mirror of
https://github.com/norandom/OpenUltraSAST.git
synced 2026-10-16 11:49:28 +00:00
81 lines
2.2 KiB
JSON
81 lines
2.2 KiB
JSON
{
|
|
"experiment": "exp-004-pooled-block-gate",
|
|
"date": "2026-10-03",
|
|
"fill": {
|
|
"client_calls": 2073,
|
|
"usd": 1.238223,
|
|
"ceiling_usd": 2.0,
|
|
"still_missing": 0,
|
|
"dry_run_estimate_usd": 5.582,
|
|
"note": "the dry-run estimator over-priced 4.5x (no prompt-cache pricing); measured spend is the meter's"
|
|
},
|
|
"run": {
|
|
"units": 501,
|
|
"client_calls": 0,
|
|
"usd": 0.0,
|
|
"replayed": 2509,
|
|
"replay_miss": 0
|
|
},
|
|
"verdict": "inconclusive",
|
|
"reason": "no t_block on any outer fold, pooled or per family; B offers no BLOCK",
|
|
"instrument_check": {
|
|
"per_family": {
|
|
"access_control": {
|
|
"n": 66,
|
|
"distinct_scores": 41,
|
|
"unsure": 5,
|
|
"pairs": 28,
|
|
"within_pair_wins": 22,
|
|
"ties": 1,
|
|
"positives_above_first_negative": 12
|
|
},
|
|
"deserialization": {
|
|
"n": 64,
|
|
"distinct_scores": 38,
|
|
"unsure": 7,
|
|
"pairs": 25,
|
|
"within_pair_wins": 18,
|
|
"ties": 4,
|
|
"positives_above_first_negative": 5
|
|
},
|
|
"injection": {
|
|
"n": 149,
|
|
"distinct_scores": 52,
|
|
"unsure": 54,
|
|
"pairs": 53,
|
|
"within_pair_wins": 30,
|
|
"ties": 17,
|
|
"positives_above_first_negative": 6
|
|
},
|
|
"output_encoding": {
|
|
"n": 69,
|
|
"distinct_scores": 31,
|
|
"unsure": 32,
|
|
"pairs": 28,
|
|
"within_pair_wins": 18,
|
|
"ties": 6,
|
|
"positives_above_first_negative": 2
|
|
},
|
|
"path": {
|
|
"n": 66,
|
|
"distinct_scores": 43,
|
|
"unsure": 15,
|
|
"pairs": 29,
|
|
"within_pair_wins": 25,
|
|
"ties": 3,
|
|
"positives_above_first_negative": 13
|
|
},
|
|
"untrusted_destination": {
|
|
"n": 87,
|
|
"distinct_scores": 36,
|
|
"unsure": 33,
|
|
"pairs": 32,
|
|
"within_pair_wins": 18,
|
|
"ties": 4,
|
|
"positives_above_first_negative": 3
|
|
}
|
|
},
|
|
"pooled_raw_top30_labels": "111111111110111110111111110111",
|
|
"reading": "scores are real (31-52 distinct values per family); pooled raw top 30 holds 27 positives (0.90), first negative at rank 12; the Wilson bound needs >= 73 flags with no error, so precision at the top, not data volume alone, now binds"
|
|
}
|
|
} |