overnight drift: long MSFT at close, exit next close (earnings: Microsoft Just Had Its Best Quarter Since 1991) [skipped at close: outranked — mat 86 long lost to mat 89 long (decision 24704) for S4 MSFT exiting 2026-10-02]
Signal: wrong for the holding window — MSFT didn't continue higher after the bullish earnings read; it fell from 520.04 to 512.82, dropping through the prior close of 513.15, so this was a reversal, not merely a stall. Timing: the entry was taken after a +1.33% move off the prior close (and +0.63% in the preceding 30 minutes), i.e. at the top of the pop; the data doesn't show how old the article was or how long the position was held, so whether the news itself was stale can't be settled here. Exit: realized −1.39% against a best of +0.47% and worst of −1.47%, so the exit was within 8 bps of the worst point and captured essentially none of the small upside that existed — the dominant factor is the signal failure (full reversal), with late timing compounding it.
📖 Glossary
S1 primary — trades the alert's primary ticker in the direction the article itself indicates; exits at the same day's close.
S2 counterparty — trades the inferred counterparty ticker (weakest signal, LLM-inferred sympathy); exits at the same day's close.
S3 peer — trades an inferred peer ticker (also LLM-inferred sympathy); exits at the same day's close.
S4 overnight — holds the primary ticker from today's close to the NEXT day's close.
Verdicts are decided top-to-bottom, first match wins; REPRICING is also the fallback when nothing else matches (2026-08-08 #220).
UNKNOWN — a needed price input (move since close or move in the last 30m) is missing.
PRICED — |move since previous close| ≥ 2.0%: already reflected in price.
REPRICING — |move in the last 30m| ≥ 0.5%: the tape is actively moving on it. Also covers a quieter move — |move since previous close| in [1.0, 2.0) with a quiet last-30m tape: still developing, not yet priced.
FRESH — |move since previous close| < 1.0%: a genuinely new move.
materiality — how market-moving the story was judged, 0-100 — alerts require materiality ≥ 70.
