Files
Open_Ultra_SAST/benchmarks/independent/verifier-batched-check-2026-09-29.json
T

37 lines
1.2 KiB
JSON
Raw Normal View History

{
"measurement": "verify_batched.py on the 46-candidate validation set (15 declared-site cases + 26 flickering pgAdmin candidates), triage on, 2 passes, 6 steps, $1.01",
"declared_sites": {
"agreed": 16,
"of": 20,
"cases_detected": 12,
"of_cases_with_a_candidate_site": 15,
"newly_found_vs_per_candidate_design": [
"budibase (both sites)",
"froxlor listing/listingCount"
],
"lost": [
"unleash fetchRetry (found in 1 of 2 passes)"
],
"missed": [
"winml (triage: constant -- a CORS literal; the reachability question does not fit config_secrets)",
"fuxa getDaqValue (1 of 2 passes)",
"froxlor validateIpAddresses (1 of 2)"
]
},
"flickering_pgadmin_26": {
"triaged_out": 2,
"agreed_in_both_passes": 9,
"disputed": 4,
"quiet": 13,
"note": "the 9 need adjudication; agreement turns run-to-run noise into a stable set"
},
"cost": {
"usd_per_candidate_two_passes": 0.022,
"old_design_two_passes": 0.0334,
"pgadmin_subset_per_candidate_two_passes": 0.0146,
"old_single_pass": 0.0167,
"note": "per-file batching: ~2.3x cheaper per pass on a file with several candidates"
},
"decision_pending": "full run of all 17 cases with this design"
}