Calibration

Postmortem.

Every signal is checked against what actually happened — did the price move in the direction the thesis predicted? Pillars whose reads consistently prove out earn more weight in future scoring; those that don't get a higher bar to clear before they influence decisions.

Conviction thresholds by pillar
PillarThreshold60d accuracyReadsUpdated
P10.7002026-05-04
P20.7002026-05-04
P30.7002026-05-04
P40.7002026-05-04
P50.7002026-05-04

Pillars with fewer than 20 scored reads keep the default threshold. Thresholds recalibrate on the 1st of each month.

Top false positives · 30d
  • NOWP4 · positive

    realized -7.6% · scored 2026-08-08

  • PEGAP5 · positive

    realized -3.4% · scored 2026-08-08

  • WDAYP3 · negative

    realized +3.8% · scored 2026-08-08

  • PEGAP5 · positive

    realized -3.4% · scored 2026-08-08

  • NOWP3 · positive

    realized -7.6% · scored 2026-08-08

Top missed-opportunity tickers · 30d
  • WDAY · neutral

    realized +13.2% · read was neutral · scored 2026-08-12

  • FRSH · neutral

    realized +12.2% · read was neutral · scored 2026-08-12

  • FRSH · neutral

    realized +12.2% · read was neutral · scored 2026-08-12

  • PANW · neutral

    realized -11.7% · read was neutral · scored 2026-08-13

Outcome totals · all-time

TP

0

FP

375

Neutral hit

0

Neutral miss

0

Insufficient

625

Each signal is evaluated at three horizons: 5 days, 20 days, and 90 days. The 5-day window drives threshold recalibration.