The Pre-Print Cohort Read
Heading into the print, the live cohort_analyze pull on CSCO returned n=234 historical analogs with a consensus score of 0.51. The 5-day forward median was -0.02% with IQR [-3.97%, +2.85%] and hit-rate 50%. The 10-day median was -0.51% with IQR [-4.76%, +2.78%]. The dominant 5-day feature was sector_etf=XLU (negative direction, importance 2.10).
What Actually Printed
Print-day close: $101.87, prior close $99.29. Day-over-day change: +2.60% (+2.58). Intraday range: $99.29 – $102.01.
Cohort vs. Reality — The Verdict
The +2.60% reaction is sitting inside the cohort's IQR (-3.97% to +2.85%). The cohort's central tendency held — neither the bull nor bear feature bucket fired hard enough to push the reaction into the tails.
- n=234, 5d median -0.02%, IQR [-3.97%, +2.85%]
- Conformal bucket boundaries: p10 -6.73% / p90 +5.78%
- Top 5d feature: sector_etf=XLU (negative direction, importance 2.10)
- Actual reaction: +2.60%; verdict: central tendency hold
The Calibration Lesson
For CSCO, the calibration verdict is: central tendency hold. The cohort's structured features (sector_etf=XLU 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.