asketeddy's picture
Publish six own random-init Gooo semantic composition models and verified finite dogfood evidence
1102d2c verified
Raw History Blame Contribute Delete
195 kB
{
"actual_model_predictions_all_stages": 29106,
"benchmark_predictions_including_allocation_probe": 12012,
"calibration": {
"offline": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2252,
"initial_complete_functions": 106,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 548,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 604,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
106,
96,
94,
88
],
"complete_function_curve_budgets_1_to_4": [
106,
202,
296,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2252,
3858,
5120,
6144
],
"summed_observed_prediction_ns": 0
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 204,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
204,
332,
454,
512
],
"summed_observed_prediction_ns": 0
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 204,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
204,
332,
454,
512
],
"summed_observed_prediction_ns": 0
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
288,
402,
512
],
"summed_observed_prediction_ns": 0
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
288,
402,
512
],
"summed_observed_prediction_ns": 0
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
298,
403,
512
],
"summed_observed_prediction_ns": 0
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
298,
403,
512
],
"summed_observed_prediction_ns": 0
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
8,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
440,
507,
512
],
"summed_observed_prediction_ns": 0
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
8,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
440,
507,
512
],
"summed_observed_prediction_ns": 0
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 174,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
8,
7,
8
],
"complete_function_curve_budgets_1_to_4": [
9,
17,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
174,
294,
399,
512
],
"summed_observed_prediction_ns": 0
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 174,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
8,
7,
8
],
"complete_function_curve_budgets_1_to_4": [
9,
17,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
174,
294,
399,
512
],
"summed_observed_prediction_ns": 0
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 144,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
144,
277,
395,
512
],
"summed_observed_prediction_ns": 0
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 144,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
144,
277,
395,
512
],
"summed_observed_prediction_ns": 0
}
}
},
"v2-fp32": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2737,
"initial_complete_functions": 145,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 397,
"actual_model_predictions": 1358,
"actual_feedback_predictions": 590,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 755,
"bilingual_initial_mask_disagreements": 104,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
145,
127,
66,
46
],
"complete_function_curve_budgets_1_to_4": [
145,
272,
338,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2737,
4797,
5671,
6144
],
"summed_observed_prediction_ns": 14155551
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 16,
"actual_model_predictions": 96,
"actual_feedback_predictions": 32,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 80,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
16,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
512,
512,
512
],
"summed_observed_prediction_ns": 994546
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 181,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
181,
394,
476,
512
],
"summed_observed_prediction_ns": 1346630
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 272,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 16,
"actual_model_predictions": 96,
"actual_feedback_predictions": 32,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 80,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
16,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
272,
512,
512,
512
],
"summed_observed_prediction_ns": 993585
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 221,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 40,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 56,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
4,
12,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
16,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
221,
292,
458,
512
],
"summed_observed_prediction_ns": 1285084
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 155,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
155,
277,
407,
512
],
"summed_observed_prediction_ns": 1314708
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 151,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
9,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
151,
287,
410,
512
],
"summed_observed_prediction_ns": 1321879
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
502,
507,
512
],
"summed_observed_prediction_ns": 1173662
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
447,
507,
512
],
"summed_observed_prediction_ns": 1165500
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 293,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 15,
"actual_model_predictions": 94,
"actual_feedback_predictions": 30,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 81,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
15,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
17,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
293,
512,
512,
512
],
"summed_observed_prediction_ns": 1006668
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 169,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
9,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
169,
276,
407,
512
],
"summed_observed_prediction_ns": 1340206
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 271,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 16,
"actual_model_predictions": 96,
"actual_feedback_predictions": 32,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 80,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
16,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
271,
512,
512,
512
],
"summed_observed_prediction_ns": 974540
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 209,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 40,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 56,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
4,
12,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
16,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
209,
274,
451,
512
],
"summed_observed_prediction_ns": 1238543
}
}
},
"v2-ptq_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2451,
"initial_complete_functions": 121,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 470,
"actual_model_predictions": 1430,
"actual_feedback_predictions": 662,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 682,
"bilingual_initial_mask_disagreements": 96,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
121,
127,
65,
71
],
"complete_function_curve_budgets_1_to_4": [
121,
248,
313,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2451,
4379,
5417,
6144
],
"summed_observed_prediction_ns": 16698471
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 181,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 41,
"actual_model_predictions": 121,
"actual_feedback_predictions": 57,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 55,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
15,
1,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
23,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
181,
387,
476,
512
],
"summed_observed_prediction_ns": 1382458
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 181,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 127,
"actual_feedback_predictions": 63,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
