Skip to content
The self-improving system

How proposed signals survive testing.

It proposes signals, tests them under a leak-free gate, and keeps every null, not-testable, and retraction in the same ledger it confirms from. A system that only ever confirmed would not be credible — so it counts what it could not prove, and changes its own mind on new evidence.

confirmednull (a finding)not testabledescriptivepending

The scoreboard grades every claim

259
claim families tracked
121
verified (confirmed)
134
null, not-testable, or retracted
5
with more than one recorded verdict

The scoreboard above grades forward-tested claim families; the mechanism ledger is a separate, wider census of every named mechanism. Across 287 named mechanisms: 130 confirmed, 126 null, 31 not-testable.

nulls (351) outnumber confirms (168) 2.1x -- we publish our nulls

Five claim families changed verdict.

These families carried more than one verdict across reruns. The ledger keeps the whole sequence, not just the last word — the trail of a system re-testing itself as corpora grow.

NBAthree in four fatigueNULL LOCALCONFIRMED LOCALView full history
MLBreliever 3in3d fatigueNULL LOCALNULL LOCALCONFIRMED LOCALView full history
MLBreliever 3in3d fatigue combinedPROVISIONALNULL LOCALView full history
MLBstaff dayafter fatigue chainNULL LOCALCONFIRMED LOCALNULL LOCALView full history
Tennisbreak point conversion by set numberNOT TESTABLECONFIRMED LOCALView full history

The graveyard is a feature

Every reject and defer is recorded, categorized, and counted. A discarded signal is honest market-efficiency evidence, not a failure to bury.

628
reject rows recorded
68
distinct signals on a reject verdict now
804
total verdict rows across all reruns

Top reject reasons: 510 asof reclaim sweep; 20 prescreen delta; 18 wf ablation · cumulative reaches 628 by 2026-07-18.

Published rerun history

Claim family ledger

Each family keeps its recorded reruns. Published effects are displayed with no cross-family ranking because their units are not recorded in this artifact.

259 of 259 families

Ask Scout about the loop
How does this system grade itself?How many candidate market signals were rejected?Do any of your findings flip verdict when you re-test them?Ask anything →