Method and acceptance tests (UAT)

Pipeline

Articles → driver signals (Jev) → monthly shares and momentum → insight cards (Claude interprets, Jev checks support) → numeric projections (1, 3 years) or scenarios (5, 10 years) → essays (Claude) → reviewed on 8 Jev criteria, rewritten if they fail → published → predictions scored in a ledger when due.

UAT results 2026-10-09 09:15

IDTestValueLevel (1–5)Result
U1Data coverage0.9134 / 3Pass
U2Signal accuracy (mean F1)0.8565 / 3Pass
U3Volume effect (max |r|)11 / 3Fail
U4Backtest (3-month direction)01 / 3Fail
U5Card grounding (Jev)01 / 3Fail
U6Essay quality (lowest of 8 Jev criteria)01 / 3Fail
U7Cross-horizon consistency (Jev)01 / 3Fail
U8Pages and menu (passed / 4)11 / 5Fail

Essay review scale (Jev, 5 levels)

Criterion12345
GroundednessClaims cite no insight cards or dataFew claims are tied to cards; most are assertionAbout half the claims cite cards or indicatorsMost claims cite specific cards or indicator valuesEvery substantive claim cites a card number or indicator value
SpecificityOnly vague generalitiesMostly general, a few concrete itemsSome concrete actors, numbers or datesMostly concrete actors, mechanisms and magnitudesConcrete actors, mechanisms, magnitudes and dates throughout
FalsifiabilityNothing could be checked laterOne loosely checkable statementA few checkable statements without thresholdsSeveral checkable predictions with dates or thresholdsClear indicators, thresholds and dates that would confirm or refute the forecast
ConsistencyContradicts itself or the dataSome internal tensions left unexplainedMostly consistentConsistent, with tensions explainedFully consistent and explains how this horizon follows from the shorter ones
UncertaintyStates the future as certainRare hedges, no probabilitiesSome probabilities or rangesProbabilities or ranges for the main claims and alternativesExplicit probabilities summing sensibly, ranges, and what would change them
NoveltyOnly restates common headlinesMostly common viewsSome non-obvious connectionsSeveral non-obvious cross-domain connectionsDistinctive, data-driven insight not found in typical commentary
ReadabilityHard to followDense or disorganisedReadable with effortClear and well organisedVery clear, plain language, easy to follow
BalanceOne-sidedMostly one-sidedMentions both opportunities and risks brieflyWeighs opportunities and risksWeighs opportunities, risks and who gains or loses, fairly