9,
7,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
17,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
181,
340,
476,
512
],
"summed_observed_prediction_ns": 1489584
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 159,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 43,
"actual_model_predictions": 123,
"actual_feedback_predictions": 59,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 53,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
13,
3,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
21,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
159,
357,
406,
512
],
"summed_observed_prediction_ns": 1415000
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 156,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 43,
"actual_model_predictions": 123,
"actual_feedback_predictions": 59,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 53,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
13,
3,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
21,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
156,
348,
405,
512
],
"summed_observed_prediction_ns": 1415173
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 169,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 127,
"actual_feedback_predictions": 63,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
9,
7,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
17,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
169,
296,
407,
512
],
"summed_observed_prediction_ns": 1466792
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 169,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
169,
288,
407,
512
],
"summed_observed_prediction_ns": 1483583
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
502,
507,
512
],
"summed_observed_prediction_ns": 1304085
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
447,
507,
512
],
"summed_observed_prediction_ns": 1304670
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 293,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 15,
"actual_model_predictions": 94,
"actual_feedback_predictions": 30,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 81,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
15,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
17,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
293,
512,
512,
512
],
"summed_observed_prediction_ns": 1064163
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 169,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 51,
"actual_model_predictions": 132,
"actual_feedback_predictions": 68,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 45,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
4,
13,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
12,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
169,
222,
407,
512
],
"summed_observed_prediction_ns": 1544548
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 271,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 16,
"actual_model_predictions": 96,
"actual_feedback_predictions": 32,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 80,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
16,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
271,
512,
512,
512
],
"summed_observed_prediction_ns": 1113538
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 151,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 55,
"actual_model_predictions": 135,
"actual_feedback_predictions": 71,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 41,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
1,
15,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
9,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
151,
168,
395,
512
],
"summed_observed_prediction_ns": 1714877
}
}
},
"v2-qat_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2555,
"initial_complete_functions": 136,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 444,
"actual_model_predictions": 1392,
"actual_feedback_predictions": 624,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 708,
"bilingual_initial_mask_disagreements": 98,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
136,
120,
60,
68
],
"complete_function_curve_budgets_1_to_4": [
136,
256,
316,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2555,
4552,
5395,
6144
],
"summed_observed_prediction_ns": 16389180
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
387,
476,
512
],
"summed_observed_prediction_ns": 1226217
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 181,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
181,
394,
476,
512
],
"summed_observed_prediction_ns": 1537046
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 201,
"initial_complete_functions": 11,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 37,
"actual_model_predictions": 114,
"actual_feedback_predictions": 50,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 59,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
11,
13,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
11,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
201,
396,
397,
512
],
"summed_observed_prediction_ns": 1295466
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 175,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
175,
292,
399,
512
],
"summed_observed_prediction_ns": 1483995
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 155,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
155,
294,
407,
512
],
"summed_observed_prediction_ns": 1536835
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 155,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
155,
287,
407,
512
],
"summed_observed_prediction_ns": 1557835
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
502,
507,
512
],
"summed_observed_prediction_ns": 1343711
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 20,
"actual_model_predictions": 100,
"actual_feedback_predictions": 36,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 76,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
12,
4,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
28,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
480,
512,
512
],
"summed_observed_prediction_ns": 1157713
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 293,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 15,
"actual_model_predictions": 94,
"actual_feedback_predictions": 30,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 81,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
15,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
17,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
293,
512,
512,
512
],
"summed_observed_prediction_ns": 1072622
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 168,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 52,
"actual_model_predictions": 132,
"actual_feedback_predictions": 68,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 44,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
4,
12,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
12,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
168,
222,
392,
512
],
"summed_observed_prediction_ns": 1538745
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 271,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 16,
"actual_model_predictions": 96,
"actual_feedback_predictions": 32,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 80,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
16,
0,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
32,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
271,
512,
512,
512
],
"summed_observed_prediction_ns": 1100251
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 141,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
141,
274,
398,
512
],
"summed_observed_prediction_ns": 1538744
}
}
},
"v3-fp32": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 3238,
"initial_complete_functions": 179,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 377,
"actual_model_predictions": 1337,
"actual_feedback_predictions": 569,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 775,
