Summary
Classifies URLs as phishing or benign from lexical and host features, with thresholds tuned for a low false-positive rate and a model card covering its limits.
InstituteCommunityPublic
Claims to check
- C10.4% false positives at 92% recall on a held-out week
- C2No page content fetched; URL and DNS only
Evidence submitted
- Code
- Repository at tag v1.0.0
- Model card
- Scope, data, limits
Automated checks
CHECKS / AI-PRF-0045v1.0.01 OF 1 PASSCLEAN ENV
- pass Install from README · 2 min
Checks run by the Institute on submission. A pass here is not a verdict.
Version history
- v1.0.02026-09-29Submitted
Reviews already filed
None yet. Yours will be the first on the ledger for this stage.
See them on the ledgerThe rubric, in full
- Works as briefed. Does it run from the instructions and do what the brief asks, on the test data? Must pass
- Claims match evidence. Is every claim in the write-up backed by a test, data or a demo you could rerun?
- Reproducible. Did a clean environment reproduce the reported results with the documented steps? Must pass
- Limits stated. Are failure cases and the limits of scope written down where a reader will see them?
- Responsible use. Are data sources cited and permitted, and are risks and human oversight addressed where relevant?
0 Missing · 1 Weak · 2 Meets · 3 Strong. Below Meets needs a written reason.