |
| "accepted": 238, | |
| "errors": 8, | |
| "risk": 0.03361344537815126, | |
| "coverage": 0.476, | |
| "coverage_of_all_cases": 0.476 | |
| }, | |
| { | |
| "threshold": 0.9536725878715515, | |
| "accepted": 239, | |
| "errors": 8, | |
| "risk": 0.03347280334728033, | |
| "coverage": 0.478, | |
| "coverage_of_all_cases": 0.478 | |
| }, | |
| { | |
| "threshold": 0.9525741338729858, | |
| "accepted": 244, | |
| "errors": 8, | |
| "risk": 0.03278688524590164, | |
| "coverage": 0.488, | |
| "coverage_of_all_cases": 0.488 | |
| }, | |
| { | |
| "threshold": 0.9504899382591248, | |
| "accepted": 245, | |
| "errors": 8, | |
| "risk": 0.0326530612244898, | |
| "coverage": 0.49, | |
| "coverage_of_all_cases": 0.49 | |
| }, | |
| { | |
| "threshold": 0.9493986964225769, | |
| "accepted": 246, | |
| "errors": 8, | |
| "risk": 0.032520325203252036, | |
| "coverage": 0.492, | |
| "coverage_of_all_cases": 0.492 | |
| }, | |
| { | |
| "threshold": 0.9492290019989014, | |
| "accepted": 247, | |
| "errors": 8, | |
| "risk": 0.032388663967611336, | |
| "coverage": 0.494, | |
| "coverage_of_all_cases": 0.494 | |
| }, | |
| { | |
| "threshold": 0.9490231275558472, | |
| "accepted": 248, | |
| "errors": 8, | |
| "risk": 0.03225806451612903, | |
| "coverage": 0.496, | |
| "coverage_of_all_cases": 0.496 | |
| }, | |
| { | |
| "threshold": 0.9478920698165894, | |
| "accepted": 250, | |
| "errors": 8, | |
| "risk": 0.032, | |
| "coverage": 0.5, | |
| "coverage_of_all_cases": 0.5 | |
| }, | |
| { | |
| "threshold": 0.9465966820716858, | |
| "accepted": 257, | |
| "errors": 11, | |
| "risk": 0.042801556420233464, | |
| "coverage": 0.514, | |
| "coverage_of_all_cases": 0.514 | |
| }, | |
| { | |
| "threshold": 0.9459934234619141, | |
| "accepted": 258, | |
| "errors": 11, | |
| "risk": 0.04263565891472868, | |
| "coverage": 0.516, | |
| "coverage_of_all_cases": 0.516 | |
| }, | |
| { | |
| "threshold": 0.9447877407073975, | |
| "accepted": 259, | |
| "errors": 11, | |
| "risk": 0.04247104247104247, | |
| "coverage": 0.518, | |
| "coverage_of_all_cases": 0.518 | |
| }, | |
| { | |
| "threshold": 0.9423937797546387, | |
| "accepted": 260, | |
| "errors": 11, | |
| "risk": 0.04230769230769231, | |
| "coverage": 0.52, | |
| "coverage_of_all_cases": 0.52 | |
| }, | |
| { | |
| "threshold": 0.9399133324623108, | |
| "accepted": 266, | |
| "errors": 13, | |
| "risk": 0.04887218045112782, | |
| "coverage": 0.532, | |
| "coverage_of_all_cases": 0.532 | |
| }, | |
| { | |
| "threshold": 0.938907265663147, | |
| "accepted": 267, | |
| "errors": 13, | |
| "risk": 0.04868913857677903, | |
| "coverage": 0.534, | |
| "coverage_of_all_cases": 0.534 | |
| }, | |
| { | |
| "threshold": 0.9367460608482361, | |
| "accepted": 269, | |
| "errors": 13, | |
| "risk": 0.048327137546468404, | |
| "coverage": 0.538, | |
| "coverage_of_all_cases": 0.538 | |
| }, | |
| { | |
| "threshold": 0.9324532747268677, | |
| "accepted": 275, | |
| "errors": 14, | |
| "risk": 0.05090909090909091, | |
| "coverage": 0.55, | |
| "coverage_of_all_cases": 0.55 | |
| }, | |
| { | |
| "threshold": 0.9275103807449341, | |
| "accepted": 276, | |
| "errors": 14, | |
| "risk": 0.050724637681159424, | |
| "coverage": 0.552, | |
| "coverage_of_all_cases": 0.552 | |
| }, | |
| { | |
| "threshold": 0.9274784922599792, | |
| "accepted": 277, | |
| "errors": 14, | |
| "risk": 0.05054151624548736, | |
| "coverage": 0.554, | |
| "coverage_of_all_cases": 0.554 | |
| }, | |
| { | |
| "threshold": 0.9259392619132996, | |
| "accepted": 278, | |
| "errors": 14, | |
| "risk": 0.050359712230215826, | |
| "coverage": 0.556, | |
| "coverage_of_all_cases": 0.556 | |
| }, | |
| { | |
| "threshold": 0.9241418242454529, | |
| "accepted": 282, | |
| "errors": 15, | |
| "risk": 0.05319148936170213, | |
| "coverage": 0.564, | |
| "coverage_of_all_cases": 0.564 | |
| }, | |
| { | |
| "threshold": 0.9225048422813416, | |
| "accepted": 283, | |
| "errors": 15, | |
| "risk": 0.053003533568904596, | |
| "coverage": 0.566, | |
| "coverage_of_all_cases": 0.566 | |
| }, | |
| { | |
| "threshold": 0.9195862412452698, | |
| "accepted": 284, | |
| "errors": 15, | |
| "risk": 0.0528169014084507, | |
| "coverage": 0.568, | |
| "coverage_of_all_cases": 0.568 | |
| }, | |
| { | |
| "threshold": 0.9169458150863647, | |
| "accepted": 285, | |
| "errors": 15, | |
| "risk": 0.05263157894736842, | |
| "coverage": 0.57, | |
| "coverage_of_all_cases": 0.57 | |
| }, | |
| { | |
| "threshold": 0.9149009585380554, | |
| "accepted": 290, | |
| "errors": 15, | |
| "risk": 0.05172413793103448, | |
| "coverage": 0.58, | |
| "coverage_of_all_cases": 0.58 | |
| }, | |
| { | |
| "threshold": 0.9130832552909851, | |
| "accepted": 291, | |
| "errors": 16, | |
| "risk": 0.054982817869415807, | |
| "coverage": 0.582, | |
| "coverage_of_all_cases": 0.582 | |
| }, | |
| { | |
| "threshold": 0.9067503809928894, | |
| "accepted": 292, | |
| "errors": 17, | |
| "risk": 0.05821917808219178, | |
| "coverage": 0.584, | |
| "coverage_of_all_cases": 0.584 | |