"bilingual_initial_mask_disagreements": 124,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
179,
75,
88,
42
],
"complete_function_curve_budgets_1_to_4": [
179,
254,
342,
384
],
"best_passing_case_curve_budgets_1_to_4": [
3238,
4409,
5686,
6144
],
"summed_observed_prediction_ns": 12776346
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 33,
"actual_model_predictions": 108,
"actual_feedback_predictions": 44,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 63,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
7,
1,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
23,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
391,
452,
512
],
"summed_observed_prediction_ns": 995003
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 291,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 30,
"actual_model_predictions": 117,
"actual_feedback_predictions": 53,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 66,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
11,
8,
1
],
"complete_function_curve_budgets_1_to_4": [
12,
23,
31,
32
],
"best_passing_case_curve_budgets_1_to_4": [
291,
394,
505,
512
],
"summed_observed_prediction_ns": 1096214
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 272,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
272,
393,
401,
512
],
"summed_observed_prediction_ns": 1015583
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 230,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 31,
"actual_model_predictions": 122,
"actual_feedback_predictions": 58,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 65,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
9,
11,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
21,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
230,
358,
512,
512
],
"summed_observed_prediction_ns": 1111084
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 44,
"actual_model_predictions": 127,
"actual_feedback_predictions": 63,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 52,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
9,
10,
5
],
"complete_function_curve_budgets_1_to_4": [
8,
17,
27,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
295,
448,
512
],
"summed_observed_prediction_ns": 1282459
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 305,
"initial_complete_functions": 18,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 31,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 65,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
18,
2,
7,
5
],
"complete_function_curve_budgets_1_to_4": [
18,
20,
27,
32
],
"best_passing_case_curve_budgets_1_to_4": [
305,
340,
449,
512
],
"summed_observed_prediction_ns": 1031215
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 33,
"actual_model_predictions": 114,
"actual_feedback_predictions": 50,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 63,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
10,
7,
3
],
"complete_function_curve_budgets_1_to_4": [
12,
22,
29,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
442,
509,
512
],
"summed_observed_prediction_ns": 1107040
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 394,
"initial_complete_functions": 24,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 18,
"actual_model_predictions": 88,
"actual_feedback_predictions": 24,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 78,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
24,
0,
6,
2
],
"complete_function_curve_budgets_1_to_4": [
24,
24,
30,
32
],
"best_passing_case_curve_budgets_1_to_4": [
394,
446,
510,
512
],
"summed_observed_prediction_ns": 846336
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 293,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 109,
"actual_feedback_predictions": 45,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
0,
9,
6
],
"complete_function_curve_budgets_1_to_4": [
17,
17,
26,
32
],
"best_passing_case_curve_budgets_1_to_4": [
293,
300,
424,
512
],
"summed_observed_prediction_ns": 1030670
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 23,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 73,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
9,
7,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
25,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
407,
512,
512
],
"summed_observed_prediction_ns": 1050498
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 271,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 34,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 62,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
2,
10,
4
],
"complete_function_curve_budgets_1_to_4": [
16,
18,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
271,
305,
452,
512
],
"summed_observed_prediction_ns": 998042
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 203,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 124,
"actual_feedback_predictions": 60,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
12,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
203,
338,
512,
512
],
"summed_observed_prediction_ns": 1212202
}
}
},
"v3-ptq_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2689,
"initial_complete_functions": 145,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 430,
"actual_model_predictions": 1387,
"actual_feedback_predictions": 619,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 722,
"bilingual_initial_mask_disagreements": 124,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
145,
109,
69,
61
],
"complete_function_curve_budgets_1_to_4": [
145,
254,
323,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2689,
4438,
5460,
6144
],
"summed_observed_prediction_ns": 14982908
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 33,
"actual_model_predictions": 109,
"actual_feedback_predictions": 45,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 63,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
7,
1,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
23,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
394,
452,
512
],
"summed_observed_prediction_ns": 1141952
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 181,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 34,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 62,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
16,
6,
2
],
"complete_function_curve_budgets_1_to_4": [
8,
24,
30,
32
],
"best_passing_case_curve_budgets_1_to_4": [
181,
388,
497,
512
],
"summed_observed_prediction_ns": 1290461
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 272,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
272,
398,
399,
512
],
"summed_observed_prediction_ns": 1096538
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 175,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
16,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
8,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
175,
398,
455,
512
],
"summed_observed_prediction_ns": 1323954
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
284,
407,
512
],
"summed_observed_prediction_ns": 1377375
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 155,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
155,
284,
407,
512
],
"summed_observed_prediction_ns": 1471245
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 116,
"actual_feedback_predictions": 52,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
8,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
440,
507,
512
],
"summed_observed_prediction_ns": 1214040
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 34,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 62,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
2,
10,
4
],
"complete_function_curve_budgets_1_to_4": [
16,
18,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
385,
507,
512
],
"summed_observed_prediction_ns": 1153959
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 293,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 30,
"actual_model_predictions": 102,
"actual_feedback_predictions": 38,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 66,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
