{
  "rule": "flag when p(class = deliberately_malicious) >= class_malicious OR p(scope = yes) >= scope",
  "frozen": {
    "class_malicious": 0.9,
    "scope": 0.9,
    "fitted_on": "English/Python-heavy dev set, <= 5% false alarms; used for every result in the card"
  },
  "multilingual_option": {
    "class_malicious": 0.9,
    "scope": 0.05,
    "fitted_on": "a 10% repo-level dev split of the 14-language set, <= 5% false alarms",
    "effect": "on the other 90%: recall 421/443 (95%) at 43/1900 (2.3%) real false alarms, vs 90% at 0.5% with the frozen thresholds"
  },
  "advice": "fit thresholds on a sample of your own data (a few hundred benign items and a few dozen known-bad ones) for your false-alarm budget"
}