| }, | |
| { | |
| "threshold": 0.905574381351471, | |
| "accepted": 293, | |
| "errors": 17, | |
| "risk": 0.05802047781569966, | |
| "coverage": 0.586, | |
| "coverage_of_all_cases": 0.586 | |
| }, | |
| { | |
| "threshold": 0.9046505093574524, | |
| "accepted": 301, | |
| "errors": 17, | |
| "risk": 0.05647840531561462, | |
| "coverage": 0.602, | |
| "coverage_of_all_cases": 0.602 | |
| }, | |
| { | |
| "threshold": 0.8992477059364319, | |
| "accepted": 302, | |
| "errors": 17, | |
| "risk": 0.056291390728476824, | |
| "coverage": 0.604, | |
| "coverage_of_all_cases": 0.604 | |
| }, | |
| { | |
| "threshold": 0.8961509466171265, | |
| "accepted": 303, | |
| "errors": 17, | |
| "risk": 0.056105610561056105, | |
| "coverage": 0.606, | |
| "coverage_of_all_cases": 0.606 | |
| }, | |
| { | |
| "threshold": 0.8933094143867493, | |
| "accepted": 308, | |
| "errors": 18, | |
| "risk": 0.05844155844155844, | |
| "coverage": 0.616, | |
| "coverage_of_all_cases": 0.616 | |
| }, | |
| { | |
| "threshold": 0.8925829529762268, | |
| "accepted": 309, | |
| "errors": 18, | |
| "risk": 0.05825242718446602, | |
| "coverage": 0.618, | |
| "coverage_of_all_cases": 0.618 | |
| }, | |
| { | |
| "threshold": 0.8921726942062378, | |
| "accepted": 310, | |
| "errors": 18, | |
| "risk": 0.05806451612903226, | |
| "coverage": 0.62, | |
| "coverage_of_all_cases": 0.62 | |
| }, | |
| { | |
| "threshold": 0.8913125991821289, | |
| "accepted": 311, | |
| "errors": 19, | |
| "risk": 0.06109324758842444, | |
| "coverage": 0.622, | |
| "coverage_of_all_cases": 0.622 | |
| }, | |
| { | |
| "threshold": 0.8879783749580383, | |
| "accepted": 312, | |
| "errors": 19, | |
| "risk": 0.060897435897435896, | |
| "coverage": 0.624, | |
| "coverage_of_all_cases": 0.624 | |
| }, | |
| { | |
| "threshold": 0.8807970285415649, | |
| "accepted": 316, | |
| "errors": 20, | |
| "risk": 0.06329113924050633, | |
| "coverage": 0.632, | |
| "coverage_of_all_cases": 0.632 | |
| }, | |
| { | |
| "threshold": 0.8783478140830994, | |
| "accepted": 318, | |
| "errors": 20, | |
| "risk": 0.06289308176100629, | |
| "coverage": 0.636, | |
| "coverage_of_all_cases": 0.636 | |
| }, | |
| { | |
| "threshold": 0.8670357465744019, | |
| "accepted": 323, | |
| "errors": 20, | |
| "risk": 0.06191950464396285, | |
| "coverage": 0.646, | |
| "coverage_of_all_cases": 0.646 | |
| }, | |
| { | |
| "threshold": 0.8653944134712219, | |
| "accepted": 324, | |
| "errors": 21, | |
| "risk": 0.06481481481481481, | |
| "coverage": 0.648, | |
| "coverage_of_all_cases": 0.648 | |
| }, | |
| { | |
| "threshold": 0.85527104139328, | |
| "accepted": 325, | |
| "errors": 21, | |
| "risk": 0.06461538461538462, | |
| "coverage": 0.65, | |
| "coverage_of_all_cases": 0.65 | |
| }, | |
| { | |
| "threshold": 0.851952850818634, | |
| "accepted": 327, | |
| "errors": 22, | |
| "risk": 0.0672782874617737, | |
| "coverage": 0.654, | |
| "coverage_of_all_cases": 0.654 | |
| }, | |
| { | |
| "threshold": 0.8447388410568237, | |
| "accepted": 328, | |
| "errors": 23, | |
| "risk": 0.0701219512195122, | |
| "coverage": 0.656, | |
| "coverage_of_all_cases": 0.656 | |
| }, | |
| { | |
| "threshold": 0.8354835510253906, | |
| "accepted": 330, | |
| "errors": 24, | |
| "risk": 0.07272727272727272, | |
| "coverage": 0.66, | |
| "coverage_of_all_cases": 0.66 | |
| }, | |
| { | |
| "threshold": 0.8344363570213318, | |
| "accepted": 331, | |
| "errors": 24, | |
| "risk": 0.07250755287009064, | |
| "coverage": 0.662, | |
| "coverage_of_all_cases": 0.662 | |
| }, | |
| { | |
| "threshold": 0.8338453769683838, | |
| "accepted": 332, | |
| "errors": 24, | |
| "risk": 0.07228915662650602, | |
| "coverage": 0.664, | |
| "coverage_of_all_cases": 0.664 | |
| }, | |
| { | |
| "threshold": 0.8175744414329529, | |
| "accepted": 335, | |
| "errors": 25, | |
| "risk": 0.07462686567164178, | |
| "coverage": 0.67, | |
| "coverage_of_all_cases": 0.67 | |
| }, | |
| { | |
| "threshold": 0.8162598013877869, | |
| "accepted": 336, | |
| "errors": 26, | |
| "risk": 0.07738095238095238, | |
| "coverage": 0.672, | |
| "coverage_of_all_cases": 0.672 | |
| }, | |
| { | |
| "threshold": 0.8092671036720276, | |
| "accepted": 337, | |
| "errors": 27, | |
| "risk": 0.08011869436201781, | |
| "coverage": 0.674, | |
| "coverage_of_all_cases": 0.674 | |
| }, | |
| { | |
| "threshold": 0.8059741258621216, | |
| "accepted": 338, | |
| "errors": 27, | |
| "risk": 0.07988165680473373, | |
| "coverage": 0.676, | |
| "coverage_of_all_cases": 0.676 | |
| }, | |
| { | |
| "threshold": 0.8023303151130676, | |
| "accepted": 339, | |
| "errors": 27, | |
| "risk": 0.07964601769911504, | |
| "coverage": 0.678, | |
| "coverage_of_all_cases": 0.678 | |
| }, | |
| { | |
| "threshold": 0.7981867790222168, | |
| "accepted": 341, | |
| "errors": 28, | |
| "risk": 0.08211143695014662, | |
| "coverage": 0.682, | |
| "coverage_of_all_cases": 0.682 | |
| }, | |
| { | |
| "threshold": 0.7880201935768127, | |
| "accepted": 342, | |
| "errors": 28, | |
| "risk": 0.08187134502923976, | |
