SupnWeather

The tier's journey, the tripwire state, which watched stations are healing, and the hardest stations of the recent window.

Season-change evidence pack, refreshed weekly: H16 form and benched stations, per-station bias-correction load, the live gated record against the fraction trigger, and the paper dip book as a no-risk window into tail pricing.

How far off the published high is, and what a thermometer-only baseline would have missed.

Every forecast promises a 50% window (p25–p75). Split history into what landed below, inside and above: each side should sit near 25%. Too much below means forecasts run warm; too much above, cold.

Polymarket settles on buckets (“exactly 28°”, “≥29°”), so this scores the full probability curve the trading layer bets with against a bland same-centre baseline. Zero mass on the truth must stay at 0%.

The champion (12-member analog pool) against a 24-member shadow candidate, scored on the same settled outcomes before anything is promoted. Bucket shape is the engine's weakest pillar; a wider pool is the lever. The experiment writes this scoreboard the moment it starts.

The bias-correction layer's candidate product (corrected centre and band), scored on the same settled outcomes as the raw view. The site publishes the raw number; this is the evidence board for whether the correction earns its keep. Shadow MAE above raw MAE means the correction is hurting.

Which correction method prices current editions, whose adjustments moved this week, how often the peak gate engages, and the warm-skew tripwire's daily walk. Every number re-derivable from the ledgers.

How far ahead each forecast was issued. Physics makes error grow with distance; the job is keeping the band balanced at every distance, where long-lead bias likes to hide.

Every forecast blends an external daily-max estimate into the analog centre: the human-issued TAF TX, an NWP model, or nothing at long lead. Each lane is scored separately, with the prior's own error beside the analog's — the two numbers that say which side of the blend is sick. Last 14 days; “unrecorded” is the pre-prior era.

Every engine change gets its own fingerprint. Everything published under one version groups into one row: a before/after of every change, scored on real outcomes.

Same engine, different difficulty. Hardest rows are volatile airfields; sharpest are steady climates. Minimum 100 scored editions to rank.

Clear skies, overcast and storms behave differently. The worst row is where new features pay most.

Distributions grouped by when they were written. After any engine change, the newest rows show the verdict while it is still news.

Every bucket probability ever published, grouped by claimed size and checked against reality. Predicted 20%, happened 21% = calibrated. Gaps beyond ±5% mean confidence needs shrinking.