aiflow-math-ink-06-intermediate / reports /component_competition_report.json
cwLeeDev's picture
Add AIFlow Math Ink 0.6 intermediate research snapshot
2948983 verified
Raw
History Blame Contribute Delete
22.3 kB
{
"experiment": "R-MATH-INK-06-COMPONENT-COMPETITION-GUARD-001",
"generated_at": "2026-07-23T18:30:20.711476+00:00",
"selection_contract": {
"split": "CROHME trainData writer-validation only",
"cross_gap_ratio": 0.4,
"multistroke_family_boost": 6.0,
"maximum_x_regression_pp": 1.0,
"maximum_family_regression_pp": 2.0,
"maximum_pair_f1_regression_pp": 0.25
},
"reference_validation": {
"component_competition_weight": 0.0,
"global": {
"formulas": 275,
"exact_partition": 0.68,
"exact_group_recall": 0.9528054535920294,
"overmerge_rate": 0.14909090909090908,
"oversplit_rate": 0.21818181818181817,
"pair_precision": 0.9563838223632039,
"pair_recall": 0.9047261815453863,
"pair_f1": 0.9298380878951427
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 244,
"oversplit": 31,
"overmerge": 3,
"grouping_recall": 0.8808664259927798
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 51,
"grouping_recall": 0.864406779661017,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 17,
"grouping_recall": 0.85
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
"winner_validation": {
"component_competition_weight": 0.0,
"global": {
"formulas": 275,
"exact_partition": 0.68,
"exact_group_recall": 0.9528054535920294,
"overmerge_rate": 0.14909090909090908,
"oversplit_rate": 0.21818181818181817,
"pair_precision": 0.9563838223632039,
"pair_recall": 0.9047261815453863,
"pair_f1": 0.9298380878951427
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 244,
"oversplit": 31,
"overmerge": 3,
"grouping_recall": 0.8808664259927798
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 51,
"grouping_recall": 0.864406779661017,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 17,
"grouping_recall": 0.85
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
"trials": [
{
"component_competition_weight": 0.0,
"global": {
"formulas": 275,
"exact_partition": 0.68,
"exact_group_recall": 0.9528054535920294,
"overmerge_rate": 0.14909090909090908,
"oversplit_rate": 0.21818181818181817,
"pair_precision": 0.9563838223632039,
"pair_recall": 0.9047261815453863,
"pair_f1": 0.9298380878951427
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 244,
"oversplit": 31,
"overmerge": 3,
"grouping_recall": 0.8808664259927798
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 51,
"grouping_recall": 0.864406779661017,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 17,
"grouping_recall": 0.85
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 1.0,
"global": {
"formulas": 275,
"exact_partition": 0.68,
"exact_group_recall": 0.9538542212899843,
"overmerge_rate": 0.14181818181818182,
"oversplit_rate": 0.22545454545454546,
"pair_precision": 0.9585326953748007,
"pair_recall": 0.9017254313578394,
"pair_f1": 0.9292616930807887
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 244,
"oversplit": 31,
"overmerge": 3,
"grouping_recall": 0.8808664259927798
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 50,
"grouping_recall": 0.847457627118644,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 16,
"grouping_recall": 0.8
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 2.0,
"global": {
"formulas": 275,
"exact_partition": 0.6727272727272727,
"exact_group_recall": 0.9538542212899843,
"overmerge_rate": 0.13090909090909092,
"oversplit_rate": 0.23272727272727273,
"pair_precision": 0.9599037690457097,
"pair_recall": 0.8979744936234059,
"pair_f1": 0.9279069767441861
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 242,
"oversplit": 33,
"overmerge": 3,
"grouping_recall": 0.8736462093862816
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 50,
"grouping_recall": 0.847457627118644,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 16,
"grouping_recall": 0.8
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 3.0,
"global": {
"formulas": 275,
"exact_partition": 0.6436363636363637,
"exact_group_recall": 0.9509701101206083,
"overmerge_rate": 0.13090909090909092,
"oversplit_rate": 0.26545454545454544,
"pair_precision": 0.9586038961038961,
"pair_recall": 0.8859714928732183,
"pair_f1": 0.9208576998050683
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 240,
"oversplit": 35,
"overmerge": 3,
"grouping_recall": 0.8664259927797834
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 50,
"grouping_recall": 0.847457627118644,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 16,
"grouping_recall": 0.8
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 4.0,
"global": {
"formulas": 275,
"exact_partition": 0.64,
"exact_group_recall": 0.9507079181961196,
"overmerge_rate": 0.12363636363636364,
"oversplit_rate": 0.28,
"pair_precision": 0.9607843137254902,
"pair_recall": 0.8822205551387847,
"pair_f1": 0.9198279233476732
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 240,
"oversplit": 35,
"overmerge": 3,
"grouping_recall": 0.8664259927797834
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 50,
"grouping_recall": 0.847457627118644,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 16,
"grouping_recall": 0.8
