The Pre-Print Cohort Read
Heading into the print, the live cohort_analyze pull on ENB returned n=271 historical analogs with a tightness score of 0.46. The 5-day forward median was +0.08% with IQR [-3.03%, +3.39%] and hit-rate 51%. The 10-day median was +1.09% with IQR [-3.63%, +4.80%]. The dominant 5-day feature was vol_regime=high (positive direction, importance 1.47).
What Actually Printed
Print-day close: $53.45, prior close $53.99. Day-over-day change: -1.01% (-0.55). Intraday range: $53.35 – $55.14.
Cohort vs. Reality — The Verdict
The -1.01% reaction is sitting inside the cohort's IQR (-3.03% to +3.39%). The cohort's central tendency held — neither the bull nor bear feature bucket fired hard enough to push the reaction into the tails.
- n=271, 5d median +0.08%, IQR [-3.03%, +3.39%]
- Conformal bucket boundaries: p10 -5.87% / p90 +7.27%
- Top 5d feature: vol_regime=high (positive direction, importance 1.47)
- Actual reaction: -1.01%; verdict: central tendency hold
The Calibration Lesson
For ENB, the calibration verdict is: central tendency hold. The cohort's structured features (vol_regime=high 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.