Made on
Aug 5, 2026
Price at call
$23.38
6-month call
Bull +13.3%
Target by Feb 2027
$26.50
Great value below
$21.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
+13.3% to $26.50
Predicted High
$26.50
at 6 months
Predicted Low
$22.60
at 1 month
Max Drawdown (predicted)
-3.3%
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 5, 2026 1:45 am
Bull
T trends higher to
$26.50
(+13.3% from $23.38)
by Feb 2027.
dip-then-recover
ThesisAT&T trades well below composite fair value but faces a fresh SpaceX/wireless-disruption narrative that will cap upside near-term; over 6 months value gravity partially reasserts as the disruption story matures and the risk-on tape helps, but sentiment drag prevents full convergence.
Invalidated ifBreak below $21 on heavy volume, or a concrete SpaceX direct-to-cell commercial launch degrading wireless subscriber guidance, invalidates the recovery leg.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $23.38 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 5, 2026 | — | $23.38 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 19, 2026 | $21.96–$24.80 typical range · internal point $22.90 | — | ±6.1% | 6/10 | Sentiment overhang continues, no near-term catalyst |
| What actually happened: closed $25.21 on Aug 19, 2026 = +7.8% vs the call (predicted -2.1%) · direction MISS (called flat, was up) · off by 9.9 pp · accuracy 4/10 · typical range ±6.1%: OUTSIDE the band · S&P +0.2% over the same window — lagged it | ||||||
| 1 month | Sep 5, 2026 | $21.32–$25.44 typical range · internal point $22.60 | — | ±8.8% | 5/10 | SpaceX disruption headlines still weighing |
| 2 months | Oct 5, 2026 | $23.10 | — | -1.2% | 4/10 | Stabilization as narrative digests, risk-on tape |
| 3 months | Nov 5, 2026 | $24.20 | — | +3.5% | 4/10 | Q3 print beat likely, dividend support |
| 4 months | Dec 5, 2026 | $25.10 | — | +7.4% | 4/10 | Value gravity pulls toward composite fair value |
| 5 months | Jan 5, 2027 | $25.80 | — | +10.4% | 3/10 | Year-end positioning, defensive rotation possible |
| 6 months | Feb 5, 2027 | $26.50 | — | +13.3% | 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 $26.94 (+15.2%) — 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 | $23.38 |
| Composite fair value | $32.12 |
| Signal-adjusted fair value | $32.12 |
| DCF fair value | — |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $21.00 |
| Value net score | +24 |
| Value confidence | 6 / 10 |
| Quality net score | +26 |
| Memo confidence | 6 / 10 |
| Deserved value (base) | — |
| Quality tilt | — |
| Deserved value (used) | — |
| Coherence (value × quality) | — |
Price behaviour (trailing — shapes the realism line)
| Realized volatility (annualized) | 1m 29.9% 3m 30.6% 6m 28.0% |
| Daily σ (realism noise) | 1.9% |
| Beta vs S&P 500 | 1m -0.22 3m -0.40 5m -0.36 |
| Trailing 6-month return | -11.1% |
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 5, 2026 | freshest | T-20260805-002307-cd88 |
ext-forensic-memo |
Aug 5, 2026 | freshest | ext-T-20260805-013018-71c8 |
ext-lens-quality |
Aug 5, 2026 | freshest | ext-T-20260805-013018-71c8 |
ext-lens-sentiment |
Aug 5, 2026 | freshest | ext-T-20260805-013018-71c8 |
ext-lens-value |
Aug 5, 2026 | freshest | ext-T-20260805-013018-71c8 |
valuation-synthesis |
Aug 5, 2026 | freshest | T-20260805-002307-cd88 |
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 5, 2026 | v0.6.0 | Bull | $23.38 | $26.50 | +13.3% | Feb 2027 | viewing |
| Jun 29, 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.