| "coverage": 0.684, | |
| "coverage_of_all_cases": 0.684 | |
| }, | |
| { | |
| "threshold": 0.7878038883209229, | |
| "accepted": 343, | |
| "errors": 28, | |
| "risk": 0.08163265306122448, | |
| "coverage": 0.686, | |
| "coverage_of_all_cases": 0.686 | |
| }, | |
| { | |
| "threshold": 0.7832459807395935, | |
| "accepted": 344, | |
| "errors": 28, | |
| "risk": 0.08139534883720931, | |
| "coverage": 0.688, | |
| "coverage_of_all_cases": 0.688 | |
| }, | |
| { | |
| "threshold": 0.7772998809814453, | |
| "accepted": 348, | |
| "errors": 30, | |
| "risk": 0.08620689655172414, | |
| "coverage": 0.696, | |
| "coverage_of_all_cases": 0.696 | |
| }, | |
| { | |
| "threshold": 0.775981605052948, | |
| "accepted": 350, | |
| "errors": 30, | |
| "risk": 0.08571428571428572, | |
| "coverage": 0.7, | |
| "coverage_of_all_cases": 0.7 | |
| }, | |
| { | |
| "threshold": 0.7726686000823975, | |
| "accepted": 351, | |
| "errors": 30, | |
| "risk": 0.08547008547008547, | |
| "coverage": 0.702, | |
| "coverage_of_all_cases": 0.702 | |
| }, | |
| { | |
| "threshold": 0.7723005414009094, | |
| "accepted": 352, | |
| "errors": 30, | |
| "risk": 0.08522727272727272, | |
| "coverage": 0.704, | |
| "coverage_of_all_cases": 0.704 | |
| }, | |
| { | |
| "threshold": 0.7664576172828674, | |
| "accepted": 353, | |
| "errors": 31, | |
| "risk": 0.08781869688385269, | |
| "coverage": 0.706, | |
| "coverage_of_all_cases": 0.706 | |
| }, | |
| { | |
| "threshold": 0.7637927532196045, | |
| "accepted": 354, | |
| "errors": 31, | |
| "risk": 0.08757062146892655, | |
| "coverage": 0.708, | |
| "coverage_of_all_cases": 0.708 | |
| }, | |
| { | |
| "threshold": 0.7596794962882996, | |
| "accepted": 355, | |
| "errors": 31, | |
| "risk": 0.08732394366197183, | |
| "coverage": 0.71, | |
| "coverage_of_all_cases": 0.71 | |
| }, | |
| { | |
| "threshold": 0.7545579075813293, | |
| "accepted": 356, | |
| "errors": 31, | |
| "risk": 0.08707865168539326, | |
| "coverage": 0.712, | |
| "coverage_of_all_cases": 0.712 | |
| }, | |
| { | |
| "threshold": 0.743022620677948, | |
| "accepted": 357, | |
| "errors": 32, | |
| "risk": 0.0896358543417367, | |
| "coverage": 0.714, | |
| "coverage_of_all_cases": 0.714 | |
| }, | |
| { | |
| "threshold": 0.7375938296318054, | |
| "accepted": 358, | |
| "errors": 33, | |
| "risk": 0.09217877094972067, | |
| "coverage": 0.716, | |
| "coverage_of_all_cases": 0.716 | |
| }, | |
| { | |
| "threshold": 0.7334461212158203, | |
| "accepted": 359, | |
| "errors": 33, | |
| "risk": 0.09192200557103064, | |
| "coverage": 0.718, | |
| "coverage_of_all_cases": 0.718 | |
| }, | |
| { | |
| "threshold": 0.7312406301498413, | |
| "accepted": 360, | |
| "errors": 33, | |
| "risk": 0.09166666666666666, | |
| "coverage": 0.72, | |
| "coverage_of_all_cases": 0.72 | |
| }, | |
| { | |
| "threshold": 0.7310585379600525, | |
| "accepted": 361, | |
| "errors": 34, | |
| "risk": 0.09418282548476455, | |
| "coverage": 0.722, | |
| "coverage_of_all_cases": 0.722 | |
| }, | |
| { | |
| "threshold": 0.7306793332099915, | |
| "accepted": 362, | |
| "errors": 35, | |
| "risk": 0.09668508287292818, | |
| "coverage": 0.724, | |
| "coverage_of_all_cases": 0.724 | |
| }, | |
| { | |
| "threshold": 0.7252358794212341, | |
| "accepted": 363, | |
| "errors": 35, | |
| "risk": 0.09641873278236915, | |
| "coverage": 0.726, | |
| "coverage_of_all_cases": 0.726 | |
| }, | |
| { | |
| "threshold": 0.7236915230751038, | |
| "accepted": 364, | |
| "errors": 35, | |
| "risk": 0.09615384615384616, | |
| "coverage": 0.728, | |
| "coverage_of_all_cases": 0.728 | |
| }, | |
| { | |
| "threshold": 0.7212070822715759, | |
| "accepted": 365, | |
| "errors": 35, | |
| "risk": 0.0958904109589041, | |
| "coverage": 0.73, | |
| "coverage_of_all_cases": 0.73 | |
| }, | |
| { | |
| "threshold": 0.7184403538703918, | |
| "accepted": 366, | |
| "errors": 35, | |
| "risk": 0.09562841530054644, | |
| "coverage": 0.732, | |
| "coverage_of_all_cases": 0.732 | |
| }, | |
| { | |
| "threshold": 0.7170881628990173, | |
| "accepted": 367, | |
| "errors": 35, | |
| "risk": 0.09536784741144415, | |
| "coverage": 0.734, | |
| "coverage_of_all_cases": 0.734 | |
| }, | |
| { | |
| "threshold": 0.7113654613494873, | |
| "accepted": 368, | |
| "errors": 35, | |
| "risk": 0.09510869565217392, | |
| "coverage": 0.736, | |
| "coverage_of_all_cases": 0.736 | |
| }, | |
| { | |
| "threshold": 0.7057850360870361, | |
| "accepted": 375, | |
| "errors": 40, | |
| "risk": 0.10666666666666667, | |
| "coverage": 0.75, | |
| "coverage_of_all_cases": 0.75 | |
| }, | |
| { | |
| "threshold": 0.7041866183280945, | |
| "accepted": 376, | |
| "errors": 40, | |
| "risk": 0.10638297872340426, | |
| "coverage": 0.752, | |
| "coverage_of_all_cases": 0.752 | |
| }, | |
| { | |
| "threshold": 0.7012091279029846, | |
| "accepted": 377, | |
| "errors": 40, | |
| "risk": 0.10610079575596817, | |
| "coverage": 0.754, | |
| "coverage_of_all_cases": 0.754 | |
| }, | |
| { | |
| "threshold": 0.6941510438919067, | |
