The Pre-Print Cohort Read
Heading into the print, the live cohort_analyze pull on WMT returned n=248 historical analogs with a consensus score of 0.60. The 5-day forward median was +0.22% with IQR [-2.17%, +2.18%] and hit-rate 52%. The 10-day median was +0.29% with IQR [-2.80%, +3.90%]. The dominant 5-day feature was yield_curve_state=flat (positive direction, importance 1.71).
What Actually Printed
Print-day close: $130.85, prior close $134.20. Day-over-day change: -2.50% (-3.35). Intraday range: $130.33 – $133.65.
Cohort vs. Reality — The Verdict
The -2.50% reaction sits in the cohort's lower IQR — bear bucket realized. The dominant feature (yield_curve_state=flat) didn't deliver in the direction the bull thesis required, and the analog set's negative-skew bucket is where the print landed.
- n=248, 5d median +0.22%, IQR [-2.17%, +2.18%]
- Conformal bucket boundaries: p10 -4.23% / p90 +4.07%
- Top 5d feature: yield_curve_state=flat (positive direction, importance 1.71)
- Actual reaction: -2.50%; verdict: lower IQR realization
The Calibration Lesson
For WMT, the calibration verdict is: lower IQR realization. The cohort's structured features (yield_curve_state=flat dominant) provided the directional read; the realized magnitude lands relative to that read at the bucket described above. Agent systems should retrieve the post-print cohort 24-48 hours after the close — the chart shape will have stabilized, the feature attribution sharpens, and the forward 5-10 day continuation distribution becomes actionable.