PREVIEW — real data, not yet part of the daily build. Unlinked page; delta baseline starts with the next daily snapshot archive.

Research Brief — ZEO

build 77c56208 · data through 2026-07-29 · methodology v5
WHAT CHANGED
WHAT MATTERS
WHAT THE EVIDENCE SAYS
WHAT REMAINS UNCERTAIN
INSPECT NEXT
ordered by trigger count — not an investment ranking
103 filings → 85 prose → 82 candidates → 82 accepted → 77 deduped → 72 matured → 50 direction-eligible
Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.
brief 9341c2ed6b7c1c31 · deterministic synthesis — no generative model · hover any sentence for its backing data fields

Evidence Decision Canvas — ZEO

build 77c56208 · data through 2026-07-29 · method b717068e17e3f09a (pre-committed clustered-inference spec)
HORIZONMEANCLUSTERED CINAIVE CIWILD CIN / ISSUERSMDE 80%STATUS
+5d+0.5%[-0.2, +1.2][-0.6, +1.5][-0.3, +1.3]50 / 81.1%DESCRIPTIVE
+10d+0.4%[-0.6, +1.4][-0.9, +1.6][-0.6, +1.3]49 / 81.4%DESCRIPTIVE
+20d-0.2%[-1.7, +1.3][-1.8, +1.4][-1.7, +1.3]47 / 82.1%DESCRIPTIVE
median 6 events/issuer · top-3 issuers 51% of sample · clustered CI is primary; naive shown for comparison

What would change this conclusion

Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

CAR panel — clustered inference + sample anatomy

Peer model vs SPY — what these CARs measure: each event's expected return is α+β·(equal-weight mean return of the other covered names in this lens), estimated over the 60 trading days before the event (gap 6, minimum 30 usable days). The peer model absorbs sector-common moves — a commodity swing that lifts every name in the lens cancels out — so the residual isolates issuer-specific reaction. A SPY-relative CAR answers a different question (movement vs the broad market) and widens whenever the sector as a whole moves; the Lab's cohort event study reports that variant. All values below are peer-model CARs in percent, direction-aligned.

HorizonMean CARCluster CI (primary)Naive CI (comparison)Sample anatomy
+5d+0.48%[-0.25%, +1.22%][-0.55%, +1.52%]50 events · 8 unique issuers · median 6.5 events/issuer · top-3 issuer share 52% · window overlap 98%
minimum detectable effect at 80% power: ±1.07%
+10d+0.36%[-0.61%, +1.35%][-0.89%, +1.61%]49 events · 8 unique issuers · median 6.5 events/issuer · top-3 issuer share 51% · window overlap 100%
minimum detectable effect at 80% power: ±1.44%
+20d-0.23%[-1.73%, +1.28%][-1.84%, +1.37%]47 events · 8 unique issuers · median 6 events/issuer · top-3 issuer share 51% · window overlap 100%
minimum detectable effect at 80% power: ±2.15%
Event-type decomposition — pooled CAR at +20d

Decomposes the pooled +20d CAR by accepted event type — shows whether the pooled effect concentrates in a single type. Cluster CI (issuer-clustered, registered machinery) where the type has ≥2 events across ≥2 issuers; thin types show mean only, badged UNDERPOWERED. MDE = minimum detectable effect at 80% power.

Event typeMean CARCluster CInIssuersBadgeMDE (80%)
OTHER_MATERIAL+0.25%[-0.72%, +1.21%]248DESCRIPTIVE±1.38%
DIVIDEND_CHANGE-1.47%[-4.93%, +1.21%]115UNDERPOWERED±4.36%
GUIDANCE_RAISE+3.20%[+2.64%, +3.76%]42UNDERPOWERED±1.11%
BUYBACK_ANNOUNCE+1.98%[-6.17%, +7.70%]33UNDERPOWERED±9.55%
CAPACITY_CHANGE-0.58%21UNDERPOWERED
EARNINGS_BEAT-8.85%21UNDERPOWERED
REGULATORY_ACTION-0.76%11UNDERPOWERED

Evidence structure

protocol 34ed4732b6e6 · registered before computation

82 filings → 72 deduped events → 13 stories → 89.8 effective (story-level design effect 0.802; issuer-level effective count 33.4). Top story 29.2% of event mass.