7,
1,
7
],
"complete_function_curve_budgets_1_to_4": [
17,
24,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
293,
394,
407,
512
],
"summed_observed_prediction_ns": 1114875
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 222,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 27,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 69,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
13,
7,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
25,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
222,
407,
512,
512
],
"summed_observed_prediction_ns": 1267290
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 271,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 40,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 56,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
0,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
271,
273,
398,
512
],
"summed_observed_prediction_ns": 1245088
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 141,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
16,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
8,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
141,
393,
512,
512
],
"summed_observed_prediction_ns": 1286131
}
}
},
"v3-qat_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 3289,
"initial_complete_functions": 183,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 365,
"actual_model_predictions": 1318,
"actual_feedback_predictions": 550,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 787,
"bilingual_initial_mask_disagreements": 138,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
183,
89,
60,
52
],
"complete_function_curve_budgets_1_to_4": [
183,
272,
332,
384
],
"best_passing_case_curve_budgets_1_to_4": [
3289,
4723,
5557,
6144
],
"summed_observed_prediction_ns": 14719928
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
415,
428,
512
],
"summed_observed_prediction_ns": 1221541
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 241,
"initial_complete_functions": 10,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 28,
"actual_model_predictions": 114,
"actual_feedback_predictions": 50,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 68,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
10,
16,
6,
0
],
"complete_function_curve_budgets_1_to_4": [
10,
26,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
241,
420,
512,
512
],
"summed_observed_prediction_ns": 1283007
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 272,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 108,
"actual_feedback_predictions": 44,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
272,
394,
401,
512
],
"summed_observed_prediction_ns": 1128752
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 225,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 28,
"actual_model_predictions": 116,
"actual_feedback_predictions": 52,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 68,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
225,
398,
512,
512
],
"summed_observed_prediction_ns": 1285662
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 132,
"actual_feedback_predictions": 68,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
286,
409,
512
],
"summed_observed_prediction_ns": 1476296
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 398,
"initial_complete_functions": 24,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 20,
"actual_model_predictions": 88,
"actual_feedback_predictions": 24,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 76,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
24,
0,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
24,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
398,
400,
463,
512
],
"summed_observed_prediction_ns": 948798
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 338,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 28,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 68,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
338,
502,
507,
512
],
"summed_observed_prediction_ns": 1113997
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 334,
"initial_complete_functions": 20,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 26,
"actual_model_predictions": 98,
"actual_feedback_predictions": 34,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 70,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
20,
2,
6,
4
],
"complete_function_curve_budgets_1_to_4": [
20,
22,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
334,
443,
507,
512
],
"summed_observed_prediction_ns": 1045915
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 293,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 34,
"actual_model_predictions": 106,
"actual_feedback_predictions": 42,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 62,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
4,
3,
8
],
"complete_function_curve_budgets_1_to_4": [
17,
21,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
293,
355,
397,
512
],
"summed_observed_prediction_ns": 1167788
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 276,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 23,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 73,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
9,
7,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
25,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
276,
407,
512,
512
],
"summed_observed_prediction_ns": 1343751
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 271,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 38,
"actual_model_predictions": 116,
"actual_feedback_predictions": 52,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 58,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
2,
6,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
18,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
271,
310,
397,
512
],
"summed_observed_prediction_ns": 1328047
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 214,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 28,
"actual_model_predictions": 116,
"actual_feedback_predictions": 52,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 68,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
214,
393,
512,
512
],
"summed_observed_prediction_ns": 1376374
}
}
}
},
"dataset_sha256": "44393fb6ae27d1dc75c9706ea50077fab8e2573928e4f59422e3e3a65aa79620",
"default_model_promoted": false,
"development": {
"offline": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2200,
"initial_complete_functions": 104,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 548,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 604,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
104,
98,
96,
86
],
"complete_function_curve_budgets_1_to_4": [
104,
202,
298,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2200,
3844,
5124,
6144
],
"summed_observed_prediction_ns": 0
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 203,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
203,
330,
450,
512
],
"summed_observed_prediction_ns": 0
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 203,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
203,
330,
450,
512
],
"summed_observed_prediction_ns": 0
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
291,
401,
512
],
"summed_observed_prediction_ns": 0
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 164,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
164,
291,
401,
512
],
"summed_observed_prediction_ns": 0
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 166,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
166,
290,
395,
512
],
"summed_observed_prediction_ns": 0
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 166,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
166,
290,
395,
512
],
"summed_observed_prediction_ns": 0
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
8,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
446,
508,
512
],
"summed_observed_prediction_ns": 0
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
