Domains that changed
Per-domain HDBSCAN drift leaderboard
Weekly unsupervised clustering of per-domain feature vectors (block rate, country footprint, dominant blocking method). Drift score = L2 distance between this week and last week in the same standardized space. A higher score means the domain's blocking footprint changed more.
Domains
—
Clusters this week
—
Clusters last week
—
New clusters this week
0
| # | Domain | Status | Last → This | Drift score | Block rate | n countries |
|---|---|---|---|---|---|---|
| 1 | megakino.cat | new | C → noise | — | 92.1% | 1 |
| 2 | coconuts.co | new | C → noise | — | 33.3% | 1 |
| 3 | israeltv.to | dropped | C10 → C | — | 89.6% | 1 |
| 4 | fondationdelislamdefrance.fr | dropped | C14 → C | — | 91.7% | 1 |
| 5 | weibo.com | dropped | C5 → C | — | 100.0% | 11 |
| 6 | www.clubhouse.com | dropped | C5 → C | — | 100.0% | 11 |
| 7 | www.gayscape.com | dropped | C16 → C | — | 100.0% | 10 |
| 8 | 1337x.to | dropped | C27 → C | — | 100.0% | 9 |
| 9 | www.888casino.com | dropped | C16 → C | — | 100.0% | 10 |
| 10 | www.xnxx.com | dropped | C5 → C | — | 100.0% | 9 |
| 11 | www.youporn.com | dropped | C27 → C | — | 100.0% | 9 |
| 12 | xhamster.com | dropped | C27 → C | — | 100.0% | 9 |
| 13 | www.mysports.to | dropped | C14 → C | — | 88.2% | 1 |
| 14 | 9gag.com | dropped | C27 → C | — | 100.0% | 9 |
| 15 | abs.twimg.com | dropped | C27 → C | — | 100.0% | 9 |
| 16 | video.twimg.com | dropped | C27 → C | — | 100.0% | 9 |
| 17 | www.douyin.com | dropped | C27 → C | — | 100.0% | 9 |
| 18 | beeg.com | dropped | C16 → C | — | 100.0% | 10 |
| 19 | kickasstorrents.to | dropped | C27 → C | — | 100.0% | 9 |
| 20 | groups.google.com | dropped | noise → C | — | 100.0% | 9 |
| 21 | pbs.twimg.com | dropped | C19 → C | — | 100.0% | 8 |
| 22 | www.snapchat.com | dropped | C5 → C | — | 100.0% | 9 |
| 23 | www.bravoporn.com | dropped | C26 → C | — | 100.0% | 9 |
| 24 | www.goldenpalace.com | dropped | C26 → C | — | 100.0% | 9 |
| 25 | www.grindr.com | dropped | C26 → C | — | 100.0% | 9 |
| 26 | www.out.com | dropped | C5 → C | — | 100.0% | 8 |
| 27 | bsky.app | dropped | C5 → C | — | 100.0% | 10 |
| 28 | ilga.org | dropped | C26 → C | — | 100.0% | 9 |
| 29 | libgen.lc | dropped | C26 → C | — | 100.0% | 9 |
| 30 | libgen.li | dropped | C26 → C | — | 100.0% | 9 |
Scroll to see every column.
GET /v1/anomaly/domain-drift/leaderboard
Raw JSON of the same data
HDBSCAN drift finding
Methodology, weekly cron schedule, honest caveats about week-over-week stability
Why a separate domain-drift surface? The per-country DBSCAN at /atlas/anomaly catches country-day shape anomalies. HDBSCAN at the domain level catches global blocking-pattern changes — “is anyone blocking openai.com differently this week?” The two are orthogonal: one detects per-country novelty, the other detects per-domain novelty.
Generated: 2026-09-06T04:00:09.096680Z