| "accepted": 378, | |
| "errors": 40, | |
| "risk": 0.10582010582010581, | |
| "coverage": 0.756, | |
| "coverage_of_all_cases": 0.756 | |
| }, | |
| { | |
| "threshold": 0.6927552819252014, | |
| "accepted": 379, | |
| "errors": 40, | |
| "risk": 0.10554089709762533, | |
| "coverage": 0.758, | |
| "coverage_of_all_cases": 0.758 | |
| }, | |
| { | |
| "threshold": 0.6924893260002136, | |
| "accepted": 380, | |
| "errors": 41, | |
| "risk": 0.10789473684210527, | |
| "coverage": 0.76, | |
| "coverage_of_all_cases": 0.76 | |
| }, | |
| { | |
| "threshold": 0.6808706521987915, | |
| "accepted": 381, | |
| "errors": 41, | |
| "risk": 0.10761154855643044, | |
| "coverage": 0.762, | |
| "coverage_of_all_cases": 0.762 | |
| }, | |
| { | |
| "threshold": 0.6778053641319275, | |
| "accepted": 382, | |
| "errors": 41, | |
| "risk": 0.10732984293193717, | |
| "coverage": 0.764, | |
| "coverage_of_all_cases": 0.764 | |
| }, | |
| { | |
| "threshold": 0.6768243312835693, | |
| "accepted": 383, | |
| "errors": 41, | |
| "risk": 0.10704960835509138, | |
| "coverage": 0.766, | |
| "coverage_of_all_cases": 0.766 | |
| }, | |
| { | |
| "threshold": 0.6765865683555603, | |
| "accepted": 384, | |
| "errors": 41, | |
| "risk": 0.10677083333333333, | |
| "coverage": 0.768, | |
| "coverage_of_all_cases": 0.768 | |
| }, | |
| { | |
| "threshold": 0.6739290356636047, | |
| "accepted": 385, | |
| "errors": 41, | |
| "risk": 0.10649350649350649, | |
| "coverage": 0.77, | |
| "coverage_of_all_cases": 0.77 | |
| }, | |
| { | |
| "threshold": 0.6624118089675903, | |
| "accepted": 386, | |
| "errors": 42, | |
| "risk": 0.10880829015544041, | |
| "coverage": 0.772, | |
| "coverage_of_all_cases": 0.772 | |
| }, | |
| { | |
| "threshold": 0.6598255038261414, | |
| "accepted": 387, | |
| "errors": 42, | |
| "risk": 0.10852713178294573, | |
| "coverage": 0.774, | |
| "coverage_of_all_cases": 0.774 | |
| }, | |
| { | |
| "threshold": 0.6513549089431763, | |
| "accepted": 389, | |
| "errors": 42, | |
| "risk": 0.10796915167095116, | |
| "coverage": 0.778, | |
| "coverage_of_all_cases": 0.778 | |
| }, | |
| { | |
| "threshold": 0.6512628793716431, | |
| "accepted": 390, | |
| "errors": 43, | |
| "risk": 0.11025641025641025, | |
| "coverage": 0.78, | |
| "coverage_of_all_cases": 0.78 | |
| }, | |
| { | |
| "threshold": 0.6456485390663147, | |
| "accepted": 391, | |
| "errors": 44, | |
| "risk": 0.11253196930946291, | |
| "coverage": 0.782, | |
| "coverage_of_all_cases": 0.782 | |
| }, | |
| { | |
| "threshold": 0.6442480087280273, | |
| "accepted": 392, | |
| "errors": 44, | |
| "risk": 0.11224489795918367, | |
| "coverage": 0.784, | |
| "coverage_of_all_cases": 0.784 | |
| }, | |
| { | |
| "threshold": 0.6381606459617615, | |
| "accepted": 393, | |
| "errors": 45, | |
| "risk": 0.11450381679389313, | |
| "coverage": 0.786, | |
| "coverage_of_all_cases": 0.786 | |
| }, | |
| { | |
| "threshold": 0.6370754837989807, | |
| "accepted": 394, | |
| "errors": 45, | |
| "risk": 0.11421319796954314, | |
| "coverage": 0.788, | |
| "coverage_of_all_cases": 0.788 | |
| }, | |
| { | |
| "threshold": 0.629304051399231, | |
| "accepted": 395, | |
| "errors": 46, | |
| "risk": 0.11645569620253164, | |
| "coverage": 0.79, | |
| "coverage_of_all_cases": 0.79 | |
| }, | |
| { | |
| "threshold": 0.6275349259376526, | |
| "accepted": 396, | |
| "errors": 46, | |
| "risk": 0.11616161616161616, | |
| "coverage": 0.792, | |
| "coverage_of_all_cases": 0.792 | |
| }, | |
| { | |
| "threshold": 0.622459352016449, | |
| "accepted": 398, | |
| "errors": 46, | |
| "risk": 0.11557788944723618, | |
| "coverage": 0.796, | |
| "coverage_of_all_cases": 0.796 | |
| }, | |
| { | |
| "threshold": 0.6181229948997498, | |
| "accepted": 399, | |
| "errors": 46, | |
| "risk": 0.11528822055137844, | |
| "coverage": 0.798, | |
| "coverage_of_all_cases": 0.798 | |
| }, | |
| { | |
| "threshold": 0.6141465306282043, | |
| "accepted": 400, | |
| "errors": 47, | |
| "risk": 0.1175, | |
| "coverage": 0.8, | |
| "coverage_of_all_cases": 0.8 | |
| }, | |
| { | |
| "threshold": 0.6095105409622192, | |
| "accepted": 401, | |
| "errors": 47, | |
| "risk": 0.1172069825436409, | |
| "coverage": 0.802, | |
| "coverage_of_all_cases": 0.802 | |
| }, | |
| { | |
| "threshold": 0.6091967225074768, | |
| "accepted": 402, | |
| "errors": 47, | |
| "risk": 0.11691542288557213, | |
| "coverage": 0.804, | |
| "coverage_of_all_cases": 0.804 | |
| }, | |
| { | |
| "threshold": 0.6043412089347839, | |
| "accepted": 403, | |
| "errors": 47, | |
| "risk": 0.11662531017369727, | |
| "coverage": 0.806, | |
| "coverage_of_all_cases": 0.806 | |
| }, | |
| { | |
| "threshold": 0.5990613102912903, | |
| "accepted": 404, | |
| "errors": 47, | |
| "risk": 0.11633663366336634, | |
| "coverage": 0.808, | |
| "coverage_of_all_cases": 0.808 | |
| }, | |
| { | |
| "threshold": 0.5931646823883057, | |
| "accepted": 405, | |
| "errors": 47, | |
| "risk": 0.11604938271604938, | |
| "coverage": 0.81, | |
| "coverage_of_all_cases": 0.81 | |