8,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
446,
508,
512
],
"summed_observed_prediction_ns": 0
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 151,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
9,
8,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
17,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
151,
290,
410,
512
],
"summed_observed_prediction_ns": 0
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 151,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
9,
8,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
17,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
151,
290,
410,
512
],
"summed_observed_prediction_ns": 0
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 148,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
148,
275,
398,
512
],
"summed_observed_prediction_ns": 0
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 148,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 0,
"actual_feedback_predictions": 0,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
148,
275,
398,
512
],
"summed_observed_prediction_ns": 0
}
}
},
"v2-fp32": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2240,
"initial_complete_functions": 110,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 524,
"actual_model_predictions": 1487,
"actual_feedback_predictions": 719,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 628,
"bilingual_initial_mask_disagreements": 126,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
110,
103,
92,
79
],
"complete_function_curve_budgets_1_to_4": [
110,
213,
305,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2240,
3788,
5290,
6144
],
"summed_observed_prediction_ns": 15672695
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 24,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 72,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
388,
512,
512
],
"summed_observed_prediction_ns": 1110579
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 93,
"initial_complete_functions": 0,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 64,
"actual_model_predictions": 144,
"actual_feedback_predictions": 80,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 32,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
0,
16,
0,
16
],
"complete_function_curve_budgets_1_to_4": [
0,
16,
16,
32
],
"best_passing_case_curve_budgets_1_to_4": [
93,
264,
438,
512
],
"summed_observed_prediction_ns": 1512085
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 277,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 20,
"actual_model_predictions": 100,
"actual_feedback_predictions": 36,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 76,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
12,
4,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
28,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
277,
456,
512,
512
],
"summed_observed_prediction_ns": 1038084
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 78,
"initial_complete_functions": 1,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 67,
"actual_model_predictions": 153,
"actual_feedback_predictions": 89,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 29,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
1,
4,
18,
9
],
"complete_function_curve_budgets_1_to_4": [
1,
5,
23,
32
],
"best_passing_case_curve_budgets_1_to_4": [
78,
143,
389,
512
],
"summed_observed_prediction_ns": 1612992
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
274,
401,
512
],
"summed_observed_prediction_ns": 1336287
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
274,
401,
512
],
"summed_observed_prediction_ns": 1390174
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 34,
"actual_model_predictions": 114,
"actual_feedback_predictions": 50,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 62,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
10,
6,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
22,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
475,
508,
512
],
"summed_observed_prediction_ns": 1187170
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
449,
508,
512
],
"summed_observed_prediction_ns": 1183251
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 157,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 126,
"actual_feedback_predictions": 62,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
7,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
9,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
157,
270,
402,
512
],
"summed_observed_prediction_ns": 1275712
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 159,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 49,
"actual_model_predictions": 130,
"actual_feedback_predictions": 66,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 47,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
6,
11,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
14,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
159,
242,
404,
512
],
"summed_observed_prediction_ns": 1433781
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 145,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
145,
276,
401,
512
],
"summed_observed_prediction_ns": 1343036
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 210,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 43,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 53,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
4,
9,
7
],
"complete_function_curve_budgets_1_to_4": [
12,
16,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
210,
277,
414,
512
],
"summed_observed_prediction_ns": 1249544
}
}
},
"v2-ptq_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2367,
"initial_complete_functions": 121,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 504,
"actual_model_predictions": 1464,
"actual_feedback_predictions": 696,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 648,
"bilingual_initial_mask_disagreements": 96,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
121,
93,
99,
71
],
"complete_function_curve_budgets_1_to_4": [
121,
214,
313,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2367,
3801,
5306,
6144
],
"summed_observed_prediction_ns": 17030920
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
0,
16,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
16,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
264,
512,
512
],
"summed_observed_prediction_ns": 1282464
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 179,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
179,
264,
475,
512
],
"summed_observed_prediction_ns": 1519960
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 277,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 26,
"actual_model_predictions": 106,
"actual_feedback_predictions": 42,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 70,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
6,
10,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
22,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
277,
370,
512,
512
],
"summed_observed_prediction_ns": 1212251
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 168,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
168,
280,
404,
512
],
"summed_observed_prediction_ns": 1472496
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
274,
399,
512
],
"summed_observed_prediction_ns": 1498912
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
290,
399,
512
],
"summed_observed_prediction_ns": 1516006
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
504,
508,
512
],
"summed_observed_prediction_ns": 1332002
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
449,
508,
512
],
"summed_observed_prediction_ns": 1303917
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 157,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 39,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 57,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
15,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
9,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
157,
402,
402,
512
],
"summed_observed_prediction_ns": 1350245
