voidly
Active-learning candidate #1833

CA CA · Invalid Date

The classifier predicted 54.8% probability of censorship for CA on Invalid Date — sitting just 4.8pp from the 0.5 decision threshold. Your label here closes the loop.

Probability
55%
above 0.5
Distance from 0.5
4.8pp
uncertainty gap
Resolution
resolved
resolved wrong
Consensus need
3+ votes
independent reviewers
Why this candidate was flagged
  • · very close to threshold
  • · already resolved as wrong

Top SHAP contributions

SHAP attribution unavailable for this candidate — the 7-day forecast endpoint did not return top_features. See the per-country forecast at /atlas/forecast/ca for the full feature stack.

Source: /v1/forecast/CA/7day

Recent incidents in CA

Suggest a label

Pick the outcome that actually happened on Invalid Date in CA. Anonymous; no login required. Three independent reviewers must agree before a label is promoted into the next retrain dataset.

What actually happened on 2026-05-31#dbscan_flip in CA?

0/2000 characters. The full text is preserved in the audit log; only PII (email, IP) is stripped before consensus.

Stored ONLY in the append-only audit log. Stripped from the consensus file. Never exposed via any read endpoint.

POST /v1/sentinel/active-learning-submit-label

Related