Files
Open_Ultra_SAST/benchmarks/measurements/2026-10-30-access-control-four-arm/summary.json
T

490 lines
13 KiB
JSON

{
"arm_execution": {
"baseline-analyzer/baseline-facts": "immutable 2026-10-28 records, adapted (vocabulary: binary)",
"baseline-analyzer/candidate-facts": "alias of baseline arm by proven input identity",
"candidate-analyzer/baseline-facts": "alias of candidate arm by proven input identity",
"candidate-analyzer/candidate-facts": "executed 2026-10-30 (vocabulary: three-way)"
},
"bundles": {
"baseline": {
"acquisition_artifact": null,
"acquisition_record_digest": "none",
"analyzer_revision": "c5341d79a21bfae49ee157bdac19f967754f0be4",
"configuration_digest": "bc4d444e2bc4",
"fact_artifact": "facts-baseline.json",
"fact_set_digest": "3eb5bf699434"
},
"candidate": {
"acquisition_artifact": null,
"acquisition_record_digest": "none",
"analyzer_revision": "9c95f842f7263710ec7d106794b37eb94a45425d",
"configuration_digest": "be6d0f688598",
"fact_artifact": "facts-candidate.json",
"fact_set_digest": "3eb5bf699434"
}
},
"candidate_arm": {
"budget": {
"budget_seconds": 120.0,
"gate": "failed",
"overruns": [
{
"id": "099364c093061a7d02d2e728a503b753441bd455ae6ae5f6970326d1815ee6f4",
"seconds": 160.65696239499812
},
{
"id": "1d77199cf964d7f168f3f0c157646f52aef7e3931b8da2f9fa829e1e32931964",
"seconds": 237.99327803600318
},
{
"id": "3a66c58b6c2b345f622f00820bd833932c5fa02ccc0d03626ac95f9b179baf55",
"seconds": 160.20379009899625
},
{
"id": "514850869e2c19bfc55dbc75b2c1e1766249e12f04385b1de7b4d116b6b209fa",
"seconds": 239.97186829699785
},
{
"id": "58a2ffe30e0bc6a166a01fe016ebf43b0c0f3385b0f4a2e8578d3e039371c17e",
"seconds": 135.12179498800106
},
{
"id": "59327d70f193338a3ae990177f6fa8aece8e6913e6e5d3a27888d383edb56165",
"seconds": 195.88553729499836
},
{
"id": "5c73c7dac092be000911ad6d4327156dbdc7a02d3d22545cfe47a25b67ce76ec",
"seconds": 201.59726526400482
},
{
"id": "5c9a822532e45241cb40e12ba6437837bf0301a6b2bead1261fbaa90e028f211",
"seconds": 238.12383715200122
},
{
"id": "720017c40d9dd8ad541f00c2577b2d1676ba3dfcaa997166a1065dbb36b42231",
"seconds": 136.7938399220002
},
{
"id": "75f92ee98982d750540239481ee8aa4258ec3cc3cb64cce6ca19835d9fcf2d99",
"seconds": 195.32054610600608
},
{
"id": "a505c341e4c5e363b3050d1523bd8f6868c10e3cd5ed383d3c8e155b49bf9a70",
"seconds": 168.9383434449992
},
{
"id": "bada9b8aaceaff26178d1940f7f6032b24d213071c54c30d2e7ce929e557df90",
"seconds": 170.55653589800204
},
{
"id": "c0fca5070cee86d26832638230b364f45d245c6e1a77333d38ee393832291e13",
"seconds": 238.88118421599938
},
{
"id": "c1859d8c2376e25dd46024b336bb8106a702f8139437934cf48d282cf0f396cb",
"seconds": 203.85092047799844
},
{
"id": "c2c52c1bb6b1f0d70b29b7b64009d6ca85c6e4d3659a195a904d577f6b02c886",
"seconds": 193.02569297700393
},
{
"id": "da89557ec3cada71aed38482d8269959d56e9a37877f66d69cf5b3905d0cbcff",
"seconds": 238.55912208399968
},
{
"id": "e0b9c856901ff36c6e54a0a73752b06f6a9996930702c18593c25936709d4c79",
"seconds": 162.15434529800405
},
{
"id": "e934b0222e338b768bfc594668434850f18e3a7ee35a76fb35c19898d4924349",
"seconds": 162.4909854649959
},
{
"id": "ea9ed8aad6259c9ea8ee1f8227a981710e8b4b1da838e74d6e68075455e78631",
"seconds": 163.5947257539956
},
{
"id": "f664ff98347b54ace35a50a499c77cfe3c6e06158e78f76f20b9d9317a29bb94",
"seconds": 160.8364557419991
}
]
},
"development_only": true,