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 159,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
9,
7
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
159,
275,
404,
512
],
"summed_observed_prediction_ns": 1474294
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 154,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
154,
276,
389,
512
],
"summed_observed_prediction_ns": 1489036
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 152,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 56,
"actual_model_predictions": 136,
"actual_feedback_predictions": 72,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 40,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
0,
16,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
8,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
152,
153,
394,
512
],
"summed_observed_prediction_ns": 1579337
}
}
},
"v2-qat_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2353,
"initial_complete_functions": 125,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 491,
"actual_model_predictions": 1450,
"actual_feedback_predictions": 682,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 661,
"bilingual_initial_mask_disagreements": 112,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
125,
95,
96,
68
],
"complete_function_curve_budgets_1_to_4": [
125,
220,
316,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2353,
3918,
5319,
6144
],
"summed_observed_prediction_ns": 17671623
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 27,
"actual_model_predictions": 107,
"actual_feedback_predictions": 43,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 69,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
5,
11,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
21,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
340,
512,
512
],
"summed_observed_prediction_ns": 1273708
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 177,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 50,
"actual_model_predictions": 130,
"actual_feedback_predictions": 66,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 46,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
6,
10,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
14,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
177,
258,
475,
512
],
"summed_observed_prediction_ns": 1553668
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 277,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 24,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 72,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
277,
402,
512,
512
],
"summed_observed_prediction_ns": 1260371
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 179,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
179,
289,
403,
512
],
"summed_observed_prediction_ns": 1508922
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
274,
401,
512
],
"summed_observed_prediction_ns": 1565956
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
294,
401,
512
],
"summed_observed_prediction_ns": 1570958
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 38,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 58,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
6,
10,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
18,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
443,
508,
512
],
"summed_observed_prediction_ns": 1339334
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 20,
"actual_model_predictions": 100,
"actual_feedback_predictions": 36,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 76,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
12,
4,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
28,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
480,
512,
512
],
"summed_observed_prediction_ns": 1154835
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 157,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 47,
"actual_model_predictions": 126,
"actual_feedback_predictions": 62,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 49,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
7,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
9,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
157,
270,
402,
512
],
"summed_observed_prediction_ns": 1455868
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 158,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
158,
275,
392,
512
],
"summed_observed_prediction_ns": 1631584
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 145,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 45,
"actual_model_predictions": 125,
"actual_feedback_predictions": 61,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 51,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
11,
5,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
19,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
145,
316,
401,
512
],
"summed_observed_prediction_ns": 1602373
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 139,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
139,
277,
400,
512
],
"summed_observed_prediction_ns": 1754046
}
}
},
"v3-fp32": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2931,
"initial_complete_functions": 163,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 397,
"actual_model_predictions": 1360,
"actual_feedback_predictions": 592,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 755,
"bilingual_initial_mask_disagreements": 144,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
163,
96,
74,
51
],
"complete_function_curve_budgets_1_to_4": [
163,
259,
333,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2931,
4471,
5560,
6144
],
"summed_observed_prediction_ns": 13122380
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 263,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 105,
"actual_feedback_predictions": 41,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
263,
399,
452,
512
],
"summed_observed_prediction_ns": 985335
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 288,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 121,
"actual_feedback_predictions": 57,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
12,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
288,
363,
512,
512
],
"summed_observed_prediction_ns": 1152877
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 277,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 106,
"actual_feedback_predictions": 42,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
277,
400,
403,
512
],
"summed_observed_prediction_ns": 1095836
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 218,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 29,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 67,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
11,
9,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
23,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
218,
386,
512,
512
],
"summed_observed_prediction_ns": 1126918
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 152,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 44,
"actual_model_predictions": 124,
"actual_feedback_predictions": 60,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 52,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
12,
4,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
20,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
152,
346,
411,
512
],
"summed_observed_prediction_ns": 1216379
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 296,
"initial_complete_functions": 18,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
18,
2,
6,
6
],
"complete_function_curve_budgets_1_to_4": [
18,
20,
26,
32
],
"best_passing_case_curve_budgets_1_to_4": [
296,
332,
428,
512
],
"summed_observed_prediction_ns": 980461
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 36,
"actual_model_predictions": 116,
"actual_feedback_predictions": 52,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 60,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
8,
8,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
20,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
