Files
Open_Ultra_SAST/benchmarks/measurements/2026-10-06-search-probe/record.json
T
Marius CiepluchandClaude Fable 5.1 263be30979 search-with-proof 3.2: oracle probe passes on kube-ax in task-boundary mode [skip ci]
All five oracles demonstrated, gaming demos inconclusive, 38 s, ~500 MB RSS.
The probe dispatcher accepts a skipped isolation check in task-boundary mode.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
2026-10-06 00:14:51 +02:00

67 lines
1.7 KiB
JSON

{
"date": "2026-10-06",
"image": "ghcr.io/norandom/ousast-search-task@sha256:32c7d23a41936c841b91edf27ded2d1fef5df9d656171e3ae199e7ed51ba0264",
"image_tools": {
"bwrap": "bubblewrap 0.12.0",
"chromium": "Chromium 154.0.8037.92 built on Debian G",
"java": "openjdk version \"21.0.12.1\" 2026-08-18\nO",
"node": "v20.19.2",
"php": "PHP 8.4.26 (cli) (built: Sep 24 2026 17:",
"python": "Python 3.13.5",
"sqlite": "3.46.1 2024-08-13 09:16:08 c9c2ab54ba1f5",
"tsc": "Version 4.9.5"
},
"isolation_check": {
"reason": "task-boundary",
"status": "skipped"
},
"isolation_mode": "task-boundary",
"lane": "kube-ax (AX task, gVisor, task-boundary)",
"namespaces": {
"cgroup": 1,
"ipc": 1,
"mount": 1,
"net": 1,
"pid": 1,
"setpriv": 127,
"user": 1,
"uts": 1
},
"oracles": {
"command": {
"observer_access": "inconclusive",
"real": "demonstrated",
"revision_patch": "inconclusive"
},
"path": {
"observer_access": "inconclusive",
"real": "demonstrated",
"revision_patch": "inconclusive"
},
"sql": {
"observer_access": "inconclusive",
"real": "demonstrated",
"revision_patch": "inconclusive"
},
"ssrf": {
"observer_access": "inconclusive",
"real": "demonstrated",
"revision_patch": "inconclusive"
},
"xss": {
"observer_access": "inconclusive",
"real": "demonstrated",
"revision_patch": "inconclusive"
}
},
"peak_rss_kib": {
"children": 460152,
"self": 42172,
"sum": 502324
},
"scratch_disk_bytes": 23040,
"status": "ok",
"task": "search-with-proof 3.2",
"wall_seconds": 38.368433234
}