"instrument_failures": 0,
"judgment_counts": {
"discharged": 0,
"indeterminate": 102,
"unguarded": 94
},
"per_repository": {
"03d0eff98aa6": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 44,
"status": "covered",
"unguarded": 2
},
"0bdd00190b32": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 6179,
"status": "covered",
"unguarded": 3
},
"1ca62ca671af": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 0,
"status": "uncovered",
"unguarded": 0
},
"34b17c3454d8": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 828,
"status": "covered",
"unguarded": 13
},
"3caf85f05a65": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 559,
"status": "covered",
"unguarded": 23
},
"4b7075e3d5a1": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 93,
"status": "covered",
"unguarded": 11
},
"4dde9ea84248": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 100,
"status": "covered",
"unguarded": 3
},
"4e75cb1165d3": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 65,
"status": "covered",
"unguarded": 3
},
"69f3c5cdd90a": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 115,
"status": "covered",
"unguarded": 7
},
"6a4eac96c6ae": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 108,
"status": "covered",
"unguarded": 4
},
"6c1d234f9e23": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 21,
"status": "covered",
"unguarded": 0
},
"6c92cca94d4b": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 470,
"status": "covered",
"unguarded": 2
},
"760591cb57ba": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 87,
"status": "covered",
"unguarded": 5
},
"78d80100d68f": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 98,
"status": "covered",
"unguarded": 1
},
"89c10adb0673": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 91,
"status": "covered",
"unguarded": 0
},
"9047b2efc25b": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 86,
"status": "covered",
"unguarded": 0
},
"ba37e9ee7b7b": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 163,
"status": "covered",
"unguarded": 1
},
"c5bd586fae3f": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 33,
"status": "covered",
"unguarded": 6
},
"c690d767b023": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 29,
"status": "covered",
"unguarded": 5
},
"c92157c966cc": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 0,
"status": "uncovered",
"unguarded": 0
},
"d8eda62c6cc2": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 58,
"status": "covered",
"unguarded": 5
},
"e89a8c0f281c": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 375,
"status": "covered",
"unguarded": 0
},
"ed1f033972e0": {
"changes": 21,
"discharged": 0,
"frameworks_recognised": 355,
"status": "covered",
"unguarded": 0
}
},
"population_role": "development",
"seconds_per_change": {
"maximum": 239.97186829699785,
"mean": 17.395369377060025,
"median": 1.0545286380001926,
"n": 483
},
"total_changes": 483,
"uncovered_repositories": [
"1ca62ca671af",
"c92157c966cc"
]
},
"comparison_to_immutable_baseline": {
"current": {
"covered_recall": {
"count": 8,
"n": 21,
"rate": 0.38095238095238093,
"wilson95": [
0.20750767797982506,
0.5912170418449848
]
},
"false_alarms_per_100_pushes": {
"cluster95": [
2.608695652173913,
8.478260869565217
],
"count": 24,
"icc": 0.06521124844323971,
"n": 460,
"rate": 5.217391304347826,
"wilson95": [
3.5308056950422455,
