SMH Lens — Admission + Multi-Estimand CAR

MATURE reserved — requires externally replicated results under a versioned standard

Research classifications, not recommendations.

Does the adverse result survive issuer weighting? Issuer-weighted (E2) envelope (-12.54, +0.24): the envelope includes zero — under issuer weighting the adverse result is not distinguishable from zero at this sample; it does NOT clearly survive issuer weighting. Primary endpoint E4 (capped-ETF-weighted) envelope (-13.09, -0.01): adverse and excludes zero under the conservative envelope. Envelope = wider of the issuer-/date-cluster bootstrap CIs; the formal CGM two-way interval is reported beside it in the table.

Reading: the real E4 value sits at the 70% point of its own event-date-shuffle null — unremarkable. The null's mean is itself deeply negative (-6.97%): under this era's melt-up, sell-direction alignment is negative on randomly chosen days for these issuers, so the adverse headline appears to be era-generic direction alignment rather than event-timing information. The placebo window (+6.24% at −20d) is consistent with that reading. Extremity is read two-sided: percentiles near 0 and near 100 are both extreme. Exploratory; every cell ledger-counted under Falsification Battery v1.

The decisive cell: the discretionary class sits at the 84% point of its own date-shuffle null — no evidence that discretionary selling carries timing information that plan selling lacks, at this sample. Point estimates even run the other way (plan more adverse than discretionary in the backfill era), with every interval UNDERPOWERED and the difference envelope spanning zero — thin-but-honest. All-era sensitivity: discretionary -1.62% (shuffle 0.433), plan -2.81% (shuffle 0.433). F/M-mechanical class: 0 events — structurally empty at event level: ingestion keeps P/S codes only, so F/M/A-only filings never became events. Class = S-mass dollar majority per event day (filing-level 10b5-1 checkbox); unclassified days: 0.

Reading: the registered primary (W=60 difference) is inconclusive — the envelope spans zero. The secondary cross-lens picture is more coherent: at W=60 the outperformed-minus-underperformed difference is negative in every lens (XEG -9.1pp (excludes 0) · ZEO -2.9pp (includes 0) · GDX -5.2pp (excludes 0) · URNM -6.9pp (excludes 0)), i.e. prior-60-day winners systematically deliver more adverse aligned CARs than prior losers across unrelated sectors — consistent with a market-wide 60-day reversal structure, not event-specific information. The pattern vanishes at W=20. Secondary cells are exploratory and ledger-counted; extremity is read two-sided.

Many events, fewer stories — statistics on this page use cluster-aware inference accordingly. Linkage rule (pre-committed): same issuer within 5 trading days, or same type and lens within 3. Story-level design effect 1.49 (issuer-level effective count 92.6); with only 3 stories the story-level variance read is itself thin — both structure and variance are shown rather than choosing one. Top story carries 95.1% of event mass. Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

Sign held in 6/7 computed cells · CI excluded zero in 1/7 · breaks in: era: live (k=20) · UNDERPOWERED cells: k=60 (backfill only), vol-high (k=20 bf). Context grid pre-declared at registration; every cell ledger-counted. 449 secondary cells ledgered registry-wide; expected false positives at alpha=0.05: 22.45. Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

Matched-control-adjusted E4 (pairs fixed at the +20 selection) (secondary cells, same grid): sign held 5/5 (coherence 1.0) · breaks: none · empty (SPY-history bound): trend<0 (k=20), trend>=0 (k=20).

Median time-to-peak across qualifying types: 20 trading days — at the window edge for every qualifying type, with no half-life reached. An absolute cumulative path rises mechanically with horizon, so this pattern is what no-decay looks like under this estimator; it is not evidence of late-arriving impact. Types below the n≥15 floor, listed not plotted: M_AND_A_CLOSE (n=13), BUYBACK_ANNOUNCE (n=13), M_AND_A_ANNOUNCE (n=11), CAPACITY_CHANGE (n=10), REGULATORY_ACTION (n=9), EARNINGS_BEAT (n=9), PARTNERSHIP (n=5), GUIDANCE_CUT (n=1). Evidence freshness (this sleeve): median age 14d, 37.5% within 7d, 0.0% older than 30d. Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

The sharpest OIE question, first cut: of the covered sleeve's S-coded sale transactions, 91 are discretionary open-market and 358 carry the filing-level Rule 10b5-1 checkbox; 129 further transactions are mechanical (F withholding, M exercise, A grants). By dollar mass, discretionary S = $734,841,227 vs plan S = $590,052,676. Zero LLM involvement, zero scoring-path contact — C6 inputs untouched.

Counts are point-in-time reads of the live pipeline; the live era is never blended with the backfill era in any statistic.

Renormalization statement: posture and E3/E4 estimand weights renormalize issuer fund weights over the covered 67.15% sleeve only; no statistic on this page weights by full-fund share. Constituent weights are dated issuer disclosures, not market data.

Rounding footnote (per disposition): the issuer's disclosed weights sum to 100.01%, so the undisclosed residual computes to -0.01% — shown as measured, an artifact of the issuer's two-decimal rounding, not a data error.

Sector-ETF holdings snapshots now cover 13 SPDR funds (issuer disclosures, dated; derived statistics only). Pilot admission read for XLK: EXPLORATORY, 11/76 names covered (54.6% of weight), effective issuers 5.58. Remaining disclosure gaps, stated: IBB (different issuer endpoint) — nothing estimated in the meantime.

Question lifecycle is append-only in the registry chain: hypotheses come from exploration, confirmation runs on data that does not exist yet, retirements cite their grounds. Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

Protocol: da44ba9fae79 locked 2026-07-31 · method hash 5bff6b284b05c718
Primary endpoint: E4 capped-ETF-weighted mean CAR at tau=+20d, backfill era, conservative envelope (two-way beside; inherited)
Run recorded: registry line 182c8637e5202266 · events 557 filings → 162 deduped → 140 with estimation window → 103 directional with complete τ=+20 path
Chain: verified at build time. Registered before computation on real lens data.