Why KELLY can be stronger here
KELLY is designed to win by being scoreable: every forecast should connect to source evidence, causal assumptions, falsifiers, settlement, calibration, replay, and memory lineage.
why it mattersA forecast platform is only as good as its ability to be wrong in public, adjust from reality, and improve the next forecast without hiding the chain.
sector edgeShows air-quality pressure, recall pressure, and public-data recency.
best claim boundaryKELLY should be called better only where its scorecards, calibration, replay receipts, and source coverage outperform alternatives. This page is built to make that measurable.
Where the proof lives
proofSource plan: the approved feed rows on this page
proofForecast method: the doctrine timeline on this page
proofAuthority evidence: Authority Index and replay receipts
proofScore evidence: settlement and calibration records
proofSystem evidence: Brain Fleet, generality evidence, and advanced proof labs
Professional layout pattern
The lab layout follows successful product patterns: fast first read, watchable objects, citations beside claims, source freshness, score history, and direct proof links.
patternCitation-forward answer pattern: put sources and proof next to claims.
patternForecasting track-record pattern: keep probability, resolution rule, score, and history together.
patternWatchlist pattern: let users inspect a saved set without writing ground truth.
patternAlert/status pattern: show what changed, what is stale, and what KELLY is watching.
Research references
TradingViewCharts, alerts, screeners, replay, multi-chart layouts, and fast command/search patterns make market work feel immediate. MetaculusForecast questions need clear resolution rules, track records, scoring, calibration, and aggregation history. Windy / Windy.appWeather users need maps, layers, local points, alerts, history, model comparison, and fast location context. PerplexityAnswer users expect citations beside claims, follow-up context, and checkable source trails.
KELLY's specialized forecast method
Air quality, recalls, environmental pressure, public records, strict non-medical boundary, closure and calibration.
1Approved source intake only
2Tag source, freshness, domain, and authority
3The Book of Why: ask what caused the change, what would have happened otherwise, and what evidence can falsify the causal story
4Thinking in Systems: map feedback loops, delays, stocks, flows, constraints, and downstream effects
5Thinking, Fast and Slow: separate fast pattern recognition from slower deliberate verification
6Superforecasting: start with base rates, update incrementally, keep probabilities explicit, and score the forecast later
7Thinking in Bets: treat every forecast as a wager against reality with a clear settlement rule
8Build causal pressure nodes and forecast cones
9Separate KELLY forecast from user forecast
10Track falsifiers, uncertainty, and competing explanations
11Close against reality
12Score calibration and error direction
13Apply continuous micro-adjustments after settlement to improve future accuracy
14Create replayable memory evidence when eligible
What this lab is for
Showing real public records while refusing diagnosis or medical advice.
safe claimShows air-quality pressure, recall pressure, and public-data recency.
boundaryNo medical advice, diagnosis, treatment, or personal safety instruction.
Live proof status
proof score35 / early
visible cells0
readiness score0%
sources wired2/5
public writesblocked
Proof links
Every health-signal view should show public source, freshness, location/event scope, and non-medical boundary.
Approved source plan
| source | status | cost | role |
|---|
Open-Meteo Air Quality
open-meteo-air-quality |
wired |
free_no_key |
No-key air-quality observations for PM2.5, PM10, ozone, nitrogen dioxide, carbon monoxide, and UV where coverage exists. |
OpenAQ
openaq |
available |
free_key_limited |
Optional air quality observations. Coverage varies by location. |
openFDA
openfda |
available |
free_limited |
Food/drug/device enforcement and adverse-event data. API key is optional for higher limits. |
NASA FIRMS
nasa-firms |
available |
free_key |
Wildfire hotspot feed. Optional key-based environmental shock source. |
OpenAI
openai |
wired |
paid_optional |
Only for narrative phrasing. The proof engine does not require an LLM. |
User questions this lab can inspect
| question lane | plain question | node |
|---|
| Air quality |
Is air quality pressure rising? |
HEALTH:AIR_QUALITY_PRESSURE |
| FDA recalls |
Are FDA recall signals rising? |
HEALTH:FDA_RECALLS |
| Smoke/fire |
Is smoke or fire pressure rising? |
HEALTH:SMOKE_PRESSURE |
| Data recency |
Is the data fresh enough? |
HEALTH:DATA_RECENCY |
| Overall risk |
Is public-health signal pressure rising? |
HEALTH:RISK |
Default focuses
| focus | meaning | context |
|---|
| New York |
air quality and recall context |
40.7128, -74.006 |
| Los Angeles |
air quality and wildfire-smoke context |
34.0522, -118.2437 |
| Chicago |
air quality and recall context |
41.8781, -87.6298 |
| Houston |
air quality and public-health context |
29.7604, -95.3698 |
| Phoenix |
air quality and heat context |
33.4484, -112.074 |
Causal pressure map
HEALTH:AIR_QUALITY_PRESSUREHEALTH:FDA_RECALLSHEALTH:SMOKE_PRESSUREHEALTH:DATA_RECENCYHEALTH:RISK
causal linkHEALTH:AIR_QUALITY_PRESSURE -> HEALTH:RISK
causal linkHEALTH:FDA_RECALLS -> HEALTH:RISK
causal linkHEALTH:SMOKE_PRESSURE -> HEALTH:AIR_QUALITY_PRESSURE
causal linkHEALTH:DATA_RECENCY -> HEALTH:RISK
Boundary receipt
{
"readOnly": true,
"publicUserWriteAllowed": false,
"noAdviceSubstitute": "No medical advice, diagnosis, treatment, or personal safety instruction.",
"noClaimOfPerfectPrediction": true,
"proofRequiredForEveryForecast": true
}