Story sizeMass Dominant issuerDominant type Span
2129.2%CNQOTHER_MATERIAL8d
1926.4%CNQOTHER_MATERIAL22d
1520.8%SOBOOTHER_MATERIAL13d
56.9%TRPOTHER_MATERIAL5d
34.2%IMOOTHER_MATERIAL4d
Many events, fewer stories — statistics on this page use cluster-aware inference accordingly. Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

Falsification battery · pooled CAR at +20

protocol df92008643c8 · N=1000 per null · seed 20260727 · registered before computation
TestReal value Null mean ± sdNull 2.5–97.5% Percentile of real in null
Event-date shuffle -0.23% -0.64% ± 0.86 (-2.25, +1.11) 0.679
Direction sign-flip -0.23% -0.04% ± 0.82 (-1.66, +1.56) 0.409
Pre-event placebo (−20d) +0.04% located in the date-shuffle null 0.788
Two-sided extremity, exploratory: percentiles near 0 and near 100 are both extreme; mid-range percentiles mean the real value is unremarkable within its null. All cells ledger-counted under Falsification Battery v1.

Pre-event momentum conditioning · pooled CAR at +20

protocol dfee13621c33 · median split by prior issuer-vs-peer relative momentum · registered before computation
WindowMedian rel-mom Outperformed halfUnderperformed half DifferenceEnvelope
prior 60d-1.9%-1.49% (n=21)+1.42% (n=21)-2.91pp(-6.07, +0.14)
prior 20d-1.6%+0.08% (n=21)-0.15% (n=21)+0.23pp(-2.76, +3.47)
Secondary, exploratory, ledger-counted; extremity read two-sided. A negative difference means prior outperformers deliver more adverse aligned CARs — a reversal structure, not event information.

Evidence lifecycle

protocol e02bd40cc884 · display-only · registered before computation
Type (backfill era)nPeak dayPeak |CAR|Half-life
OTHER_MATERIAL35194.28%not reached within window
An absolute cumulative path rises mechanically with horizon — a window-edge peak with no half-life is what no-decay looks like under this estimator. Types below the n>=15 floor, listed not plotted: DIVIDEND_CHANGE (n=7), BUYBACK_ANNOUNCE (n=3), GUIDANCE_RAISE (n=3), REGULATORY_ACTION (n=1), EXEC_CHANGE (n=1), CAPACITY_CHANGE (n=1), EARNINGS_BEAT (n=1). Evidence freshness: median age 20d, 12.5% within 7d, 37.5% older than 30d. Investment implication: none established — no buy, sell, or alpha conclusion is supported by this page.

Form-4 transaction taxonomy

No ingested Form-4 substrate for this lens's members (MJDS/FPI insider filings are outside current evidence scope — SEDI substrate not ingested).

Issuer table — sortable, filterable

Material event = latest accepted non-insider event. Evidence age = days since the last accepted event of any type, as of 2026-07-29. Source status reflects the most recent filing's document fetch.

TickerIssuerWeight ↕Events ↕Grade ↕Latest material eventEvidence age (d) ↕Last filingSource status
CVECENOVUS ENERGY INC.9.15%7AOTHER_MATERIAL · 2026-07-2902026-07-29primary doc fetched
SOBOSouth Bow Corp8.65%10ADIVIDEND_CHANGE · 2026-05-07832026-07-14primary doc fetched
PBAPEMBINA PIPELINE CORP8.57%11ADIVIDEND_CHANGE · 2026-07-16132026-07-17primary doc fetched
TRPTC ENERGY CORP8.50%11AOTHER_MATERIAL · 2026-07-10192026-07-14primary doc fetched
WCPRFWHITECAP RESOURCES INC.8.42%0Dnone accepted yetno filings yet
SUSUNCOR ENERGY INC8.21%17AOTHER_MATERIAL · 2026-07-2182026-07-21primary doc fetched
IMOIMPERIAL OIL LTD8.10%10AOTHER_MATERIAL · 2026-07-15142026-07-15primary doc fetched
ENBENBRIDGE INC8.04%8AOTHER_MATERIAL · 2026-05-08822026-07-14primary doc fetched
CNQCANADIAN NATURAL RESOURCES Ltd7.21%8ADIVIDEND_CHANGE · 2026-05-12782026-07-14primary doc fetched
Daily delta — 2026-07-28 → 2026-07-29

Rendered from the archived snapshots (output/synthesis/<date>_ZEO_snapshot.json) — real day-over-day changes, not recomputed history.

Grade profile — what each letter is made of

Coverage classifications, not rankings. Dimension values are medians across the names holding each grade: coverage = filings ingested · freshness = days since last event · depth = prose filings · diversity = distinct event types · price-integrity = % of last 30 trade dates with a close.

Grade A (8 names, medians)
coverage12
freshness16.5
depth9.5
diversity2
price-integrity100%
Grade D (1 names, medians)
coverage0
freshness
depth0
diversity0
price-integrity100%