Files
Open_Ultra_SAST/benchmarks/measurements/2026-10-12-valid-benchmark-pilot/metrics_combined.json
T

80 lines
2.2 KiB
JSON

{
"exploit_verified": {
"count": 0,
"flagged_positive_pushes": 9,
"flagged_positives": 26,
"n": 0,
"not_yet_proved": [
"contentful-contentful-mcp-server-22e8b2fc09c3b2c4",
"contentful-contentful-mcp-server-df53a40a29ee8d8d",
"i18next-i18next-http-middleware-f3e2a6886951f36a",
"imzbf-md-editor-v3-14658213915dbde5",
"imzbf-md-editor-v3-b9c833a3524a57a9",
"jupyter-lsp-jupyterlab-lsp-59f9a8b80b133f6f",
"nvbn-thefuck-456ad18acb14f1b2",
"nvbn-thefuck-74126de049d52d8c",
"ondata-ckan-mcp-server-01a3f68f84397eb4",
"ondata-ckan-mcp-server-b0b05cdc830b1f8b",
"webpack-webpack-bundle-analyzer-8e07af8a5ee1cc52",
"zenitram-malla-15753fae1999978e",
"zenitram-malla-45807117f798f314",
"zenitram-malla-4c7ce7ae0b9dd0cf",
"zenitram-malla-5b8f3116fefd595b",
"zenitram-malla-72b8d4dc93a566fb",
"zenitram-malla-73c0175a1009ffbf",
"zenitram-malla-825a0f3ce563c373",
"zenitram-malla-858255cb6145e104",
"zenitram-malla-92e437caca55290b",
"zenitram-malla-aeb1d1e3d40815a8",
"zenitram-malla-bf4b3bcd2652952c",
"zenitram-malla-c3ab7f5f4e769cc6",
"zenitram-malla-f3535c03a02fa0e3",
"zereight-gitlab-mcp-2367b459f8c3802b",
"zereight-gitlab-mcp-768c7d5a32ccc95b"
],
"rate": null,
"status": "not yet proved",
"wilson95": [
null,
null
]
},
"false_alarms_per_100_pushes": {
"cluster95": [
47.89915966386555,
62.916666666666664
],
"count": 132,
"icc": 0.02916674829529659,
"n": 238,
"rate": 55.46218487394958,
"wilson95": [
49.11079301666095,
61.64004554874716
]
},
"headline": "On unseen app repos: recall 41.7% (Wilson 19.3-68.0), false alarms 55.5 per 100 pushes, precision 3.5%; exploit-verified 0 of 26 (26 not yet proved).",
"precision": {
"count": 5,
"n": 141,
"rate": 0.03546099290780142,
"wilson95": [
0.015239951514497675,
0.08032375394028879
]
},
"recall": {
"cluster95": [
0.16666666666666666,
0.6666666666666666
],
"count": 5,
"n": 12,
"rate": 0.4166666666666667,
"wilson95": [
0.19325746190524656,
0.6804926643446272
]
}
}