The Pre-Print Cohort Read
Heading into the print, the live cohort_analyze pull on AMAT returned n=262 historical analogs with a consensus score of 0.41. The 5-day forward median was +0.57% with IQR [-2.15%, +3.04%] and hit-rate 57%. The 10-day median was +1.12% with IQR [-2.13%, +5.90%]. The dominant 5-day feature was hy_oas (positive direction, importance 1.63).
What Actually Printed
Print-day close: $440.56, prior close $436.61. Day-over-day change: +0.90% (+3.95). Intraday range: $438.00 – $448.45.
Cohort vs. Reality — The Verdict
The +0.90% reaction is sitting inside the cohort's IQR (-2.15% to +3.04%). The cohort's central tendency held — neither the bull nor bear feature bucket fired hard enough to push the reaction into the tails.
- n=262, 5d median +0.57%, IQR [-2.15%, +3.04%]
- Conformal bucket boundaries: p10 -4.76% / p90 +7.38%
- Top 5d feature: hy_oas (positive direction, importance 1.63)
- Actual reaction: +0.90%; verdict: central tendency hold
The Calibration Lesson
For AMAT, the calibration verdict is: central tendency hold. The cohort's structured features (hy_oas 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.