418,
508,
512
],
"summed_observed_prediction_ns": 1092914
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 390,
"initial_complete_functions": 24,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 17,
"actual_model_predictions": 87,
"actual_feedback_predictions": 23,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 79,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
24,
1,
5,
2
],
"complete_function_curve_budgets_1_to_4": [
24,
25,
30,
32
],
"best_passing_case_curve_budgets_1_to_4": [
390,
451,
510,
512
],
"summed_observed_prediction_ns": 881791
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 157,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 45,
"actual_model_predictions": 125,
"actual_feedback_predictions": 61,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 51,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
8,
8,
7
],
"complete_function_curve_budgets_1_to_4": [
9,
17,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
157,
294,
404,
512
],
"summed_observed_prediction_ns": 1220584
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 23,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 73,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
9,
7,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
25,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
403,
512,
512
],
"summed_observed_prediction_ns": 1068956
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 150,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 126,
"actual_feedback_predictions": 62,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
10,
6,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
18,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
150,
302,
396,
512
],
"summed_observed_prediction_ns": 1140374
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 204,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 29,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 67,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
11,
9,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
23,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
204,
377,
512,
512
],
"summed_observed_prediction_ns": 1159955
}
}
},
"v3-ptq_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2519,
"initial_complete_functions": 127,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 465,
"actual_model_predictions": 1440,
"actual_feedback_predictions": 672,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 687,
"bilingual_initial_mask_disagreements": 100,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
127,
104,
98,
55
],
"complete_function_curve_budgets_1_to_4": [
127,
231,
329,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2519,
4241,
5548,
6144
],
"summed_observed_prediction_ns": 15688552
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 238,
"initial_complete_functions": 10,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 124,
"actual_feedback_predictions": 60,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
10,
6,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
10,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
238,
390,
475,
512
],
"summed_observed_prediction_ns": 1308996
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 179,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 37,
"actual_model_predictions": 125,
"actual_feedback_predictions": 61,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 59,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
11,
13,
0
],
"complete_function_curve_budgets_1_to_4": [
8,
19,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
179,
312,
512,
512
],
"summed_observed_prediction_ns": 1427874
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 179,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
179,
293,
403,
512
],
"summed_observed_prediction_ns": 1380166
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 155,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 40,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 56,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
16,
0
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
155,
289,
512,
512
],
"summed_observed_prediction_ns": 1354787
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
289,
401,
512
],
"summed_observed_prediction_ns": 1375877
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 161,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 48,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 48,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
161,
289,
401,
512
],
"summed_observed_prediction_ns": 1372426
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 38,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 58,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
6,
10,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
18,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
401,
508,
512
],
"summed_observed_prediction_ns": 1316837
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 40,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 56,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
4,
12,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
16,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
386,
508,
512
],
"summed_observed_prediction_ns": 1300833
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 290,
"initial_complete_functions": 17,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 29,
"actual_model_predictions": 103,
"actual_feedback_predictions": 39,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 67,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
17,
8,
0,
7
],
"complete_function_curve_budgets_1_to_4": [
17,
25,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
290,
404,
404,
512
],
"summed_observed_prediction_ns": 1109421
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 213,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 27,
"actual_model_predictions": 114,
"actual_feedback_predictions": 50,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 69,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
13,
7,
0
],
"complete_function_curve_budgets_1_to_4": [
12,
25,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
213,
404,
512,
512
],
"summed_observed_prediction_ns": 1222630
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 104,
"actual_feedback_predictions": 40,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
8,
0,
8
],
"complete_function_curve_budgets_1_to_4": [
16,
24,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
392,
400,
512
],
"summed_observed_prediction_ns": 1183372
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 139,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 120,
"actual_feedback_predictions": 56,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
16,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
8,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
139,
392,
512,
512
],
"summed_observed_prediction_ns": 1335333
}
}
},
"v3-qat_ternary": {
"total": {
"function_views": 384,
"ordered_finite_cases": 6144,
"initial_cases_passed": 2269,
"initial_complete_functions": 115,
"complete_functions_by_budget_four": 384,
"additional_candidate_attempts": 470,
"actual_model_predictions": 1479,
"actual_feedback_predictions": 711,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 682,
"bilingual_initial_mask_disagreements": 166,
"bilingual_function_pairs": 192,
"minimum_complete_budget_histogram_1_to_4": [
115,
126,
85,
58
],
"complete_function_curve_budgets_1_to_4": [
115,
241,
326,
384
],
"best_passing_case_curve_budgets_1_to_4": [
2269,
4348,
5482,
6144
],
"summed_observed_prediction_ns": 16228448
},
"family_language": {
"assignment_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 201,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 46,
"actual_model_predictions": 128,
"actual_feedback_predictions": 64,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 50,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
8,
10,
6
],
"complete_function_curve_budgets_1_to_4": [
8,
16,
26,
32
],
"best_passing_case_curve_budgets_1_to_4": [