| }, | |
| { | |
| "threshold": 0.5926666259765625, | |
| "accepted": 408, | |
| "errors": 47, | |
| "risk": 0.11519607843137254, | |
| "coverage": 0.816, | |
| "coverage_of_all_cases": 0.816 | |
| }, | |
| { | |
| "threshold": 0.5912318229675293, | |
| "accepted": 409, | |
| "errors": 48, | |
| "risk": 0.11735941320293398, | |
| "coverage": 0.818, | |
| "coverage_of_all_cases": 0.818 | |
| }, | |
| { | |
| "threshold": 0.5910080671310425, | |
| "accepted": 410, | |
| "errors": 49, | |
| "risk": 0.11951219512195121, | |
| "coverage": 0.82, | |
| "coverage_of_all_cases": 0.82 | |
| }, | |
| { | |
| "threshold": 0.5893962979316711, | |
| "accepted": 411, | |
| "errors": 50, | |
| "risk": 0.12165450121654502, | |
| "coverage": 0.822, | |
| "coverage_of_all_cases": 0.822 | |
| }, | |
| { | |
| "threshold": 0.5848519802093506, | |
| "accepted": 412, | |
| "errors": 50, | |
| "risk": 0.12135922330097088, | |
| "coverage": 0.824, | |
| "coverage_of_all_cases": 0.824 | |
| }, | |
| { | |
| "threshold": 0.584510326385498, | |
| "accepted": 413, | |
| "errors": 50, | |
| "risk": 0.12106537530266344, | |
| "coverage": 0.826, | |
| "coverage_of_all_cases": 0.826 | |
| }, | |
| { | |
| "threshold": 0.5802332758903503, | |
| "accepted": 414, | |
| "errors": 51, | |
| "risk": 0.12318840579710146, | |
| "coverage": 0.828, | |
| "coverage_of_all_cases": 0.828 | |
| }, | |
| { | |
| "threshold": 0.5651715397834778, | |
| "accepted": 415, | |
| "errors": 52, | |
| "risk": 0.12530120481927712, | |
| "coverage": 0.83, | |
| "coverage_of_all_cases": 0.83 | |
| }, | |
| { | |
| "threshold": 0.5638106465339661, | |
| "accepted": 416, | |
| "errors": 53, | |
| "risk": 0.12740384615384615, | |
| "coverage": 0.832, | |
| "coverage_of_all_cases": 0.832 | |
| }, | |
| { | |
| "threshold": 0.562176525592804, | |
| "accepted": 419, | |
| "errors": 53, | |
| "risk": 0.12649164677804295, | |
| "coverage": 0.838, | |
| "coverage_of_all_cases": 0.838 | |
| }, | |
| { | |
| "threshold": 0.5610589385032654, | |
| "accepted": 420, | |
| "errors": 54, | |
| "risk": 0.12857142857142856, | |
| "coverage": 0.84, | |
| "coverage_of_all_cases": 0.84 | |
| }, | |
| { | |
| "threshold": 0.5609003305435181, | |
| "accepted": 421, | |
| "errors": 54, | |
| "risk": 0.12826603325415678, | |
| "coverage": 0.842, | |
| "coverage_of_all_cases": 0.842 | |
| }, | |
| { | |
| "threshold": 0.545341432094574, | |
| "accepted": 422, | |
| "errors": 54, | |
| "risk": 0.12796208530805686, | |
| "coverage": 0.844, | |
| "coverage_of_all_cases": 0.844 | |
| }, | |
| { | |
| "threshold": 0.5342407822608948, | |
| "accepted": 423, | |
| "errors": 55, | |
| "risk": 0.13002364066193853, | |
| "coverage": 0.846, | |
| "coverage_of_all_cases": 0.846 | |
| }, | |
| { | |
| "threshold": 0.5325173735618591, | |
| "accepted": 424, | |
| "errors": 55, | |
| "risk": 0.12971698113207547, | |
| "coverage": 0.848, | |
| "coverage_of_all_cases": 0.848 | |
| }, | |
| { | |
| "threshold": 0.531209409236908, | |
| "accepted": 427, | |
| "errors": 56, | |
| "risk": 0.13114754098360656, | |
| "coverage": 0.854, | |
| "coverage_of_all_cases": 0.854 | |
| }, | |
| { | |
| "threshold": 0.5228227376937866, | |
| "accepted": 428, | |
| "errors": 57, | |
| "risk": 0.13317757009345793, | |
| "coverage": 0.856, | |
| "coverage_of_all_cases": 0.856 | |
| }, | |
| { | |
| "threshold": 0.516264021396637, | |
| "accepted": 429, | |
| "errors": 58, | |
| "risk": 0.1351981351981352, | |
| "coverage": 0.858, | |
| "coverage_of_all_cases": 0.858 | |
| }, | |
| { | |
| "threshold": 0.5121442675590515, | |
| "accepted": 430, | |
| "errors": 58, | |
| "risk": 0.13488372093023257, | |
| "coverage": 0.86, | |
| "coverage_of_all_cases": 0.86 | |
| }, | |
| { | |
| "threshold": 0.5115438103675842, | |
| "accepted": 431, | |
| "errors": 58, | |
| "risk": 0.1345707656612529, | |
| "coverage": 0.862, | |
| "coverage_of_all_cases": 0.862 | |
| }, | |
| { | |
| "threshold": 0.5115255117416382, | |
| "accepted": 432, | |
| "errors": 58, | |
| "risk": 0.13425925925925927, | |
| "coverage": 0.864, | |
| "coverage_of_all_cases": 0.864 | |
| }, | |
| { | |
| "threshold": 0.5087225437164307, | |
| "accepted": 433, | |
| "errors": 58, | |
| "risk": 0.13394919168591224, | |
| "coverage": 0.866, | |
| "coverage_of_all_cases": 0.866 | |
| }, | |
| { | |
| "threshold": 0.5051097869873047, | |
| "accepted": 434, | |
| "errors": 58, | |
| "risk": 0.1336405529953917, | |
| "coverage": 0.868, | |
| "coverage_of_all_cases": 0.868 | |
| }, | |
| { | |
| "threshold": 0.5, | |
| "accepted": 436, | |
| "errors": 58, | |
| "risk": 0.13302752293577982, | |
| "coverage": 0.872, | |
| "coverage_of_all_cases": 0.872 | |
| }, | |
| { | |
| "threshold": 0.49847978353500366, | |
| "accepted": 437, | |
| "errors": 58, | |
| "risk": 0.13272311212814644, | |
| "coverage": 0.874, | |
| "coverage_of_all_cases": 0.874 | |
| }, | |
| { | |
| "threshold": 0.4914195239543915, | |
| "accepted": 438, | |
| "errors": 58, | |
| "risk": 0.1324200913242009, | |
