Made on
Aug 9, 2026
Price at call
$52.96
6-month call
Bear -6.0%
Target by Feb 2027
$49.80
Great value below
$38.00
Model
v0.6.0
Projection vs Actual (6M history + forecast)
Forecast Change
-6.0% to $49.80
Predicted High
$53.10
in 2 weeks
Predicted Low
$49.80
at 6 months
Max Drawdown (predicted)
-6.0%
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 12:51 am
Bear
GSK trends lower to
$49.80
(-6.0% from $52.96)
by Feb 2027.
decay
ThesisGSK trades well above composite fair value ($32.68) with weak quality and negative value lens, but low beta and defensive characteristics limit downside speed in a risk-on tape. Expect modest drift lower over 6 months toward the deterministic baseline as fallen-angel lift fades and valuation gravity slowly asserts.
Invalidated ifA break above $56 on volume or a positive pipeline/M&A catalyst would invalidate the slow-fade thesis.
| Checkpointtime after the call | Datewhen it gets graded | Predictedthe claim: closing price | Current priceactual close — fills in over time | Predicted returnpredicted vs $52.96 at call | Conv.brain's confidence, 1–10 | Driverwhy the brain put the point here |
|---|---|---|---|---|---|---|
| Prediction made | Aug 9, 2026 | — | $52.96 at call | — | — | The anchor — every point below is measured from this price and date. |
| 2 weeks | Aug 23, 2026 | $50.28–$55.64 typical range · internal point $53.10 | — | ±5.1% | 6/10 | Low-beta drift, calm tape, no near-term catalyst |
| What actually happened: closed $52.41 on Aug 21, 2026 = -1.0% vs the call (predicted +0.3%) · direction HIT (called flat, was flat) · off by 1.3 pp · accuracy 10/10 · typical range ±5.1%: inside the band · S&P -1.1% over the same window — lagged it | ||||||
| 1 month | Sep 9, 2026 | $49.07–$56.85 typical range · internal point $52.60 | — | ±7.3% | 6/10 | Sentiment lift fades slightly, defensive bid holds |
| 2 months | Oct 9, 2026 | $51.80 | — | -2.2% | 5/10 | Valuation gravity begins, no earnings catalyst |
| 3 months | Nov 9, 2026 | $51.20 | — | -3.3% | 5/10 | Q3 print window, muted reaction expected |
| 4 months | Dec 9, 2026 | $50.60 | — | -4.5% | 4/10 | Year-end positioning, tax-loss pressure on laggards |
| 5 months | Jan 9, 2027 | $50.30 | — | -5.0% | 4/10 | Baseline convergence, defensive floor holds |
| 6 months | Feb 9, 2027 | $49.80 | — | -6.0% | 4/10 | Slow drift toward fair value anchor continues |
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 $50.25 (-5.1%) — 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 · 1 note — follow the chain top-down (cause → effect).-
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 | $52.96 |
| Composite fair value | $32.68 |
| Signal-adjusted fair value | $31.36 |
| DCF fair value | $37.84 |
| Anchored-PE fair value | — |
| Buy-below (value lens) | $38.00 |
| Value net score | -71 |
| Value confidence | 6 / 10 |
| Quality net score | +35 |
| 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 25.3% 3m 25.4% 6m 25.8% |
| Daily σ (realism noise) | 1.6% |
| Beta vs S&P 500 | 1m 0.08 3m -0.09 5m 0.30 |
| Trailing 6-month return | -10.5% |
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 | GSK-20260809-000707-40e6 |
ext-forensic-memo |
Aug 9, 2026 | freshest | ext-GSK-20260809-004137-753a |
ext-lens-quality |
Aug 9, 2026 | freshest | ext-GSK-20260809-004137-753a |
ext-lens-sentiment |
Aug 9, 2026 | freshest | ext-GSK-20260809-004137-753a |
ext-lens-value |
Aug 9, 2026 | freshest | ext-GSK-20260809-004137-753a |
scenario-valuation |
Aug 9, 2026 | freshest | GSK-20260809-000707-40e6 |
valuation-synthesis |
Aug 9, 2026 | freshest | GSK-20260809-000707-40e6 |
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 | $52.96 | $49.80 | -6.0% | Feb 2027 | viewing |
| Jul 7, 2026 | v0.3.0 | Bull | $53.09 | $60.87 | +14.6% | 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.