Made on
Aug 2, 2026
Price at call
$990.29
6-month call
Bear -12.1%
Target by Feb 2027
$870.00
Great value below
$450.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-12.1% to $870.00
Predicted High
$1,010.00
at 1 month
Predicted Low
$870.00
at 6 months
Max Drawdown (predicted)
-12.1%
Forecast
The masterbrain trajectory — 7 dated checkpoints. Short rungs (2w, 1m) show the typical range as the primary claim; point calls run from 2 months out. Every claim still gets graded. Predicted Aug 2, 2026 12:40 am
Bear
GEV trends lower to
$870.00
(-12.1% from $990.29)
by Feb 2027.
ride-then-fade
ThesisGEV is deeply overvalued on fundamentals but sustained by a powerful AI-power/energy-transition narrative with high beta and momentum. Near-term the cult narrative holds and the neutral regime allows drift, but over 6 months some valuation gravity plus post-earnings fatigue pulls it modestly lower toward the deterministic baseline without full mean reversion.
Invalidated ifA decisive break above 1080 on strong volume (narrative reacceleration) or a break below 850 (thesis intact); a hawkish macro shock crushing high-beta names would also invalidate the gentle-drift path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $990.29 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 2, 2026 | — | $990.29 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 16, 2026 | $874.97–$1,105.61 typical range · internal point $1,002.00 | — | ±11.6% | 6/10 | post-wobble stabilization, narrative intact, neutral regime drift |
| What actually happened: closed $1,063.25 on Aug 14, 2026 = +7.4% vs the call (predicted +1.2%) · direction MISS (called flat, was up) · off by 6.2 pp · accuracy 4/10 · typical range ±11.6%: inside the band · S&P +4.7% over the same window — lagged it | ||||||
| 1 month | Sep 2, 2026 | $823.17–$1,157.41 typical range · internal point $1,010.00 | — | ±16.9% | 5/10 | AI-power theme buoyancy, no earnings catalyst |
| What actually happened: closed $898.53 on Sep 1, 2026 = -9.3% vs the call (predicted +2.0%) · direction MISS (called flat, was down) · off by 11.3 pp · accuracy 4/10 · typical range ±16.9%: inside the band · S&P +1.9% over the same window — lagged it | ||||||
| 2 months | Oct 2, 2026 | $985.00 | — | -0.5% | 4/10 | pre-earnings positioning, valuation friction begins |
| What actually happened: closed $987.45 on Oct 1, 2026 = -0.3% vs the call (predicted -0.5%) · direction HIT (called flat, was flat) · off by 0.3 pp · accuracy 10/10 · S&P +2.4% over the same window — beat it | ||||||
| 3 months | Nov 2, 2026 | $950.00 | — | -4.1% | 4/10 | Q3 print risk, high-beta sensitivity to any rate wobble |
| 4 months | Dec 2, 2026 | $920.00 | — | -7.1% | 4/10 | valuation gravity, narrative fatigue after another quarter |
| 5 months | Jan 2, 2027 | $895.00 | — | -9.6% | 3/10 | year-end profit taking on 2026 winners |
| 6 months | Feb 2, 2027 | $870.00 | — | -12.1% | 3/10 | partial convergence toward deterministic baseline |
Why ranges on the short rungs?
A 102-prediction trial (2026-07-21) showed 2-week point calls carry no information here —
three prompt formulations all lost to simply predicting zero — while the stock's own
volatility scale (σ×√t) described those windows well. So the short rungs claim what's
actually knowable: the typical travel, with earnings timing flagged where the variance
will come from. The internal point calls keep being generated and graded to map where
real skill begins. Full evidence: stocks/predictions/V0.5-DESIGN.md §8.
Deterministic control (v0.3 value line) targets $833.62 (-15.8%) — both lines get graded at every checkpoint, so the brain has to beat the formula, not just replace it. Brain: claude-opus-4-7.