7.645768376796072
]
},
"instrument_failures": 0,
"location_recall": {
"count": 25,
"n": 93,
"rate": 0.26881720430107525,
"wilson95": [
0.1892118216186081,
0.36676412260370955
]
},
"precision": {
"count": 8,
"n": 32,
"rate": 0.25,
"wilson95": [
0.1325224398262155,
0.42106891770246624
]
},
"recall_on_fix_changes": {
"count": 8,
"n": 23,
"rate": 0.34782608695652173,
"wilson95": [
0.18811054636982238,
0.5511002309310836
]
},
"uncovered_recall": {
"count": 0,
"n": 2,
"rate": 0.0,
"wilson95": [
0,
0.6576280471103807
]
}
},
"immutable_baseline": {
"false_alarms_per_100_pushes": {
"cluster95": [
8.695652173913043,
21.521739130434785
],
"count": 69,
"icc": 0.144640754781103,
"n": 460,
"rate": 15.0,
"wilson95": [
12.027398310244092,
18.552351328425665
]
},
"instrument_failures": 0,
"location_recall": {
"count": 55,
"n": 93,
"rate": 0.5913978494623656,
"wilson95": [
0.4897977403042717,
0.6857466538403933
]
},
"precision": {
"count": 15,
"n": 84,
"rate": 0.17857142857142858,
"wilson95": [
0.1113109090339025,
0.2739461901081896
]
},
"recall_on_fix_changes": {
"count": 15,
"n": 23,
"rate": 0.6521739130434783,
"wilson95": [
0.4488997690689164,
0.8118894536301776
]
}
},
"note": "regression evidence against the immutable 2026-10-28 baseline; development population only, never an untouched-population result"
},
"date": "2026-10-30",
"development_only": true,
"fact_inputs_identical": {
"fact_set_digest": "e7db4031d3d5",
"identical": true
},
"four_arm": {
"arms": [
"baseline-analyzer/baseline-facts",
"baseline-analyzer/candidate-facts",
"candidate-analyzer/baseline-facts",
"candidate-analyzer/candidate-facts"
],
"attribution": {
"analyzer_only_lift": {
"discharged": -130,
"indeterminate": 102,
"unguarded": -246
},
"arms": [
"baseline-analyzer/baseline-facts",
"baseline-analyzer/candidate-facts",
"candidate-analyzer/baseline-facts",
"candidate-analyzer/candidate-facts"
],
"fact_only_lift": {
"discharged": 0,
"indeterminate": 0,
"unguarded": 0
},
"funnel_delta_fact_only": {
"seconds": 0.0
},
"judgment_delta_analyzer_only": {
"discharged": -130,
"indeterminate": 102,
"unguarded": -246
},
"judgment_delta_fact_only": {
"discharged": 0,
"indeterminate": 0,
"unguarded": 0
},
"transitions": [
"flagged->indeterminate",
"flagged->none",
"flagged->unguarded",
"quiet->indeterminate",
"quiet->none",
"quiet->unguarded",
"same"
]
},
"fact_inputs_identical": true,
"per_change_transitions": {
"flagged->indeterminate": 25,
"flagged->none": 30,
"flagged->unguarded": 29,
"quiet->indeterminate": 8,
"quiet->none": 388,
"quiet->unguarded": 3
}
},
"population": {
"changes": 483,
"freeze_verified": true,
"per_record_stamp_note": "executed-arm records carry the shard-scoped population digest of the subset their worker processed (8b7be14b70df shard 0, 27fb15c10491 shard 1); this field is the authoritative full-population digest over all 483 change ids. Baseline-arm adapted records carry no population stamp from the immutable 2026-10-28 run; disclosed rather than back-filled.",
"pool": "benchmarks/valid/train/pool-train.toml",
"population_digest": "999594274a4e"
},
"population_role": "development",
"stage_funnel": {
"entry_points": 17046,
"judgment_counts": {
"discharged": 0,
"indeterminate": 102,
"unguarded": 94
},
"resolution": {
"complete_calls": 589520,
"incomplete_calls": 1451325,
"unresolved_calls": 2908559
}
}
}