Files

22 lines
546 B
JSON

{
"model": "openai/deepseek-flash",
"judgments": 340,
"failed": 0,
"pushes_flagged_by_prover": 84,
"true_pushes_kept": "15/15",
"false_pushes_dropped": "5/69",
"recall_after_judge": 0.6522,
"fa_per_100_after_judge": 13.9,
"finding_verdicts": {
"on_vulnerability_pushes": {
"protected": 90,
"public": 1
},
"on_ordinary_pushes": {
"protected": 216,
"public": 33
}
},
"headline": "Judge over prover findings: keeps 15/15 true flags, drops 5/69 false flags (recall 65.2%, FA 13.9/100)"
}