Weaknesses
No weaknesses recorded for this run.All inputs present, no fallbacks used — nothing to flag.
Equation Inputs
Everything feeding the v0.6.0 model — value anchors, the stock's own price behaviour, and the tunable knobs.Value anchors (from deep analysis)
| Price at call | $990.29 |
| Composite fair value | $234.58 |
| Signal-adjusted fair value | $242.58 |
| DCF fair value | $126.62 |
| Anchored-PE fair value | $638.82 |
| Buy-below (value lens) | $450.00 |
| Value net score | -82 |
| Value confidence | 8 / 10 |
| Quality net score | +51 |
| Memo confidence | 8 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 63.0% 3m 58.5% 6m 54.2% |
| Daily σ (realism noise) | 3.7% |
| Beta vs S&P 500 | 1m 2.18 3m 2.18 5m 2.12 |
| Trailing 6-month return | 38.0% |
Knobs (equation params)
| ladder | ["w2","m1","m2","m3","m4","m5","m6"] |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | {"w_dcf":0.5,"k_qual":0.200000000000000011102230246251565404236316680908203125,"reach_6m":0.450000000000000011102230246251565404236316680908203125,"coh_floor":0.5,"conf_gain":0.059999999999999997779553950749686919152736663818359375,"noise_phi":0.84999999999999997779553950749686919152736663818359375,"conf_floor":0.40000000000000002220446049250313080847263336181640625,"w_composite":0.5,"noise_window":"3m","flat_band_pct":5,"horizon_months":6,"noise_sigma_fallback":0.01499999999999999944488848768742172978818416595458984375} |
| Neutral band (%) | 5 |
| earnings_brief | v1 |
| prompt_version | p1 |
| control_version | v0.3.0 |
Version & Tech Chain
What produced this prediction — stamped on the record so versions can be compared by success rate later.
Model
v0.6.0
#271041f8fcd5 Tech composition (what this version is built from)
| # | Process | Kind | Group |
|---|---|---|---|
| 1 | Synthesis valuation-synthesis |
deterministic | final |
| 2 | Scenario Analysis scenario-valuation |
deterministic | valuation |
| 3 | Valuation / Mispricing ext-lens-value |
llm | extended |
| 4 | Company Quality ext-lens-quality |
llm | extended |
| 5 | Forensic Memo (combiner) ext-forensic-memo |
llm | extended |
| 6 | Classification company-classification |
llm | foundation |
| 7 | Live Quote fmp-quote |
data | market-data |
Inputs used (the runs that fed this prediction)
| Upstream process | Ran | Lag | Run id |
|---|---|---|---|
company-classification |
Aug 2, 2026 | freshest | GEV-20260802-000311-333b |
ext-forensic-memo |
Aug 2, 2026 | freshest | ext-GEV-20260802-002813-27ac |
ext-lens-quality |
Aug 2, 2026 | freshest | ext-GEV-20260802-002813-27ac |
ext-lens-sentiment |
Aug 2, 2026 | freshest | ext-GEV-20260802-002813-27ac |
ext-lens-value |
Aug 2, 2026 | freshest | ext-GEV-20260802-002813-27ac |
scenario-valuation |
Aug 2, 2026 | freshest | GEV-20260802-000311-333b |
valuation-synthesis |
Aug 2, 2026 | freshest | GEV-20260802-000311-333b |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
2 frozen snapshots — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Aug 2, 2026 | v0.6.0 | Bear | $990.29 | $870.00 | -12.1% | Feb 2027 | viewing |
| Jun 25, 2026 | v0.3.0 | — | — | — | — | — | view |
Not Yet Modeled
What this v0.6.0 forecast deliberately ignores — the work ahead, in plain sight.- Scenario probabilities — one path, no bull/bear split (base_prob = 1.0).
- Intraday / sub-2-week behaviour — the first claim is at 14 days by design (EOD product).
- Position sizing / portfolio context — the path is a price claim only.