| "coverage": 0.876, | |
| "coverage_of_all_cases": 0.876 | |
| }, | |
| { | |
| "threshold": 0.4785914421081543, | |
| "accepted": 439, | |
| "errors": 58, | |
| "risk": 0.13211845102505695, | |
| "coverage": 0.878, | |
| "coverage_of_all_cases": 0.878 | |
| }, | |
| { | |
| "threshold": 0.4783940017223358, | |
| "accepted": 440, | |
| "errors": 58, | |
| "risk": 0.1318181818181818, | |
| "coverage": 0.88, | |
| "coverage_of_all_cases": 0.88 | |
| }, | |
| { | |
| "threshold": 0.4749179184436798, | |
| "accepted": 441, | |
| "errors": 58, | |
| "risk": 0.13151927437641722, | |
| "coverage": 0.882, | |
| "coverage_of_all_cases": 0.882 | |
| }, | |
| { | |
| "threshold": 0.4737212061882019, | |
| "accepted": 442, | |
| "errors": 58, | |
| "risk": 0.13122171945701358, | |
| "coverage": 0.884, | |
| "coverage_of_all_cases": 0.884 | |
| }, | |
| { | |
| "threshold": 0.46419432759284973, | |
| "accepted": 443, | |
| "errors": 59, | |
| "risk": 0.13318284424379231, | |
| "coverage": 0.886, | |
| "coverage_of_all_cases": 0.886 | |
| }, | |
| { | |
| "threshold": 0.45797958970069885, | |
| "accepted": 444, | |
| "errors": 60, | |
| "risk": 0.13513513513513514, | |
| "coverage": 0.888, | |
| "coverage_of_all_cases": 0.888 | |
| }, | |
| { | |
| "threshold": 0.4551844000816345, | |
| "accepted": 445, | |
| "errors": 60, | |
| "risk": 0.1348314606741573, | |
| "coverage": 0.89, | |
| "coverage_of_all_cases": 0.89 | |
| }, | |
| { | |
| "threshold": 0.4516263008117676, | |
| "accepted": 446, | |
| "errors": 60, | |
| "risk": 0.13452914798206278, | |
| "coverage": 0.892, | |
| "coverage_of_all_cases": 0.892 | |
| }, | |
| { | |
| "threshold": 0.4489894509315491, | |
| "accepted": 447, | |
| "errors": 61, | |
| "risk": 0.13646532438478748, | |
| "coverage": 0.894, | |
| "coverage_of_all_cases": 0.894 | |
| }, | |
| { | |
| "threshold": 0.44753921031951904, | |
| "accepted": 448, | |
| "errors": 62, | |
| "risk": 0.13839285714285715, | |
| "coverage": 0.896, | |
| "coverage_of_all_cases": 0.896 | |
| }, | |
| { | |
| "threshold": 0.43655669689178467, | |
| "accepted": 449, | |
| "errors": 63, | |
| "risk": 0.1403118040089087, | |
| "coverage": 0.898, | |
| "coverage_of_all_cases": 0.898 | |
| }, | |
| { | |
| "threshold": 0.43190452456474304, | |
| "accepted": 450, | |
| "errors": 63, | |
| "risk": 0.14, | |
| "coverage": 0.9, | |
| "coverage_of_all_cases": 0.9 | |
| }, | |
| { | |
| "threshold": 0.42257094383239746, | |
| "accepted": 451, | |
| "errors": 64, | |
| "risk": 0.1419068736141907, | |
| "coverage": 0.902, | |
| "coverage_of_all_cases": 0.902 | |
| }, | |
| { | |
| "threshold": 0.40729448199272156, | |
| "accepted": 452, | |
| "errors": 64, | |
| "risk": 0.1415929203539823, | |
| "coverage": 0.904, | |
| "coverage_of_all_cases": 0.904 | |
| }, | |
| { | |
| "threshold": 0.39370301365852356, | |
| "accepted": 453, | |
| "errors": 64, | |
| "risk": 0.141280353200883, | |
| "coverage": 0.906, | |
| "coverage_of_all_cases": 0.906 | |
| }, | |
| { | |
| "threshold": 0.3924282491207123, | |
| "accepted": 454, | |
| "errors": 65, | |
| "risk": 0.14317180616740088, | |
| "coverage": 0.908, | |
| "coverage_of_all_cases": 0.908 | |
| }, | |
| { | |
| "threshold": 0.3922504186630249, | |
| "accepted": 455, | |
| "errors": 66, | |
| "risk": 0.14505494505494507, | |
| "coverage": 0.91, | |
| "coverage_of_all_cases": 0.91 | |
| }, | |
| { | |
| "threshold": 0.3899627923965454, | |
| "accepted": 456, | |
| "errors": 66, | |
| "risk": 0.14473684210526316, | |
| "coverage": 0.912, | |
| "coverage_of_all_cases": 0.912 | |
| }, | |
| { | |
| "threshold": 0.37951433658599854, | |
| "accepted": 457, | |
| "errors": 66, | |
| "risk": 0.14442013129102846, | |
| "coverage": 0.914, | |
| "coverage_of_all_cases": 0.914 | |
| }, | |
| { | |
| "threshold": 0.3708578050136566, | |
| "accepted": 458, | |
| "errors": 67, | |
| "risk": 0.1462882096069869, | |
| "coverage": 0.916, | |
| "coverage_of_all_cases": 0.916 | |
| }, | |
| { | |
| "threshold": 0.36751577258110046, | |
| "accepted": 459, | |
| "errors": 68, | |
| "risk": 0.14814814814814814, | |
| "coverage": 0.918, | |
| "coverage_of_all_cases": 0.918 | |
| }, | |
| { | |
| "threshold": 0.36438554525375366, | |
| "accepted": 460, | |
| "errors": 68, | |
| "risk": 0.14782608695652175, | |
| "coverage": 0.92, | |
| "coverage_of_all_cases": 0.92 | |
| }, | |
| { | |
| "threshold": 0.36382174491882324, | |
| "accepted": 461, | |
| "errors": 69, | |
| "risk": 0.14967462039045554, | |
| "coverage": 0.922, | |
| "coverage_of_all_cases": 0.922 | |
| }, | |
| { | |
| "threshold": 0.3594815135002136, | |
| "accepted": 462, | |
| "errors": 70, | |
| "risk": 0.15151515151515152, | |
| "coverage": 0.924, | |
| "coverage_of_all_cases": 0.924 | |
| }, | |
| { | |
| "threshold": 0.35696759819984436, | |
| "accepted": 463, | |
| "errors": 70, | |
| "risk": 0.1511879049676026, | |
| "coverage": 0.926, | |
| "coverage_of_all_cases": 0.926 | |
| }, | |
| { | |
| "threshold": 0.35523292422294617, | |
| "accepted": 464, | |