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 6.0,
"global": {
"formulas": 275,
"exact_partition": 0.6290909090909091,
"exact_group_recall": 0.9499213424226534,
"overmerge_rate": 0.11636363636363636,
"oversplit_rate": 0.29818181818181816,
"pair_precision": 0.9628406275805119,
"pair_recall": 0.8747186796699175,
"pair_f1": 0.9166666666666666
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 239,
"oversplit": 36,
"overmerge": 3,
"grouping_recall": 0.8628158844765343
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 50,
"grouping_recall": 0.847457627118644,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 16,
"grouping_recall": 0.8
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 8.0,
"global": {
"formulas": 275,
"exact_partition": 0.6145454545454545,
"exact_group_recall": 0.948348190875721,
"overmerge_rate": 0.11272727272727273,
"oversplit_rate": 0.31636363636363635,
"pair_precision": 0.9633943427620633,
"pair_recall": 0.8687171792948237,
"pair_f1": 0.9136094674556214
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 237,
"oversplit": 38,
"overmerge": 3,
"grouping_recall": 0.855595667870036
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 50,
"grouping_recall": 0.847457627118644,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 15,
"grouping_recall": 0.8823529411764706
},
"\\rightarrow": {
"samples": 20,
"matched": 16,
"grouping_recall": 0.8
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
},
{
"component_competition_weight": 12.0,
"global": {
"formulas": 275,
"exact_partition": 0.5527272727272727,
"exact_group_recall": 0.9396958573675931,
"overmerge_rate": 0.11272727272727273,
"oversplit_rate": 0.3927272727272727,
"pair_precision": 0.9621993127147767,
"pair_recall": 0.8402100525131283,
"pair_f1": 0.8970764917901483
},
"behavior_targets": {
"x": {
"samples": 277,
"matched": 229,
"oversplit": 46,
"overmerge": 3,
"grouping_recall": 0.8267148014440433
},
"X": {
"samples": 7,
"matched": 7,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
},
"\\times": {
"samples": 44,
"matched": 44,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 59,
"matched": 48,
"grouping_recall": 0.8135593220338984,
"by_label": {
"\\sum": {
"samples": 11,
"matched": 8,
"grouping_recall": 0.7272727272727273
},
"\\pi": {
"samples": 17,
"matched": 14,
"grouping_recall": 0.8235294117647058
},
"\\rightarrow": {
"samples": 20,
"matched": 15,
"grouping_recall": 0.75
},
"\\neq": {
"samples": 2,
"matched": 2,
"grouping_recall": 1.0
},
"\\pm": {
"samples": 9,
"matched": 9,
"grouping_recall": 1.0
}
}
}
}
],
"official_test_reference": {
"component_competition_weight": 0.0,
"global": {
"formulas": 488,
"exact_partition": 0.6004098360655737,
"exact_group_recall": 0.9370456528060482,
"overmerge_rate": 0.21721311475409835,
"oversplit_rate": 0.2520491803278688,
"pair_precision": 0.9231143552311436,
"pair_recall": 0.8986262434864993,
"pair_f1": 0.9107057129140663
},
"behavior_targets": {
"x": {
"samples": 450,
"matched": 412,
"oversplit": 30,
"overmerge": 12,
"grouping_recall": 0.9155555555555556
},
"X": {
"samples": 14,
"matched": 12,
"oversplit": 2,
"overmerge": 1,
"grouping_recall": 0.8571428571428571
},
"\\times": {
"samples": 36,
"matched": 36,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 135,
"matched": 112,
"grouping_recall": 0.8296296296296296,
"by_label": {
"\\sum": {
"samples": 31,
"matched": 22,
"grouping_recall": 0.7096774193548387
},
"\\pi": {
"samples": 30,
"matched": 27,
"grouping_recall": 0.9
},
"\\rightarrow": {
"samples": 49,
"matched": 44,
"grouping_recall": 0.8979591836734694
},
"\\neq": {
"samples": 13,
"matched": 10,
"grouping_recall": 0.7692307692307693
},
"\\pm": {
"samples": 12,
"matched": 9,
"grouping_recall": 0.75
}
}
}
},
"official_test_winner": {
"component_competition_weight": 0.0,
"global": {
"formulas": 488,
"exact_partition": 0.6004098360655737,
"exact_group_recall": 0.9370456528060482,
"overmerge_rate": 0.21721311475409835,
"oversplit_rate": 0.2520491803278688,
"pair_precision": 0.9231143552311436,
"pair_recall": 0.8986262434864993,
"pair_f1": 0.9107057129140663
},
"behavior_targets": {
"x": {
"samples": 450,
"matched": 412,
"oversplit": 30,
"overmerge": 12,
"grouping_recall": 0.9155555555555556
},
"X": {
"samples": 14,
"matched": 12,
"oversplit": 2,
"overmerge": 1,
"grouping_recall": 0.8571428571428571
},
"\\times": {
"samples": 36,
"matched": 36,
"oversplit": 0,
"overmerge": 0,
"grouping_recall": 1.0
}
},
"families": {
"total": 135,
"matched": 112,
"grouping_recall": 0.8296296296296296,
"by_label": {
"\\sum": {
"samples": 31,
"matched": 22,
"grouping_recall": 0.7096774193548387
},
"\\pi": {
"samples": 30,
"matched": 27,
"grouping_recall": 0.9
},
"\\rightarrow": {
"samples": 49,
"matched": 44,
"grouping_recall": 0.8979591836734694
},
"\\neq": {
"samples": 13,
"matched": 10,
"grouping_recall": 0.7692307692307693
},
"\\pm": {
"samples": 12,
"matched": 9,
"grouping_recall": 0.75
}
}
}
},
"official_test_deltas": {
"exact_partition_pp": 0.0,
"pair_f1_pp": 0.0,
"x_grouping_pp": 0.0,
"family_grouping_pp": 0.0
},
"decision": {
"adopted": false,
"selected_component_competition_weight": 0.0,
"reason": "official adoption gate failed"
},
"track": "R_noncommercial_only",
"product_validation": false
}