Earth & Disaster LabProof dossier

What KELLY is doing in this lab.

A concise read-only proof story for Earth & Disaster Lab: what KELLY sees, how it forecasts, what could change its mind, and where the proof lives.

score 40earlyread onlyreceipts linked

Proof story

1Earth & Disaster Lab is a read-only KELLY lens for Risk, continuity, insurance, infrastructure, emergency-planning, and public situational-awareness users.
2KELLY is designed to win by being scoreable: every forecast should connect to source evidence, causal assumptions, falsifiers, settlement, calibration, replay, and memory lineage.
3Current proof score is 40/100 (early).
4The lab currently has 3/5 source families wired or available and 0 visible authority rows.
5Every disaster view should show official source, location, risk node, freshness, and post-event closure.

What KELLY sees

Are public hazard signals increasing, and which causal chain is KELLY watching?

sourceNational Weather Service: available
sourceUSGS Earthquake Feeds: wired
sourceNOAA CO-OPS Water Levels: wired
sourceNASA FIRMS: available
sourceOpenAI: wired

How KELLY forecasts here

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 could change KELLY's mind

falsifierSource coverage drops below current 3/5.
falsifierBrain fleet health drops below quorum from current 0/4.
falsifierAuthority evidence or replay receipts fail to link from the lab proof surface.
falsifierSettlement and calibration records contradict the current forecast posture.
falsifierFresh reality data changes the base rate or causal pressure map.

Proof links

authorityIndexcompetitiveProofLabsagiReadinessbrainFleettemplates

Next useful upgrade

Score combines source coverage, brain fleet health, visible authority evidence, proof links, readiness map, and doctrine coverage. It is a product proof score, not a promise of forecast accuracy.

Causal map in this lab

DISASTER:EARTHQUAKE_MAGDISASTER:EARTHQUAKE_RECENCYDISASTER:EARTHQUAKE_DEPTH_RISKDISASTER:EARTHQUAKE_PRESSUREDISASTER:OFFICIAL_ALERTSDISASTER:WATER_LEVELDISASTER:FIRE_HOTSPOTSDISASTER:RISK
causal linkDISASTER:EARTHQUAKE_MAG -> DISASTER:EARTHQUAKE_PRESSURE
causal linkDISASTER:EARTHQUAKE_RECENCY -> DISASTER:EARTHQUAKE_PRESSURE
causal linkDISASTER:EARTHQUAKE_DEPTH_RISK -> DISASTER:EARTHQUAKE_PRESSURE
causal linkDISASTER:EARTHQUAKE_PRESSURE -> DISASTER:RISK
causal linkDISASTER:OFFICIAL_ALERTS -> DISASTER:RISK
causal linkDISASTER:WATER_LEVEL -> DISASTER:RISK
causal linkDISASTER:FIRE_HOTSPOTS -> DISASTER:RISK

Boundary receipt

{
  "readOnly": true,
  "publicUserWriteAllowed": false,
  "noAdviceSubstitute": "No emergency guidance, no evacuation instruction, and no certainty from sparse sensors.",
  "noClaimOfPerfectPrediction": true,
  "proofRequiredForEveryForecast": true
}