The calls, graded
A call is a dated, falsifiable statement with our probability attached and the command that decides it. On the grading date the command is run on the fresh export, the result is pasted in, and the tag flips. Nothing is edited afterwards; an ambiguous rule is graded against us. The full text of every call is on the calls page.
| call | the claim | we said | graded on | result |
|---|
The settled weeks
The weekly scorecard, kept to the weeks that have settled entries. The favorite rule buys Yes the first time a bracket's midpoint sits between 65c and 90c, at the ask that was resting plus Kalshi's taker fee, and holds to settlement. "Day before" is the day-ahead entry; "same day" the intraday one. Per contract is the mean over settled entries, in cents, and a week with under 20 settled entries cannot decide anything.
| week of | entered | entries | settled | paid | mean ask | per contract | median size at ask |
|---|---|---|---|---|---|---|---|
| reading… | |||||||
The dead brackets: the ones the station's confirmed running extreme had cleared by a full degree when the robot read them. The last column is the observation feed's error rate, live: brackets called dead that settled Yes anyway.
| week of | dead brackets | book reads | median at 1c | reads with a stale bid | settled Yes anyway |
|---|---|---|---|---|---|
| reading… | |||||
the record begins with the robot's first read on 2026-09-18, so the week of Sep 14 holds only Sep 18–20; the live tables with every week, settled or not, are on the scorecard.
The desk that started this
From July 24 to September 8, 2026, this site was a forecast desk: public National Weather Service guidance turned into a probability for every Kalshi temperature contract, compared with the price, and published when they disagreed. Every published number was scored after settlement against the National Weather Service's Daily Climate Report for the station the market names, head to head with the price on the same markets. That report was Kalshi's settlement source through the markets of 2026-08-13; from 2026-08-14 Kalshi settles on The Weather Company's reported figure for the same station, so the desk's record from 2026-08-14 to 2026-09-08 is graded on the government's report for that station rather than on Kalshi's source.
The money view makes the same point in cents. One contract on every published forecast, the first per settled market, at the execution price recovered from that forecast's own logged quote, held to settlement:
| strategy | total | per contract | 95% day-clustered | win rate |
|---|---|---|---|---|
| The forecast's side, as a taker (Yes at the ask, No at the bid, plus the fee) | −$147.57 | −4.02c | −5.14c to −3.00c | 42.4% |
| The forecast's opposite side (the other side of the same spread) | −$97.44 | −2.66c | −3.74c to −1.54c | 57.3% |
| The forecast's side, resting at the far edge of the spread, no fee, always filled (maker best case) | +$34.17 | +0.93c | −0.19c to +2.01c | 42.4% |
3,669 forecasts. The desk's own model expected +20.4c a contract on them, on average; the realized result is the round-trip friction, a median half-spread of 1c plus the fee. The direction added nothing, on either side.
The desk was closed on September 17, 2026. What survived is the measuring: the logger that had been reading the ladders with no model kept reading them. Its first live week, 11–15 September, is below, taken from the closing research note; those rows are not in the database the scorecard reads, so the scorecard begins with markets dated 2026-09-18.
| the first live week, 11–15 September (research note), at the logged ask plus the fee | markets | per contract | 95% CI | median contracts at the ask | a day at the ask |
|---|---|---|---|---|---|
| 65–90c the day before (the favorite rule) | 26 | −4.6c | [−26.6, +13.8] | 17 | $90 |
| 65–90c the same day | 193 | +1.2c | [−1.9, +5.4] | 25 | $1,144 |
| 80–90c the same day | 118 | +3.1c | [−0.9, +7.1] | 33 | $977 |
| 90–95c the same day | 106 | +1.8c | [−0.3, +3.8] | 46 | $2,018 |
47,857 reads on 1,200 markets over five days, every bracket of all forty ladders. Five days cannot decide a sign; the size decides the worth, and the day-ahead rule was closed by capacity at $90 a day.
Where the numbers come from
The calls are graded by the commands they name, on an export of the database (agents/export_ledger.py). Each grading's full printout is published as a plain-text receipt, linked from its call on the calls page. The settled weeks are scorecard_views.sql, a materialized view over the ladder logger's rows and the outcomes, refreshed hourly. The retired desk's record is the closing research note in the repository, RESEARCH_2026-09-10.md, every table of which names the script that produced it and can be re-run on the archived export: desk-versus-market Brier on identical reads with day-clustered bootstrap intervals (agents/replay.py), the money view (agents/exp_pnl.py), and the favorites at the real ask (agents/exp_favorites.py).