Made on
Jul 28, 2026
Price at call
$17.60
6-month call
Bull +8.5%
Target by Jan 2027
$19.10
Great value below
$15.50
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+8.5% to $19.10
Predicted High
$19.10
at 6 months
Predicted Low
$17.70
in 2 weeks
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 Jul 28, 2026 12:38 am
Bull
PCG trends higher to
$19.10
(+8.5% from $17.60)
by Jan 2027.
dip-then-recover
ThesisPCG is a low-beta regulated utility trading modestly below composite fair value ($19.68) with earnings momentum (5/5 beats) and improving sentiment offsetting the wildfire liability overhang. Expect a slow grind higher toward fair value, though heavy quality/forensic red flags cap upside and keep conviction moderate in the tail.
Invalidated ifA new California wildfire event tagged to PCG equipment, adverse CPUC ruling, or breach below $16.35 bear scenario invalidates the recovery path.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $17.60 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Jul 28, 2026 | — | $17.60 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 11, 2026 | $16.70–$18.50 typical range · internal point $17.70 | — | ±5.1% | 6/10 | Low-beta drift in risk-off tape, minimal near-term catalyst |
| What actually happened: closed $17.04 on Aug 10, 2026 = -3.2% vs the call (predicted +0.6%) · direction HIT (called flat, was flat) · off by 3.8 pp · accuracy 9/10 · typical range ±5.1%: inside the band · S&P +4.4% over the same window — beat it | ||||||
| 1 month | Aug 28, 2026 | $16.29–$18.91 typical range · internal point $17.85 | — | ±7.4% | 5/10 | Sentiment tailwind from liability action slowly compounds |
| 2 months | Sep 28, 2026 | $18.10 | — | +2.8% | 5/10 | Q3 print approaching, sixth beat expectation building |
| 3 months | Oct 28, 2026 | $18.40 | — | +4.5% | 5/10 | Earnings beat likely lifts shares toward fair value |
| 4 months | Nov 28, 2026 | $18.60 | — | +5.7% | 4/10 | Post-earnings drift, wildfire season winding down reduces tail risk |
| 5 months | Dec 28, 2026 | $18.85 | — | +7.1% | 4/10 | Year-end rate-base clarity and tax-loss rotation into utilities |
| 6 months | Jan 28, 2027 | $19.10 | — | +8.5% | 4/10 | Convergence toward composite fair value, quality drag caps upside |
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 $17.40 (-1.1%) — 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 · 0 degraded · 2 notes — follow the chain top-down (cause → effect).-
Note
Valuation anchor absent: dcf.
-
Note
Valuation anchor absent: anchored_pe.
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 | $17.60 |
| Composite fair value | $19.68 |
| Signal-adjusted fair value | $19.68 |
| DCF fair value | — |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $15.50 |
| Value net score | -5 |
| Value confidence | 5 / 10 |
| Quality net score | -82 |
| 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 26.4% 3m 25.8% 6m 26.6% |
| Daily σ (realism noise) | 1.6% |
| Beta vs S&P 500 | 1m 0.04 3m -0.21 5m 0.16 |
| Trailing 6-month return | 17.7% |
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 |
Jul 28, 2026 | freshest | PCG-20260728-000553-fb1a |
ext-forensic-memo |
Jul 28, 2026 | freshest | ext-PCG-20260728-002713-19bf |
ext-lens-quality |
Jul 28, 2026 | freshest | ext-PCG-20260728-002713-19bf |
ext-lens-sentiment |
Jul 28, 2026 | freshest | ext-PCG-20260728-002713-19bf |
ext-lens-value |
Jul 28, 2026 | freshest | ext-PCG-20260728-002713-19bf |
scenario-valuation |
Jul 28, 2026 | freshest | PCG-20260728-000553-fb1a |
valuation-synthesis |
Jul 28, 2026 | freshest | PCG-20260728-000553-fb1a |
Inputs flagged 7d+ behind the freshest one may be stale relative to the rest of the analysis.
Saved History
1 frozen snapshot — the record we score once predictions mature.| Made | Model | Call | At call | Target | Exp. | Eval due | |
|---|---|---|---|---|---|---|---|
| Jul 28, 2026 | v0.6.0 | Bull | $17.60 | $19.10 | +8.5% | Jan 2027 | viewing |
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.