| "errors": 71, | |
| "risk": 0.15301724137931033, | |
| "coverage": 0.928, | |
| "coverage_of_all_cases": 0.928 | |
| }, | |
| { | |
| "threshold": 0.35232609510421753, | |
| "accepted": 465, | |
| "errors": 72, | |
| "risk": 0.15483870967741936, | |
| "coverage": 0.93, | |
| "coverage_of_all_cases": 0.93 | |
| }, | |
| { | |
| "threshold": 0.3517778217792511, | |
| "accepted": 466, | |
| "errors": 73, | |
| "risk": 0.15665236051502146, | |
| "coverage": 0.932, | |
| "coverage_of_all_cases": 0.932 | |
| }, | |
| { | |
| "threshold": 0.346769779920578, | |
| "accepted": 467, | |
| "errors": 73, | |
| "risk": 0.15631691648822268, | |
| "coverage": 0.934, | |
| "coverage_of_all_cases": 0.934 | |
| }, | |
| { | |
| "threshold": 0.3458821177482605, | |
| "accepted": 468, | |
| "errors": 73, | |
| "risk": 0.15598290598290598, | |
| "coverage": 0.936, | |
| "coverage_of_all_cases": 0.936 | |
| }, | |
| { | |
| "threshold": 0.34539833664894104, | |
| "accepted": 469, | |
| "errors": 74, | |
| "risk": 0.15778251599147122, | |
| "coverage": 0.938, | |
| "coverage_of_all_cases": 0.938 | |
| }, | |
| { | |
| "threshold": 0.33743640780448914, | |
| "accepted": 470, | |
| "errors": 75, | |
| "risk": 0.1595744680851064, | |
| "coverage": 0.94, | |
| "coverage_of_all_cases": 0.94 | |
| }, | |
| { | |
| "threshold": 0.32827404141426086, | |
| "accepted": 471, | |
| "errors": 75, | |
| "risk": 0.1592356687898089, | |
| "coverage": 0.942, | |
| "coverage_of_all_cases": 0.942 | |
| }, | |
| { | |
| "threshold": 0.32752493023872375, | |
| "accepted": 472, | |
| "errors": 76, | |
| "risk": 0.16101694915254236, | |
| "coverage": 0.944, | |
| "coverage_of_all_cases": 0.944 | |
| }, | |
| { | |
| "threshold": 0.32717207074165344, | |
| "accepted": 473, | |
| "errors": 77, | |
| "risk": 0.16279069767441862, | |
| "coverage": 0.946, | |
| "coverage_of_all_cases": 0.946 | |
| }, | |
| { | |
| "threshold": 0.32649895548820496, | |
| "accepted": 474, | |
| "errors": 78, | |
| "risk": 0.16455696202531644, | |
| "coverage": 0.948, | |
| "coverage_of_all_cases": 0.948 | |
| }, | |
| { | |
| "threshold": 0.32638153433799744, | |
| "accepted": 475, | |
| "errors": 79, | |
| "risk": 0.16631578947368422, | |
| "coverage": 0.95, | |
| "coverage_of_all_cases": 0.95 | |
| }, | |
| { | |
| "threshold": 0.32601913809776306, | |
| "accepted": 476, | |
| "errors": 80, | |
| "risk": 0.16806722689075632, | |
| "coverage": 0.952, | |
| "coverage_of_all_cases": 0.952 | |
| }, | |
| { | |
| "threshold": 0.32572489976882935, | |
| "accepted": 477, | |
| "errors": 81, | |
| "risk": 0.16981132075471697, | |
| "coverage": 0.954, | |
| "coverage_of_all_cases": 0.954 | |
| }, | |
| { | |
| "threshold": 0.3225614130496979, | |
| "accepted": 478, | |
| "errors": 82, | |
| "risk": 0.17154811715481172, | |
| "coverage": 0.956, | |
| "coverage_of_all_cases": 0.956 | |
| }, | |
| { | |
| "threshold": 0.3166254758834839, | |
| "accepted": 479, | |
| "errors": 83, | |
| "risk": 0.1732776617954071, | |
| "coverage": 0.958, | |
| "coverage_of_all_cases": 0.958 | |
| }, | |
| { | |
| "threshold": 0.314787358045578, | |
| "accepted": 480, | |
| "errors": 84, | |
| "risk": 0.175, | |
| "coverage": 0.96, | |
| "coverage_of_all_cases": 0.96 | |
| }, | |
| { | |
| "threshold": 0.310443252325058, | |
| "accepted": 481, | |
| "errors": 85, | |
| "risk": 0.17671517671517672, | |
| "coverage": 0.962, | |
| "coverage_of_all_cases": 0.962 | |
| }, | |
| { | |
| "threshold": 0.3080218434333801, | |
| "accepted": 482, | |
| "errors": 85, | |
| "risk": 0.17634854771784234, | |
| "coverage": 0.964, | |
| "coverage_of_all_cases": 0.964 | |
| }, | |
| { | |
| "threshold": 0.30747413635253906, | |
| "accepted": 483, | |
| "errors": 86, | |
| "risk": 0.17805383022774326, | |
| "coverage": 0.966, | |
| "coverage_of_all_cases": 0.966 | |
| }, | |
| { | |
| "threshold": 0.29790326952934265, | |
| "accepted": 484, | |
| "errors": 87, | |
| "risk": 0.1797520661157025, | |
| "coverage": 0.968, | |
| "coverage_of_all_cases": 0.968 | |
| }, | |
| { | |
| "threshold": 0.2976965308189392, | |
| "accepted": 485, | |
| "errors": 88, | |
| "risk": 0.18144329896907216, | |
| "coverage": 0.97, | |
| "coverage_of_all_cases": 0.97 | |
| }, | |
| { | |
| "threshold": 0.29680362343788147, | |
| "accepted": 486, | |
| "errors": 89, | |
| "risk": 0.1831275720164609, | |
| "coverage": 0.972, | |
| "coverage_of_all_cases": 0.972 | |
| }, | |
| { | |
| "threshold": 0.2952236533164978, | |
| "accepted": 487, | |
| "errors": 90, | |
| "risk": 0.18480492813141683, | |
| "coverage": 0.974, | |
| "coverage_of_all_cases": 0.974 | |
| }, | |
| { | |
| "threshold": 0.2887818217277527, | |
| "accepted": 488, | |
| "errors": 91, | |
| "risk": 0.1864754098360656, | |
| "coverage": 0.976, | |
| "coverage_of_all_cases": 0.976 | |
| }, | |
| { | |
| "threshold": 0.2849769592285156, | |
| "accepted": 489, | |
| "errors": 91, | |
| "risk": 0.18609406952965235, | |
| "coverage": 0.978, | |
| "coverage_of_all_cases": 0.978 | |
| }, | |
