The Pre-Print Cohort Read
Heading into the print, the live cohort_analyze pull on HD returned n=277 historical analogs with a consensus score of 0.00. The 5-day forward median was +1.16% with IQR [-3.53%, +4.20%] and hit-rate 58%. The 10-day median was +0.38% with IQR [-6.20%, +5.52%]. The dominant 5-day feature was pct_off_ath (positive direction, importance 1.21).
What Actually Printed
Print-day close: $299.81, prior close $297.51. Day-over-day change: +0.77% (+2.30). Intraday range: $297.30 – $303.78.
Cohort vs. Reality — The Verdict
The +0.77% reaction is sitting inside the cohort's IQR (-3.53% to +4.20%). The cohort's central tendency held — neither the bull nor bear feature bucket fired hard enough to push the reaction into the tails.
- n=277, 5d median +1.16%, IQR [-3.53%, +4.20%]
- Conformal bucket boundaries: p10 -14.44% / p90 +12.53%
- Top 5d feature: pct_off_ath (positive direction, importance 1.21)
- Actual reaction: +0.77%; verdict: central tendency hold
The Calibration Lesson
For HD, the calibration verdict is: central tendency hold. The cohort's structured features (pct_off_ath 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.