201,
390,
478,
512
],
"summed_observed_prediction_ns": 1405413
},
"assignment_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 240,
"initial_complete_functions": 10,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 30,
"actual_model_predictions": 118,
"actual_feedback_predictions": 54,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 66,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
10,
14,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
10,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
240,
404,
512,
512
],
"summed_observed_prediction_ns": 1272663
},
"assignment_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 105,
"initial_complete_functions": 4,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 52,
"actual_model_predictions": 136,
"actual_feedback_predictions": 72,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 44,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
4,
12,
8,
8
],
"complete_function_curve_budgets_1_to_4": [
4,
16,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
105,
293,
402,
512
],
"summed_observed_prediction_ns": 1500620
},
"assignment_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 160,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 124,
"actual_feedback_predictions": 60,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
16,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
8,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
160,
402,
512,
512
],
"summed_observed_prediction_ns": 1331831
},
"branch_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 89,
"initial_complete_functions": 4,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 54,
"actual_model_predictions": 139,
"actual_feedback_predictions": 75,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 42,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
4,
11,
8,
9
],
"complete_function_curve_budgets_1_to_4": [
4,
15,
23,
32
],
"best_passing_case_curve_budgets_1_to_4": [
89,
272,
398,
512
],
"summed_observed_prediction_ns": 1506342
},
"branch_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 221,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 41,
"actual_model_predictions": 119,
"actual_feedback_predictions": 55,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 55,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
7,
5,
8
],
"complete_function_curve_budgets_1_to_4": [
12,
19,
24,
32
],
"best_passing_case_curve_budgets_1_to_4": [
221,
334,
399,
512
],
"summed_observed_prediction_ns": 1294867
},
"predicate_branch/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 12,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 112,
"actual_feedback_predictions": 48,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
12,
12,
4,
4
],
"complete_function_curve_budgets_1_to_4": [
12,
24,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
450,
508,
512
],
"summed_observed_prediction_ns": 1193248
},
"predicate_branch/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 328,
"initial_complete_functions": 20,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 27,
"actual_model_predictions": 99,
"actual_feedback_predictions": 35,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 69,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
20,
1,
7,
4
],
"complete_function_curve_budgets_1_to_4": [
20,
21,
28,
32
],
"best_passing_case_curve_budgets_1_to_4": [
328,
447,
508,
512
],
"summed_observed_prediction_ns": 1127786
},
"reference_operand/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 157,
"initial_complete_functions": 9,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 41,
"actual_model_predictions": 126,
"actual_feedback_predictions": 62,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 55,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
9,
12,
4,
7
],
"complete_function_curve_budgets_1_to_4": [
9,
21,
25,
32
],
"best_passing_case_curve_budgets_1_to_4": [
157,
348,
404,
512
],
"summed_observed_prediction_ns": 1364718
},
"reference_operand/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 268,
"initial_complete_functions": 16,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 23,
"actual_model_predictions": 110,
"actual_feedback_predictions": 46,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 73,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
16,
9,
7,
0
],
"complete_function_curve_budgets_1_to_4": [
16,
25,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
268,
403,
512,
512
],
"summed_observed_prediction_ns": 1259041
},
"reference_schedule/en": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 88,
"initial_complete_functions": 4,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 60,
"actual_model_predictions": 144,
"actual_feedback_predictions": 80,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 36,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
4,
8,
8,
12
],
"complete_function_curve_budgets_1_to_4": [
4,
12,
20,
32
],
"best_passing_case_curve_budgets_1_to_4": [
88,
213,
337,
512
],
"summed_observed_prediction_ns": 1598959
},
"reference_schedule/ko": {
"function_views": 32,
"ordered_finite_cases": 512,
"initial_cases_passed": 144,
"initial_complete_functions": 8,
"complete_functions_by_budget_four": 32,
"additional_candidate_attempts": 32,
"actual_model_predictions": 124,
"actual_feedback_predictions": 60,
"zero_call_feedback_context_declines": 0,
"type_rejections": 0,
"unattempted_masks_after_completion": 64,
"bilingual_initial_mask_disagreements": 0,
"bilingual_function_pairs": 0,
"minimum_complete_budget_histogram_1_to_4": [
8,
16,
8,
0
],
"complete_function_curve_budgets_1_to_4": [
8,
24,
32,
32
],
"best_passing_case_curve_budgets_1_to_4": [
144,
392,
512,
512
],
"summed_observed_prediction_ns": 1372960
}
}
}
},
"go_python_parity_max_absolute_error": {
"v2": 1.4901161193847656e-7,
"v3": 2.682209014892578e-7
},
"native_calls": 0,
"new_optimizer_updates": 0,
"parity_predictions": 192,
"runtime": {
"v2-fp32": {
"warm_benchmark_predictions": 1001,
"warm_ns_per_prediction": 9445.75,
"predict_into_heap_allocations_per_call": 0,
"allocation_probe_predictions": 1001,
"resident_tensor_bytes": 50912,
"matrix_scale_bytes": 0,
"workspace_bytes": 1248
},
"v2-ptq_ternary": {
"warm_benchmark_predictions": 1001,
"warm_ns_per_prediction": 10591.542,
"predict_into_heap_allocations_per_call": 0,
"allocation_probe_predictions": 1001,
"resident_tensor_bytes": 12896,
"matrix_scale_bytes": 8,
"workspace_bytes": 1248
},
"v2-qat_ternary": {
"warm_benchmark_predictions": 1001,
"warm_ns_per_prediction": 10927.917,
"predict_into_heap_allocations_per_call": 0,
"allocation_probe_predictions": 1001,
"resident_tensor_bytes": 12896,
"matrix_scale_bytes": 8,
"workspace_bytes": 1248
},
"v3-fp32": {
"warm_benchmark_predictions": 1001,
"warm_ns_per_prediction": 8280.458,
"predict_into_heap_allocations_per_call": 0,
"allocation_probe_predictions": 1001,
"resident_tensor_bytes": 50912,
"matrix_scale_bytes": 0,
"workspace_bytes": 1248
},
"v3-ptq_ternary": {
"warm_benchmark_predictions": 1001,
"warm_ns_per_prediction": 9686.167,
"predict_into_heap_allocations_per_call": 0,
"allocation_probe_predictions": 1001,
"resident_tensor_bytes": 12896,
"matrix_scale_bytes": 8,
"workspace_bytes": 1248
},
"v3-qat_ternary": {
"warm_benchmark_predictions": 1001,
"warm_ns_per_prediction": 9674.833,
"predict_into_heap_allocations_per_call": 0,
"allocation_probe_predictions": 1001,
"resident_tensor_bytes": 12896,
"matrix_scale_bytes": 8,
"workspace_bytes": 1248
}
},
"schema": "gooo/fresh-composition-study/v1",
"scope": "Six compositions, four goals with bilingual/parameter variants; all 16 ordered independent cases retained. Model ranks legal compiler-owned fragments and observed feedback only. Calibration selector frozen before development sessions. Four-path completeness is finite enumerative evidence, not general language understanding. Warm inference allocations exclude loading/context/session and decoded ternary matrices remain int8.",
"selected_candidate": "v3-qat_ternary",
"source_revision": "15962b584c4d7d0841171323374c66b19a01cb9f",
"status": "PASS"
}