| { | |
| "threshold": 0.2810051143169403, | |
| "accepted": 490, | |
| "errors": 92, | |
| "risk": 0.18775510204081633, | |
| "coverage": 0.98, | |
| "coverage_of_all_cases": 0.98 | |
| }, | |
| { | |
| "threshold": 0.2804868519306183, | |
| "accepted": 491, | |
| "errors": 93, | |
| "risk": 0.1894093686354379, | |
| "coverage": 0.982, | |
| "coverage_of_all_cases": 0.982 | |
| }, | |
| { | |
| "threshold": 0.27835917472839355, | |
| "accepted": 492, | |
| "errors": 94, | |
| "risk": 0.1910569105691057, | |
| "coverage": 0.984, | |
| "coverage_of_all_cases": 0.984 | |
| }, | |
| { | |
| "threshold": 0.27671149373054504, | |
| "accepted": 493, | |
| "errors": 95, | |
| "risk": 0.1926977687626775, | |
| "coverage": 0.986, | |
| "coverage_of_all_cases": 0.986 | |
| }, | |
| { | |
| "threshold": 0.27509620785713196, | |
| "accepted": 494, | |
| "errors": 96, | |
| "risk": 0.19433198380566802, | |
| "coverage": 0.988, | |
| "coverage_of_all_cases": 0.988 | |
| }, | |
| { | |
| "threshold": 0.27262595295906067, | |
| "accepted": 495, | |
| "errors": 97, | |
| "risk": 0.19595959595959597, | |
| "coverage": 0.99, | |
| "coverage_of_all_cases": 0.99 | |
| }, | |
| { | |
| "threshold": 0.2718034088611603, | |
| "accepted": 496, | |
| "errors": 98, | |
| "risk": 0.1975806451612903, | |
| "coverage": 0.992, | |
| "coverage_of_all_cases": 0.992 | |
| }, | |
| { | |
| "threshold": 0.2673657536506653, | |
| "accepted": 497, | |
| "errors": 99, | |
| "risk": 0.19919517102615694, | |
| "coverage": 0.994, | |
| "coverage_of_all_cases": 0.994 | |
| }, | |
| { | |
| "threshold": 0.25559332966804504, | |
| "accepted": 498, | |
| "errors": 100, | |
| "risk": 0.20080321285140562, | |
| "coverage": 0.996, | |
| "coverage_of_all_cases": 0.996 | |
| }, | |
| { | |
| "threshold": 0.2484910935163498, | |
| "accepted": 499, | |
| "errors": 101, | |
| "risk": 0.20240480961923848, | |
| "coverage": 0.998, | |
| "coverage_of_all_cases": 0.998 | |
| }, | |
| { | |
| "threshold": 0.24818962812423706, | |
| "accepted": 500, | |
| "errors": 102, | |
| "risk": 0.204, | |
| "coverage": 1.0, | |
| "coverage_of_all_cases": 1.0 | |
| } | |
| ] | |
| }, | |
| "probability_incomplete": 0, | |
| "latency_ms": { | |
| "count": 500, | |
| "mean": 20.08110391406808, | |
| "p50": 19.291491502372082, | |
| "p95": 19.581971003935905, | |
| "min": 18.74839499942027, | |
| "max": 414.07370699744206 | |
| }, | |
| "wall_latency_ms": { | |
| "count": 500, | |
| "mean": 21.834221785858972, | |
| "p50": 20.283657002437394, | |
| "p95": 24.277247994905334, | |
| "min": 19.293662000563927, | |
| "max": 432.526392993168 | |
| }, | |
| "input_tokens": { | |
| "count": 500, | |
| "mean": 309.888, | |
| "p50": 202.0, | |
| "p95": 888.1499999999999, | |
| "min": 108.0, | |
| "max": 1631.0 | |
| }, | |
| "state_characters": { | |
| "count": 500, | |
| "mean": 571.486, | |
| "p50": 199.5, | |
| "p95": 2825.1, | |
| "min": 10.0, | |
| "max": 6317.0 | |
| }, | |
| "notes": [ | |
| "accuracy_all counts errors and skips as incorrect", | |
| "accuracy_attempted and family macro count errors as wrong and exclude intentional skips", | |
| "family defaults to source; latency_ms is local forward-pass or hosted HTTP time", | |
| "wall_latency_ms includes per-record scorer preprocessing and inference; no warmup excluded", | |
| "F1 uses semantic option keys, never shuffled answer letters", | |
| "Probability metrics only include explicitly complete distributions" | |
| ] | |
| } | |
| }, | |
| "decision_minus_tev": { | |
| "accuracy": { | |
| "accuracy_delta": 0.114, | |
| "ci95": [ | |
| 0.074, | |
| 0.15404999999999974 | |
| ], | |
| "samples": 2000, | |
| "seed": 42, | |
| "by_source": { | |
| "clinc150": { | |
| "count": 100, | |
| "groups": 100, | |
| "fixed_weight": 0.2, | |
| "accuracy_delta": 0.06, | |
| "ci95": [ | |
| 0.0, | |
| 0.12 | |
| ] | |
| }, | |
| "go_emotions": { | |
| "count": 100, | |
| "groups": 100, | |
| "fixed_weight": 0.2, | |
| "accuracy_delta": 0.13, | |
| "ci95": [ | |
| 0.03, | |
| 0.23 | |
| ] | |
| }, | |
| "helpsteer2": { | |
| "count": 100, | |
| "groups": 100, | |
| "fixed_weight": 0.2, | |
| "accuracy_delta": -0.09, | |
| "ci95": [ | |
| -0.18, | |
| 0.0 | |
| ] | |
| }, | |
| "paws": { | |
| "count": 100, | |
| "groups": 100, | |
| "fixed_weight": 0.2, | |
| "accuracy_delta": 0.35, | |
| "ci95": [ | |
| 0.24, | |
| 0.46 | |
| ] | |
| }, | |
| "vitaminc": { | |
| "count": 100, | |
| "groups": 100, | |
| "fixed_weight": 0.2, | |
| "accuracy_delta": 0.12, | |
| "ci95": [ | |
| 0.03, | |
| 0.21 | |
| ] | |
| } | |
| }, | |
| "method": "paired percentile bootstrap; whole groups within source; fixed observed source weights" | |
| }, | |
| "family_macro": { | |
| "family_macro_accuracy_delta": 0.11399999999999999, | |
| "family_macro_ci95": [ | |
| 0.074, | |
| 0.15404999999999971 | |
| ], | |
| "samples": 2000, | |
| "seed": 42, | |
| "method": "paired percentile bootstrap, whole groups within family, equal observed family weights" | |
| } | |
| } | |
| } | |