Made on
Aug 9, 2026
Price at call
$124.85
6-month call
Bear -5.1%
Target by Feb 2027
$118.50
Great value below
$108.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-5.1% to $118.50
Predicted High
$125.80
at 1 month
Predicted Low
$118.50
at 6 months
Max Drawdown (predicted)
-5.1%
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 9, 2026 1:01 am
Bear
DUK trends lower to
$118.50
(-5.1% from $124.85)
by Feb 2027.
ride-then-fade
ThesisDUK trades above composite fair value with negative value/quality lenses, but modest risk-on sentiment and a recent Q2 beat support near-term resilience before value gravity slowly pulls the price toward the low-$120s to high-$110s.
Invalidated ifA break above $130 on data-center demand upgrades, or below $115 on rate-case setbacks, would falsify this path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $124.85 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 9, 2026 | — | $124.85 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 23, 2026 | $120.13–$129.57 typical range · internal point $125.40 | — | ±3.8% | 6/10 | Sentiment tailwind and low beta keep drift modestly positive |
| What actually happened: closed $119.85 on Aug 21, 2026 = -4.0% vs the call (predicted +0.4%) · direction HIT (called flat, was flat) · off by 4.5 pp · accuracy 8/10 · typical range ±3.8%: OUTSIDE the band · S&P -1.1% over the same window — lagged it | ||||||
| 1 month | Sep 9, 2026 | $118.02–$131.68 typical range · internal point $125.80 | — | ±5.5% | 5/10 | Risk-on regime persists, no catalyst to reprice |
| 2 months | Oct 9, 2026 | $124.20 | — | -0.5% | 5/10 | Value gravity begins as sentiment cools into fall |
| 3 months | Nov 9, 2026 | $122.50 | — | -1.9% | 5/10 | Q3 print approaches, positioning gets more cautious |
| 4 months | Dec 9, 2026 | $121.00 | — | -3.1% | 4/10 | Rate normalization and fair-value pull weigh on utility |
| 5 months | Jan 9, 2027 | $119.50 | — | -4.3% | 4/10 | Anchored PE and composite FV exert steady drag |
| 6 months | Feb 9, 2027 | $118.50 | — | -5.1% | 4/10 | Convergence toward deterministic baseline near $118 |
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 $118.01 (-5.5%) — 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
0 blocking · 1 degraded · 1 note — follow the chain top-down (cause → effect).-
Degraded
[critical] High debt risk — interest coverage dangerously low or refinancing needed
-
Note
Valuation anchor absent: dcf.
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 | $124.85 |
| Composite fair value | $108.94 |
| Signal-adjusted fair value | $114.17 |
| DCF fair value | — |
| Anchored-PE fair value | $104.63 |
| Buy-below (value lens) | $108.00 |
| Value net score | -56 |
| Value confidence | 7 / 10 |
| Quality net score | -12 |
| Memo confidence | 7 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 15.9% 3m 19.0% 6m 17.4% |
| Daily σ (realism noise) | 1.2% |
| Beta vs S&P 500 | 1m -0.48 3m -0.43 5m -0.26 |
| Trailing 6-month return | 1.2% |
Knobs (equation params)
| ladder | Array |
| llm_model | claude-opus-4-7 |
| max_tokens | 3000 |
| control_knobs | Array |
| 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 9, 2026 | freshest | DUK-20260809-002341-4d34 |
ext-forensic-memo |
Aug 9, 2026 | freshest | ext-DUK-20260809-004954-afc1 |
ext-lens-quality |
Aug 9, 2026 | freshest | ext-DUK-20260809-004954-afc1 |
ext-lens-sentiment |
Aug 9, 2026 | freshest | ext-DUK-20260809-004954-afc1 |
ext-lens-value |
Aug 9, 2026 | freshest | ext-DUK-20260809-004954-afc1 |
valuation-synthesis |
Aug 9, 2026 | freshest | DUK-20260809-002341-4d34 |
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 9, 2026 | v0.6.0 | Bear | $124.85 | $118.50 | -5.1% | Feb 2027 | viewing |
| Jul 8, 2026 | v0.3.0 | Neutral | $128.22 | $126.34 | -1.5% | Jan 2027 | 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.